Close

Atlassian Intelligence designed for transparency

Our no b.s. commitment to open communication, accountability, and helping teams to use AI responsibly.

Atlassian Intelligence is designed to fast-track collaboration and empower teams to accelerate their work. And just like getting to know how to best work with your team, understanding how Atlassian Intelligence works will help teams more effectively use it. On this page, we’ll explain how our AI-powered products and features work, including what they can and cannot do, and how they contribute to the way that you experience our products. We believe that equipping you with the information on this page will help you make the most out of our products — and your teamwork. To learn more about our commitment to building technology responsibly visit our Responsible Technology Principles.

Alert grouping

How alert grouping uses Atlassian Intelligence Copy link to heading Copied! Show
  

Alert grouping by Atlassian Intelligence is powered by large language models developed by OpenAI and other machine learning models. These models include the OpenAI models described here.

Atlassian Intelligence uses these machine learning models to analyze and generate alert groups and give related suggestions (past alert groups and past alert responders) within our products based on the similarity of the alert content or the tags used. Atlassian Intelligence then uses large language models to analyze and generate natural language descriptions and content for these groups within our products.

These large language models generate responses based on your inputs and are probabilistic. This means that their responses are generated by predicting the most probable next word or text based on the data they have been trained on.

Read more about the capabilities of OpenAI’s models, or about this approach in OpenAI’s research papers.

Use cases for alert grouping Copy link to heading Copied! Show
  

Alert grouping uses Atlassian Intelligence to identify and group similar alerts together. It also helps you by identifying and recommending past similar alert groups and past alert responders (or teams of responders), based on the semantic similarity of the alert content or tags used.

When you want to escalate the alert group to an incident, alert grouping will also pre-populate all contextual information for you to review as part of the incident creation process.

We believe that alert grouping works best in scenarios where:

  • Your organization frequently encounters patterns of similar or duplicate alerts occurring at a high volume, whether experienced over a short period or a more extended time frame.
  • Your organization consistently categorizes alerts using tags.
  • Your team often finds that similar or duplicate alerts should be escalated into incidents.
Considerations when using alert grouping Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power alert grouping work, these models can sometimes behave in ways that are inaccurate, incomplete, or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on or include content that sounds reasonable but is false or incomplete. In the case of the alert groups that you see, they might not precisely reflect the semantic similarity of their tags.

We’ve found that alert grouping is less useful in scenarios where:

  • You need current and accurate information about people, places, and facts.
  • You need alert grouping to have access to information that isn’t readily available to you to properly group the alerts. Alert grouping works within the boundaries of your team’s configured roles and permissions, so you’ll only have access to groups and insights for alerts you have permission to view.
  • The alert tags used by your team are not consistent or well-maintained. Because alert grouping groups alerts based on the semantic similarity of alert titles and tags, the quality of the alert groups it generates depends on the consistency and hygiene of the alert tags used by your team and your organisation.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about ensuring that you and your team follow consistent practices in using alert tags.

Your data and alert grouping Copy link to heading Copied! Show
  

We understand you may have questions about how alert grouping uses your data. This section supplements the information available on our FAQ page

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as your alert data (alert titles, alert tags, priority, responder teams, description).
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

We process your alert data to train a version of the machine learning model to recognize patterns specific to your alerts. This version is used to serve only your experience:

  • We store the identified patterns to provide you with insights.
  • We do not use your alert data to train any LLM.

When it comes to your data, alert grouping applies the following measures:

  • Your inputs and outputs:
    • Are not available to other customers
    • Are not stored by OpenAI.
    • Are not used to improve OpenAI models.
    • Are used only to serve your experience.
  • OpenAI is a subprocessor on our list of subprocessors. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows your site's permissions. For instance, if Atlassian Intelligence groups 50 alerts based on their tags and semantic similarity and you have permission to view only 30 of them, you’ll only see those 30 in the group detail view. If you don't want your alerts to be available in response to other users in your site, please work with your org/site admin to ensure your permissions are set appropriately.

Atlassian Intelligence answers in Jira Service Management

How Atlassian Intelligence answers in Jira Service Management works Copy link to heading Copied! Show
  

Atlassian Intelligence answers is powered by large language models developed by OpenAI. These models include the OpenAI models described here.

Atlassian Intelligence uses these models to analyze and generate natural language within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, or about this approach in OpenAI’s research papers.

Use cases for Atlassian Intelligence answers in Jira Service Management Copy link to heading Copied! Show
  

The Atlassian Intelligence answers feature connects to the virtual service agent in Jira Service Management. It uses generative artificial intelligence to search across your linked knowledge base spaces and answer your customer questions.

We believe that Atlassian Intelligence answers works best in scenarios where:

  • You have a complete, up-to-date linked knowledge base that the virtual service agent can access to provide answers to customer questions using Atlassian Intelligence answers.
  • Atlassian Intelligence answers is used to respond to customer questions that:
    • Can be resolved by providing information or instructions.
    • Are covered in (or can be added to) your existing knowledge base articles.
    • Don’t usually need to be escalated to one of your agents.
Considerations when using Atlassian Intelligence answers in Jira Service Management Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power Atlassian Intelligence answers work, these models can sometimes behave in ways that are inaccurate, incomplete or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that Atlassian Intelligence answers is less useful in scenarios where:

  • You need current and accurate information about people, places, and facts.
  • You need Atlassian Intelligence answers to have access to information that isn’t readily available to you (for example, in your linked knowledge base) to properly answer your request.
  • Your knowledge base is outdated or incomplete, so searches may not be helpful.
  • The articles in your knowledge base don’t include relevant or high quality information, so the Atlassian Intelligence answers may provide less relevant information to customers based on those articles.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Proactively reviewing and updating your linked knowledge base (and the existing articles included within it) to make sure it remains complete and up-to-date.
  • Proactively reviewing the permissions and restrictions applicable to your linked knowledge base spaces to make sure Atlassian Intelligence answers has access to the right information to be useful.
Your data and Atlassian Intelligence answers in Jira Service Management Copy link to heading Copied! Show
  

We understand you may have questions about how Atlassian Intelligence answers in Jira Service Management uses your data. This section supplements the information available on our FAQ page.

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as your linked knowledge base spaces.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.
  • When it comes to your data, Atlassian Intelligence answers in Jira Service Management applies the following measures:
  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not stored by OpenAI.
    • Are not used to improve OpenAI’s models.
    • Are used only to serve your experience.
  • OpenAI is a subprocessor on our List of Subprocessors. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows the permissions and restrictions applicable to your linked knowledge base spaces. This means all pages available to customers on your Jira Service Management portal will be available through Atlassian Intelligence answers. For example, if access to a certain Confluence page is restricted and not generally available via Jira Service Management, the content from that page will not be suggested in the responses from Atlassian Intelligence answers. If you don’t want your content to be available in responses to other users in your instance, work with your org admin to ensure your permissions are set appropriately.

Automation using Atlassian Intelligence

Use cases for automation using Atlassian Intelligence Copy link to heading Copied! Show
  

Automation using Atlassian Intelligence is powered by GPT models developed by OpenAI. These models include the OpenAI models described here.

Atlassian Intelligence uses these models to analyze natural language input and generate an automation rule for you within Jira and Confluence.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated by predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, or about this approach in OpenAI’s research papers.

Use cases for automation using Atlassian Intelligence Copy link to heading Copied! Show
  

Creating automation rules is at the core of the everyday automation experience, and we want to make this even easier for you by adding Atlassian Intelligence to the automation rule builder in Jira and Confluence. Now, you can easily create automation rules by simply typing in and describing what you wish to automate, and let Atlassian Intelligence handle all the heavy lifting of creating the rule for you. Find out more about Automation using Atlassian Intelligence for Jira and for Confluence.

We believe that Automation using Atlassian Intelligence for Jira and Confluence works best in scenarios when you are not sure how to get started or want to accelerate the rule creation process.

Not sure how best to create an automation rule?

Automation rules are created by a combination of different types of components: triggers, actions, conditions, and branches. Think of components as the building blocks of a rule. To successfully create a rule with Atlassian Intelligence, your rule must at least contain both a trigger and an action. For example:

In Jira:

Every Monday, find all the tasks with a due date in the next 7 days, and send the assignee a reminder email.

When a ticket moves to Testing, assign the ticket to John Smith.

In Confluence:

  • Every Monday, find all the tasks with a due date in the next 7 days, and send the assignee a reminder email.
  • Every 6 months, archive any pages that haven’t been updated in that time. After archiving, send an email to the page author letting them know.
  • When a page is published with Product Spec in the title, create a Jira ticket to review the page with a link to the page.

In addition, for a rule to be successfully created, all its components must be supported by automation using Atlassian Intelligence. This means that any triggers, actions, conditions, or branches in your rule must be compatible with automation in Jira and/or Confluence.

Considerations for Automation using Atlassian Intelligence Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power automation using Atlassian Intelligence work, these models can sometimes behave in ways that are inaccurate, incomplete or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that automation using Atlassian Intelligence is less useful in scenarios where:

  • You need to give automation using Atlassian Intelligence access to information that isn’t readily available to you (for example, a restricted page or project) to properly answer your request.
  • You need to perform one-off tasks.
  • You need to query information from within your knowledge base.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

Automation using Atlassian Intelligence will only work with the existing set of available automation components in Jira and Confluence.

You might also want to think about being as specific as possible in what you ask Atlassian Intelligence to do, as described above.

Your data and Automation using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how Automation using Atlassian Intelligence uses your data. This section supplements the information available on our Trust Center.

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as a Jira project or a Confluence page.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, using Atlassian Intelligence for Confluence automation applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not stored by OpenAI.
    • Are not used to improve OpenAI models.
    • Are used only to serve your experience.

OpenAI is a subprocessor on our List of Subprocessors. They do not use your inputs and outputs for any purpose besides processing your request.

This feature follows the permissions in your instance. For example, if you do not have access to a specific project or page, you will not be suggested content from those assets in the response you receive. If you do not want your content to be available in responses to other users in your instance, work with your org admin to ensure your permissions are set appropriately.

Chart Insights

How chart insights uses Atlassian Intelligence Copy link to heading Copied! Show
  

Chart insights is powered by large language models developed by OpenAI. These models include the OpenAI models described here.

Atlassian Intelligence uses these models to analyze and generate natural language within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated by predicting the most probable next word or text based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, or about this approach in OpenAI’s research papers.

Use cases for chart insights Copy link to heading Copied! Show
  

Chart insights uses Atlassian Intelligence to help speed up your understanding of data in any chart in Atlassian Analytics. It does so by using the dashboard title, chart title, and chart data (including column headers and row values) to generate a natural language summary of that chart and its data. It will also aim to identify any trends or anomalies to provide you with certain insights into that chart.

We believe that chart insights work best in scenarios where:

  • Charts have many rows of data.
  • Charts have a dashboard title.
  • Charts have column headers.
  • Charts have values in all of the rows and columns.

Bar charts, line charts, and bar-line charts work best with this feature since they typically have trends, dates, and many rows of data.

Considerations when using chart insights Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power chart insights work, these models can sometimes behave in ways that are inaccurate, incomplete, or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that chart insights is less useful in scenarios where:

  • You have charts with one or just a few rows of data.
  • You have charts that are of the single value type.
  • You have charts missing titles, axis-labels, and column headers.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Double checking the accuracy of the insights with other users who may have more context on the specific data displayed in the chart.
  • Taking into account that Atlassian Intelligence is only using the context of a single chart and not the entire dashboard when providing a response.
Your data and chart insights Copy link to heading Copied! Show
  

We understand you may have questions about how chart insights uses your data. This section supplements the information available on this page

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as the data in your chart.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, chart insights applies the following measures.

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not stored by OpenAI
    • Are not used to improve OpenAI models.
    • Are used only to serve your experience.
  • OpenAI is a subprocessor on our List of Subprocessors. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature only uses information from the dashboard you have access to and have requested insights for.

Confluence quick summary

How Atlassian Intelligence summarizes pages and blogs in Confluence Copy link to heading Copied! Show
  

Summarize pages and blogs using Atlassian Intelligence is powered by LLM models developed by OpenAI. These models include the OpenAI models described here.

Atlassian Intelligence uses these models to analyze and generate natural language within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, or about this approach in OpenAI’s research papers.

Use cases for Confluence quick summary Copy link to heading Copied! Show
  

Save time and get the details you need to do your work faster by generating a quick summary of a Confluence page or blog with Atlassian Intelligence. Find out more about using Atlassian Intelligence in Confluence.

We believe that summarizing pages and blogs using Atlassian Intelligence works best in scenarios when:

  • There is a text-heavy page that takes a 5 minutes or more to read.
  • There is a lot of written content, with limited visuals and/or other formatting like expands on a page.
Considerations when summarizing pages and blogs using Atlassian Intelligence Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power summarizing pages and blogs using Atlassian Intelligence work, they can sometimes behave in ways that are inaccurate, incomplete, or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on or include content that sounds reasonable but is false or incomplete.

While we continue to build better support for macros, tables, and expand in summaries, we’ve found that summarizing pages and blogs using Atlassian Intelligence is less useful in scenarios where:

  • You need current and accurate information about people, places, and facts.
  • You need a summary of a very short Confluence page where there is not enough content.
  • You need a summary of a Confluence page where most of the content is in tables or expands.
  • You need a summary of a Confluence page with most of the content in macros.

We encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Asking Atlassian Intelligence to summarise pages that you know are heavy on text-based content.
Your data and summarizing pages and blogs using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how using Atlassian Intelligence for Confluence automation uses your data. This section supplements the information available on our Trust Center.

We process:

  • Your prompts (inputs) and responses (outputs).

  • Context from your instance relevant to your prompt, such as content from the Confluence page you want to summarize.

  • Data about how you interact with our features, such as clickstream data and the people you work with

  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, summarizing pages and blogs using Atlassian Intelligence applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not stored by OpenAI.
    • Are not used to improve OpenAI.
    • Are used only to serve your experience.
  • OpenAI is a subprocessor on our List of Subprocessors. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows the permissions in your instance. For example, if you do not have access to a Confluence page, you will not be shown this feature or be able to summarize a page using Atlassian Intelligence. If you do not want your content to be available to other users in your instance, work with your org admin to ensure your permissions are set appropriately.

Define terms using Atlassian Intelligence

How Atlassian Intelligence defines terms Copy link to heading Copied! Show
  

Defining terms using Atlassian Intelligence in Confluence and Jira is powered by large language models developed by OpenAI. These models include the OpenAI models described here.

Atlassian Intelligence uses these models to analyze and generate natural language answers within Confluence.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Use cases for defining terms using Atlassian Intelligence Copy link to heading Copied! Show
  

One of the most challenging things about consuming content in Confluence and Jira can be getting the context you need to understand what you’re reading. Abbreviations, acronyms, unfamiliar terms, and team or project-specific names can lead to a lengthy search for the information you need.

Defining terms using Atlassian Intelligence will provide the definition of company-specific terms (such as acronyms, project, system, or team names) on a page in Confluence or in an issue description in Jira. This gives users the information they need, when they need it - all whilst helping teams work better together.

Atlassian Intelligence can save you time by defining these things for you, without navigating away from what you’re reading.

If you encounter a definition that you feel is inaccurate, you can edit or add a new definition, then set the visibility to be for that page or issue, the whole space or project, or access your entire organization.

We believe that defining terms using Atlassian Intelligence in Confluence works best in scenarios when:

  • A company has multiple pages in their Confluence instance that mention, describe, or explain what a specific term is for Atlassian Intelligence to reference.
Considerations when defining terms using Atlassian Intelligence Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to define terms using Atlassian Intelligence in Confluence work, these models can sometimes behave in ways that are inaccurate, incomplete or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that defining terms using Atlassian Intelligence in Confluence is less useful in scenarios where:

  • You need current and accurate information about people, places and facts.
  • You don’t have ample context on the term inside that Confluence instance (for example, if there are no pages that mention the specific term, that term’s definition will not be accurately generated).
  • The definition requires access to Confluence content that you don't have permission to view
  • You attempt to define multiple terms instead of one individual term at a time.

In addition, in Jira, we've also found that because defining terms using Atlassian Intelligence relies on search in Confluence, the feature will only work in Jira if you have permission to view a Confluence instance on the same site as your Jira instance.

It's also possible that you might find that defining terms using Atlassian Intelligence doesn't perform as expected in Confluence spaces or Jira instances that have content written in multiple languages.

Your data and defining terms using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how defining terms using Atlassian Intelligence uses your data. This section supplements the information available on our Trust Center.

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as the term you want to define.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, defining terms using Atlassian Intelligence applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers
    • Are not stored by OpenAI.
    • Are not used to improve OpenAI models.
    • Are used only to serve your experience.
  • OpenAI is a subprocessor on our List of Subprocessors. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows existing user access permissions, so users won’t be shown a definition from content they do not have access to. Instead, the feature pulls content and definitions only from pages and projects that the user has permission to view in the instance. If you do not want your content to be available in responses to other users in your instance, work with your org admin to ensure your permissions are set appropriately.
  • If a user edits or updates a definition manually, the definition is stored and retained for 1 year.

Generate pull request descriptions with Atlassian Intelligence

How Bitbucket Cloud uses Atlassian Intelligence to generate pull request descriptions Copy link to heading Copied! Show
  

Generating pull request descriptions with Atlassian Intelligence is powered by large language models (LLM) developed by OpenAI. These models include the OpenAI models described here.

Atlassian Intelligence uses these models to analyze and generate natural language and code within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated by predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, or about this approach in OpenAI’s research papers.

Use cases for generating pull request descriptions with Atlassian Intelligence Copy link to heading Copied! Show
  

Atlassian Intelligence can help you generate, transform, and summarize content while you're writing pull request descriptions or comments in the Bitbucket Cloud code review experience. This includes:

  • Generating a pull request description based on the code changes contained in the pull request.
  • Summarizing, improving, or changing the tone of a pull request description.
  • Summarizing, improving or changing the tone of a pull request comment.

We believe that generating Bitbucket Cloud pull request descriptions with Atlassian Intelligence works best in scenarios where:

  • As a code author, you want Atlassian Intelligence to assist you with writing or improving a pull request description. This works best for teams who are able to review and confirm that the content generated by Atlassian Intelligence is appropriate to describe the pull request.
  • As a code reviewer, you want Atlassian Intelligence to assist you with improving the tone or content of a pull request comment you have already drafted.
Considerations when generating pull request descriptions with Atlassian Intelligence Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power this feature work, these models can sometimes behave in ways that are inaccurate, incomplete, or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on or include content that sounds reasonable but is false or incomplete.

We’ve found that generating Bitbucket Cloud pull request descriptions with Atlassian Intelligence is less useful in scenarios where:

  • You need your pull request description to reference information that isn’t already present in the code changes (for example, source code contained elsewhere in the repository).
  • You are not able to review and confirm that the content generated by Atlassian Intelligence is an accurate reflection of the pull request.
  • You need current and accurate information about people, places, and facts.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Being as specific as possible in what you ask Atlassian Intelligence to do.
  • Proofread, review, and edit the output generated by the AI writing assistant for accuracy and clarity.
  • Collaborate with others to gather feedback and improve the quality of your output.
Your data and generating pull request descriptions with Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how defining terms using Atlassian Intelligence in Confluence uses your data. This section supplements the information available on our Trust Center.

We process:

  • Your prompts (inputs) and responses (outputs)
  • Context from your instance relevant to your prompt, such as:
    • the code changes and commit messages in your pull request
    • the content of your pull request description
    • the content of your pull request comment
  • Data about how you interact with our features, such as clickstream data and the people you work with
  • Feedback you choose to provide about this feature

When it comes to your data, generating pull request descriptions with Atlassian Intelligence applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers
    • Are not stored by OpenAI
    • Are not used to improve OpenAI models
    • Are used only to serve your experience
  • OpenAI is a subprocessor on our List of Subprocessors. They may not use your data for any purpose besides processing your request.

Generate SQL queries in Atlassian Analytics

How Atlassian Intelligence generates SQL queries in Atlassian Analytics Copy link to heading Copied! Show
  

Generating SQL queries using Atlassian Intelligence in Atlassian Analytics is powered by large language models developed by OpenAI. These models include the OpenAI models described here.

Atlassian Intelligence uses these models to analyze and understand natural language, then translates it to structured query language (SQL) within Atlassian Analytics.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, or about this approach in OpenAI’s research papers.

Use cases for generating SQL queries using Atlassian Intelligence Copy link to heading Copied! Show
  

Ask Atlassian Intelligence a question in natural language and have it translated into SQL, rather than writing your own SQL queries from scratch. After you ask a question, Atlassian Intelligence uses the Atlassian Data Lake schema of your selected data source to generate an SQL query that can be used to build charts on your Atlassian Analytics dashboards, and can also help you learn about the schema in the Data Lake.

We believe that generating SQL queries using Atlassian Intelligence works best in scenarios where:

  • You want to build a custom chart starting with the generated SQL and refining the query where needed.
  • The natural language question includes words and concepts that are referenced in the Atlassian Data Lake schema, where you are as specific as possible.
  • You want to explore and learn about the Atlassian Data Lake schema.

Not sure what questions to ask?

Here are some suggestions:

  • What are the top 5 labels by count of open Jira issues?
  • How many Jira issues have been completed in the x project in the last month?
  • What’s the average time in status for the top 5 status?
  • What are the top 5 most favorited Confluence pages in the last month?
  • How many requests have been raised in the last 5 days in our x Jira Service Management project?
Considerations when generating SQL queries using Atlassian Intelligence Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to generate SQL queries using Atlassian Intelligence work, these models can sometimes behave in ways that are inaccurate, incomplete or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that generating SQL queries using Atlassian Intelligence is less useful in scenarios where:

  • You need current and accurate information about people, places, and facts.
  • You need this feature to have access to information that isn’t readily available in the Atlassian Data Lake schema (for example, data for Advanced Roadmaps) to properly answer the question.
  • The question includes references to custom fields.
  • The question is asked in a language other than English.
  • You don’t have enough familiarity with SQL to validate the SQL returned by Atlassian Intelligence.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Being as specific as possible in what you ask Atlassian Intelligence to do.
  • Ensure that the Atlassian Data Lake data source you are using covers the data needed to answer your question.
Your data and generating SQL queries using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how generating SQL queries using Atlassian Intelligence uses your data. This section supplements the information available on our Trust Center.

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, including the publicly available Atlassian Data Lake schemas applicable to your instance.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, generating SQL queries using Atlassian Intelligence applies the following measures.

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not stored by OpenAI.
    • Are not used to improve OpenAI models.
    • Are used only to serve your experience.
  • OpenAI is a subprocessor on our List of Subprocessors. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows the permissions in your Atlassian Data Lake connection. For example, if you do not have access to an Atlassian Data Lake connection, you will not be able to build SQL to query it.

Generative AI in the editor

How Atlassian Intelligence in editing experiences works Copy link to heading Copied! Show
  

Atlassian Intelligence in editing experiences is powered by large language models developed by OpenAI. These models include the OpenAI models described here.

Atlassian Intelligence uses these models to analyze and generate natural language within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, or about this approach in OpenAI’s research papers.

Use cases for generative AI in the editor Copy link to heading Copied! Show
  

Atlassian Intelligence helps drive effective communication across all teams in an organization to improve efficiency, decision-making, and processes.

We believe that using Atlassian Intelligence in editing experiences works best in scenarios like:

  • Transforming existing content for different audiences. Atlassian Intelligence helps with changing tone, improving writing, and making technical information easier for other teams to understand. This works best for teams who want to make their writing more professional and concise.
  • Summarizing existing content. With Atlassian Intelligence, you can turn rough notes into useful strategy documentation, knowledge base articles, campaign plans, and more. You can also use it to analyze existing information to define action plans and items. This works best for text-heavy pages where there is a lot of context to pull from.
  • Generating new content. Atlassian Intelligence helps you draft new content such as strategy pages, project overviews, release notes, or user stories. This works best when teams use clear, specific prompts, with a specific goal in mind.
Considerations when using Atlassian Intelligence in editing experiences Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power Atlassian Intelligence in editing experiences work, they can sometimes behave in ways that are inaccurate, incomplete, or unreliable.

For example, the responses that you receive might not accurately reflect the content they’re based on or include content that sounds reasonable but is false or incomplete.

We’ve found that using Atlassian Intelligence in editing experiences is less useful in scenarios where:

  • You need current and accurate, up-to-date information about people, places, and facts.
  • You need to have access to information that isn’t readily available to you (for example, in your instance) to properly answer your request.
  • You need to generate content in a format beyond standard markdown (for example, generating an info panel from scratch).
  • You need to reference information that isn’t already present in the document being edited (for example, content present in another document, or another product).
  • You need to generate and transform content in languages other than English.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Being as specific as possible in what you ask Atlassian Intelligence to do.
  • Break down complex requests into smaller, more manageable tasks.
  • Incorporate relevant keywords to improve the accuracy of generated content.
  • Use proper grammar and punctuation in your input text.
  • Proofread, review, and edit the output generated by the AI writing assistant for accuracy and clarity.
  • Experiment with different prompts or variations of your input text to explore different ideas.
  • Collaborate with others to gather feedback and improve the quality of your output.
Your data and Atlassian Intelligence in editing experiences Copy link to heading Copied! Show
  

We understand you may have questions about how Atlassian Intelligence in editing experiences uses your data. This section supplements the information available on our Trust Center.

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as the product you triggered Atlassian Intelligence from.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, Atlassian Intelligence in editing experiences applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not stored by OpenAI.
    • Are not used to improve OpenAI models.
    • Are used only to serve your experience.
  • OpenAI is a subprocessor on our List of Subprocessors. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows the permissions in your instance. For example, if you do not have access to a certain Confluence page, you will not be suggested content from that page in the response you receive. If you don't want your content to be available in responses to other users in your instance, work with your org admin to ensure your permissions are set appropriately.

Search answers in Confluence

How Atlassian Intelligence searches answers in Confluence Copy link to heading Copied! Show
  

Search answers in Confluence using Atlassian Intelligence is powered by LLM models developed by OpenAI. These models include the OpenAI models described here.

Atlassian Intelligence uses these models to analyze and generate natural language within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, or about this approach in OpenAI’s research papers.

Uses cases for searching answers in Confluence Copy link to heading Copied! Show
  

Knowledge bases are growing too fast for users to keep up. Searching answers in Confluence using Atlassian Intelligence provides a faster path to key information that customers need to move their work forward. This feature helps you easily find the information you need. It understands the types of questions you would ask a teammate, and answers them instantly. Find out more about using Atlassian Intelligence to search for answers in Confluence.

We believe that searching answers in Confluence using Atlassian Intelligence works best when your Confluence site is full of detailed, complete, and up-to-date content.

This feature does not generate new content, but searches Confluence pages and blogs (while respecting restrictions) to find an answer to your question. Atlassian Intelligence generates answers solely based on what’s in your Confluence, and what you, specifically, have access to.

Not sure what questions to ask?

Here are some suggestions

  • When is the next marketing team offsite?
  • What is the work from home policy?
  • What is Project Sunrise?
  • When is our next marketing campaign?
  • Where are the release notes for SpaceLaunch’s newest product?
  • How do I submit expenses for reimbursement?
Considerations when searching answers in Confluence using Atlassian Intelligence Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to search answers in Confluence using Atlassian Intelligence work, these models can sometimes behave in ways that are inaccurate, incomplete, or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on or include content that sounds reasonable but is false or incomplete.

We’ve found that searching answers in Confluence using Atlassian Intelligence is less useful in scenarios where:

  • You need current and accurate information about people, places, and facts.
  • You need current and accurate information about information that tends to change frequently (for example, a roadmap that updates monthly).
  • You need current and accurate information about specific people and the role that they play in your organization.
  • You need access to information that isn’t readily available to you (for example, restricted pages in your Confluence instance) to properly answer your question.
  • The answer consists of a range of different values or categories (for example, metrics that update each week).
  • You need answers that require nuance, complexities, or human-like levels of reasoning.

It’s also possible that you might find that searching answers in Confluence using Atlassian Intelligence doesn’t perform as expected in Confluence spaces that have documents written in multiple languages.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Being as specific as possible in what you ask Atlassian Intelligence to do.
  • Asking questions about things that you know are documented in your Confluence instance and that you have access to.
Your data and searching answers in Confluence using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how searching answers in Confluence using Atlassian Intelligence uses your data. This section supplements the information available on our Trust Center.

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as content from the top three pages returned from Confluence search.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, searching answers in Confluence using Atlassian Intelligence applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not stored by any LLM provider.
    • Are not used to improve LLM models.
    • Are used only to serve your experience.
  • OpenAI is a sub-processor on our List of Subprocessors. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows the permissions in your instance. For example, if you do not have access to a certain Confluence page, this feature will not use content from that page in the response you see. If you do not want your content to be available in responses to other users in your instance, work with your org admin to ensure your permissions are set appropriately.

Search issues in Jira

How Atlassian Intelligence searches issues in Jira Copy link to heading Copied! Show
  

Search issues using Atlassian Intelligence in Jira is powered by large language models developed by OpenAI. The models include the OpenAI models described here, fine-tuned by Atlassian using generated synthetic data.

Atlassian Intelligence uses these models to analyze and understand natural language, then translates it to Jira Query Language (JQL) code within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means their responses are generated by predicting the most probable next word or text based on the data they have been trained on.

Read more about the capabilities of OpenAI models, and OpenAI fine-tuning. You can also read more about this approach in OpenAI’s research papers.

Use cases for searching issues in Jira Copy link to heading Copied! Show
  

You can now ask Atlassian Intelligence what you want in everyday language instead of coming up with complex queries. By searching issues using Atlassian Intelligence, your prompt is translated into a JQL query which quickly assists you in your search for specific issues.

We believe searching issues using Atlassian Intelligence works best in scenarios where:

  • You're querying for Jira issues using issue fields available in your Jira project.
  • The query has specific fields and values that can help narrow down your issue search.
  • The fields and values you're searching for exist in your Jira project.
  • Your query is in English.
  • The query is translatable to JQL. Since Atlassian Intelligence converts prompts to JQL code, inputs containing keywords that can be translated to JQL can provide better results.
Considerations when searching issues using Atlassian Intelligence Copy link to heading Copied! Show
  

It's important to remember that because of the way that the models used to search issues using Atlassian Intelligence work, these models can sometimes behave in ways that are inaccurate, incomplete, or unreliable.

For example, the responses you receive might not accurately reflect the content they are based on or include content that sounds reasonable but is false or incomplete.

We've found that searching issues using Atlassian Intelligence is less useful in scenarios where:

  • You need current and accurate information about people, places, and facts.
  • You’re searching for Jira entities that are not issues, such as projects, boards, or users.
  • You’re searching in a language other than English.
  • You need the search to analyze the issues to create charts, summaries, or other representations of your data.
  • The search requires functions not currently available in JQL (for example, a question such as “Find issues I have commented on” that can’t be translated into a JQL function).

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about being as specific as possible in what you ask Atlassian Intelligence to do. Make sure to include the exact fields and values you're looking for.

Your data and searching issues using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how searching issues using Atlassian Intelligence uses your data. This section supplements the information available on our Trust Center.

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as the current project you are in.
  • Data about how you interact with our features, such as clickstream data and the people you work with
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, searching issues using Atlassian Intelligence applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not stored by any LLM provider.
    • Are not used to improve LLM models.
    • Are used only to serve your experience.
  • OpenAI is a subprocessor on our List of Subprocessors. They do not use your inputs and outputs for any purpose besides processing your request.
  • Your search responses will be based on the issues and fields you have access to (for example, if you don't have access to a specific Jira project, you won't receive search results for issues and fields from that project).

Suggest request types in Jira Service Management

How Atlassian Intelligence suggests request types in Jira Service Management Copy link to heading Copied! Show
  

Suggest request types using Atlassian Intelligence is powered by large language models developed by OpenAI. These models include the OpenAI models described here.

Atlassian Intelligence uses these models to analyze natural language input and generate recommendations for request type names and descriptions for you within Jira Service Management.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, or about this approach in OpenAI’s research papers.

Use cases for suggesting request types in Jira Service Management Copy link to heading Copied! Show
  

Spend less time figuring out what kind of request types you need to create for your project, and instead get suggestions from Atlassian Intelligence. Simply describe your work and what your team typically manages, to see what types of requests you could create. Select one of the suggestions generated by Atlassian Intelligence to create a request type. Find out more about how to use Atlassian Intelligence to suggest request types.

We believe that using Atlassian Intelligence to suggest request types works best in scenarios where:

  • You have very specific use cases that existing request type templates don’t cater to.
  • You have very general requirements and are looking for some ideas.
  • You are using a widely spoken language (for example, English or Spanish).
Considerations when using Atlassian Intelligence to suggest request types Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to suggest request types using Atlassian Intelligence work, these models can sometimes behave in ways that are inaccurate, incomplete or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that using Atlassian Intelligence to suggest request types is less useful in scenarios where:

  • You need current and accurate information about people, places and facts.
  • You need this feature to have access to information that isn’t readily available to you (for example, in your instance) to properly answer your request.
  • You provide prompts that are too vague or irrelevant to service management.
  • You are not using a widely spoken language

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Being as specific as possible in what you ask Atlassian Intelligence to do.
Your data and using Atlassian Intelligence to suggest request types Copy link to heading Copied! Show
  

We understand you may have questions about how using Atlassian Intelligence to suggest request types uses your data. This section supplements the information available on our Trust Center.

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, using Atlassian Intelligence to suggest request types applies the following measures.

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not stored by OpenAI.
    • Are not used to improve OpenAI models.
    • Are used only to serve your experience.
  • OpenAI is a subprocessor on our List of Subprocessors. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature only uses the information from your prompts, so all Jira permissions are respected.

Summarize issue details in Jira Service Management

How Atlassian Intelligence summarizes issue details in Jira Service Management Copy link to heading Copied! Show
  

Summarize issue details using Atlassian Intelligence is powered by large language models developed by OpenAI. These models include the OpenAI models described here.

Atlassian Intelligence uses these models to analyze and generate natural language within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, or about this approach in OpenAI’s research papers.

Use cases for summarizing issue details in Jira Service Management Copy link to heading Copied! Show
  

Instead of reading through long descriptions and numerous comments on a Jira Service Management issue, you can use Atlassian Intelligence to quickly summarize this information for you. This helps agents quickly understand the context of the issue and any progress made, enabling them to take swift action and provide timely assistance.

We believe that summarizing issue details using Atlassian Intelligence works best for:

  • Issues with description and comments in English.
  • Issues with a large number of comments and/or lengthy comments and descriptions.
Considerations when summarizing issue details using Atlassian Intelligence Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power summarizing issue details using Atlassian Intelligence work, these models can sometimes behave in ways that are inaccurate, incomplete or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that summarizing issue details using Atlassian Intelligence is less useful in scenarios when:

  • You are using a language other than English
  • The issue has no history or details

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

Your data and summarizing issue details using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how summarizing issue details using Atlassian Intelligence uses your data. This section supplements the information available on our Trust Center.

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt includes details about the Jira Service. Management issue, such as the issue description, comments, and users involved in the ticket.
  • Data about how you interact with our features, such as clickstream data and the people you work with
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, summarizing issue details using Atlassian Intelligence applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not sent to any third-party LLM provider other than OpenAI.
    • Are not stored by OpenAI.
    • Are not used to improve OpenAI models.
    • Are used only to serve your experience.
  • OpenAI is a subprocessor on our List of Subprocessors. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows the permissions in your instance. Only agents and project admins have the visibility to the Summarize button.

Write custom formulas using Atlassian Intelligence

How Atlassian Intelligence writes custom formulas in Atlassian Analytics Copy link to heading Copied! Show
  

Writing custom formulas using Atlassian Intelligence is powered by large language models developed by OpenAI. These models include the OpenAI models described here.

Atlassian Intelligence uses these models to analyze natural language and then translates it to SQLite within Atlassian Analytics.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated by predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, or about this approach in OpenAI’s research papers.

Use cases for writing custom formulas using Atlassian Intelligence Copy link to heading Copied! Show
  

Ask or describe to Atlassian Intelligence how you want to transform the data in your result table and it will translate it into a SQLite expression that’s used for custom formulas, rather than writing your own SQLite expressions from scratch. After you ask a question, Atlassian Intelligence uses the data in the result table of the previous Visual SQL step to generate an SQLite expression that applies calculations or operations to that data for your chart. This can also help you learn about SQLite functions and their syntax.

Writing custom formulas using Atlassian Intelligence works best in scenarios where:

  • You want to apply changes to a single column in your queried data.
  • You want to start with a generated SQLite expression and refine it where needed.
  • The natural language question includes words and concepts that are referenced in your column headers or row data.
  • You want to learn more about SQLite and discover available SQLite functions.
Considerations when writing custom formulas using Atlassian Intelligence Copy link to heading Copied! Show
  

When using custom formulas, remember that the models used in Atlassian Intelligence can sometimes behave inaccurately, incompletely or unreliably.

For example, the responses you receive might not accurately reflect the content they're based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that writing custom formulas using Atlassian Intelligence is less useful in scenarios where:

  • You want to apply changes to more than one column in a single custom formula.
  • You need this feature to have access to information that isn’t readily available in the result table’s data.
  • The prompt is asked in a language other than English.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Being as specific as possible in what you ask Atlassian Intelligence to do.
  • Ensuring that the data you’ve queried covers the data needed to answer your question
Your data and writing custom formulas using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how your data is used when writing custom formulas using Atlassain Intelligence. This section supplements the information available on our Trust Center.

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as including the data from the result set in the previous Visual SQL step.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.
  • Data about how you interact with our features, such as clickstream data

When it comes to your data, writing custom formulas using Atlassian Intelligence applies the following measures.

Your prompts (inputs) and responses (outputs):

  • Are not available to other customers.
  • Are not stored by OpenAI.
  • Are not used to improve OpenAI models.
  • Are used only to serve your experience.

OpenAI is a subprocessor on our List of Subprocessors. They do not use your inputs and outputs for any purpose besides processing your request.

Atlassian AI logo.

Atlassian Intelligence and Rovo are designed for transparency

Our no b.s. commitment to open communication, accountability, and helping teams to use AI responsibly.

Rovo

Select a Rovo feature below to get a transparent look at use cases and data use.

How Atlassian Intelligence answers in Jira Service Management works Copy link to heading Copied! Show
  

Atlassian Intelligence answers is powered by large language models developed by OpenAI, Google, and Anthropic, as well as a combination of open-source large language models (including the Llama series, Phi series, and Mixtral series) and other machine learning models. These large language models include OpenAI's GPT series of models, Google's Gemini series of models, and Anthropic's Claude series of models. 

Atlassian Intelligence uses these models to analyze and generate natural language within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, Google’s models and Anthropic’s models. For more information on open-source language models, see information on the Llama series and the Phi series.

Use cases for Atlassian Intelligence answers in Jira Service Management Copy link to heading Copied! Show
  

The Atlassian Intelligence answers feature connects to the virtual service agent in Jira Service Management. It uses generative artificial intelligence to search across your linked knowledge base spaces and answer your customer questions.

We believe that Atlassian Intelligence answers works best in scenarios where:

  • You have a complete, up-to-date linked knowledge base that the virtual service agent can access to provide answers to customer questions using Atlassian Intelligence answers.
  • Atlassian Intelligence answers is used to respond to customer questions that:
    • Can be resolved by providing information or instructions.
    • Are covered in (or can be added to) your existing knowledge base articles.
    • Don’t usually need to be escalated to one of your agents.
Considerations when using Atlassian Intelligence answers in Jira Service Management Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power Atlassian Intelligence answers work, these models can sometimes behave in ways that are inaccurate, incomplete or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that Atlassian Intelligence answers is less useful in scenarios where:

  • You need current and accurate information about people, places, and facts.
  • You need Atlassian Intelligence answers to have access to information that isn’t readily available to you (for example, in your linked knowledge base) to properly answer your request.
  • Your knowledge base is outdated or incomplete, so searches may not be helpful.
  • The articles in your knowledge base don’t include relevant or high quality information, so the Atlassian Intelligence answers may provide less relevant information to customers based on those articles.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Proactively reviewing and updating your linked knowledge base (and the existing articles included within it) to make sure it remains complete and up-to-date.
  • Proactively reviewing the permissions and restrictions applicable to your linked knowledge base spaces to make sure Atlassian Intelligence answers has access to the right information to be useful.
Your data and Atlassian Intelligence answers in Jira Service Management Copy link to heading Copied! Show
  

We understand you may have questions about how Atlassian Intelligence answers in Jira Service Management uses your data. This section supplements the information available on our FAQ page.

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as your linked knowledge base spaces.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.
  • When it comes to your data, Atlassian Intelligence answers in Jira Service Management applies the following measures:
  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not sent to any third party LLM provider other than OpenAI, Google, or Anthropic on AWS Bedrock.
    • Are not stored by any LLM vendor.
    • Are not used to improve LLM models.
    • Are used only to serve your experience.
  • All third-party LLM providers are subprocessors and listed as so on our Subprocessors page. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows the permissions and restrictions applicable to your linked knowledge base spaces. This means all pages available to customers on your Jira Service Management portal will be available through Atlassian Intelligence answers. For example, if access to a certain Confluence page is restricted and not generally available via Jira Service Management, the content from that page will not be suggested in the responses from Atlassian Intelligence answers. If you don’t want your content to be available in responses to other users in your instance, work with your org admin to ensure your permissions are set appropriately.
How Automation uses Atlassian Intelligence Copy link to heading Copied! Show
  

Automation using Atlassian Intelligence is powered by large language models developed by OpenAI, Google, and Anthropic, as well as a combination of open-source large language models (including the Llama series, Phi series, and Mixtral series) and other machine learning models. These large language models include OpenAI's GPT series of models, Google's Gemini series of models, and Anthropic's Claude series of models. 

Atlassian Intelligence uses these models to analyze natural language input and generate an automation rule for you within Jira and Confluence.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated by predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, Google’s models and Anthropic’s models. For more information on open-source language models, see information on the Llama series and the Phi series.

Use cases for Automation using Atlassian Intelligence Copy link to heading Copied! Show
  

Creating automation rules is at the core of the everyday automation experience, and we want to make this even easier for you by adding Atlassian Intelligence to the automation rule builder in Jira and Confluence. Now, you can easily create automation rules by simply typing in and describing what you wish to automate, and let Atlassian Intelligence handle all the heavy lifting of creating the rule for you. Find out more about Automation using Atlassian Intelligence for Jira and for Confluence.

We believe that Automation using Atlassian Intelligence for Jira and Confluence works best in scenarios when you are not sure how to get started or want to accelerate the rule creation process.

Not sure how best to create an automation rule?

Automation rules are created by a combination of different types of components: triggers, actions, conditions, and branches. Think of components as the building blocks of a rule. To successfully create a rule with Atlassian Intelligence, your rule must at least contain both a trigger and an action. For example:

In Jira:

Every Monday, find all the tasks with a due date in the next 7 days, and send the assignee a reminder email.

When a ticket moves to Testing, assign the ticket to John Smith.

In Confluence:

  • Every Monday, find all the tasks with a due date in the next 7 days, and send the assignee a reminder email.
  • Every 6 months, archive any pages that haven’t been updated in that time. After archiving, send an email to the page author letting them know.
  • When a page is published with Product Spec in the title, create a Jira ticket to review the page with a link to the page.

In addition, for a rule to be successfully created, all its components must be supported by Automation using Atlassian Intelligence. This means that any triggers, actions, conditions, or branches in your rule must be compatible with Automation in Jira and/or Confluence.

Considerations for Automation using Atlassian Intelligence Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power Automation using Atlassian Intelligence work, these models can sometimes behave in ways that are inaccurate, incomplete or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that Automation using Atlassian Intelligence is less useful in scenarios where:

  • You need to give Automation using Atlassian Intelligence access to information that isn’t readily available to you (for example, a restricted page or project) to properly answer your request.
  • You need to perform one-off tasks.
  • You need to query information from within your knowledge base.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

Automation using Atlassian Intelligence will only work with the existing set of available automation components in Jira and Confluence.

You might also want to think about being as specific as possible in what you ask Atlassian Intelligence to do, as described above.

Your data and Automation using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how Automation using Atlassian Intelligence uses your data. This section supplements the information available on our FAQ page.

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as a Jira project or a Confluence page.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, using Atlassian Intelligence for Confluence automation applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not sent to any third party LLM provider other than OpenAI, Google, or Anthropic on AWS Bedrock
    • Are not stored by any LLM vendor.
    • Are not used to improve LLM models.
    • Are used only to serve your experience.

All third-party LLM providers are subprocessors and listed as so on our  Subprocessors page. They do not use your inputs and outputs for any purpose besides processing your request.

This feature follows the permissions in your instance. For example, if you do not have access to a specific project or page, you will not be suggested content from those assets in the response you receive. If you do not want your content to be available in responses to other users in your instance, work with your org admin to ensure your permissions are set appropriately.

How alert grouping uses Atlassian Intelligence Copy link to heading Copied! Show
  

Alert grouping by Atlassian Intelligence is powered by large language models developed by OpenAI, Google, and Anthropic, as well as a combination of open-source large language models (including the Llama series, Phi series, and Mixtral series) and other machine learning models. These models include an algorithm designed to identify patterns in alert data, and OpenAI's GPT series of models, Google's Gemini series of models, and Anthropic's Claude series of models.

Atlassian Intelligence uses these machine learning models to analyze and generate alert groups and give related suggestions (past alert groups and past alert responders) within our products based on the similarity of the alert content or the tags used. Atlassian Intelligence then uses large language models to analyze and generate natural language descriptions and content for these groups within our products.

These large language models generate responses based on your inputs and are probabilistic. This means that their responses are generated by predicting the most probable next word or text based on the data they have been trained on.

Read more about the capabilities of OpenAI’s models, Google’s models and Anthropic’s models. For more information on open-source language models, see information on the Llama series and the Phi series.

Use cases for alert grouping Copy link to heading Copied! Show
  

Alert grouping uses Atlassian Intelligence to identify and group similar alerts together. It also helps you by identifying and recommending past similar alert groups and past alert responders (or teams of responders), based on the semantic similarity of the alert content or tags used.

When you want to escalate the alert group to an incident, alert grouping will also pre-populate all contextual information for you to review as part of the incident creation process.

We believe that alert grouping works best in scenarios where:

  • Your organization frequently encounters patterns of similar or duplicate alerts occurring at a high volume, whether experienced over a short period or a more extended time frame.
  • Your organization consistently categorizes alerts using tags.
  • Your team often finds that similar or duplicate alerts should be escalated into incidents.
Considerations when using alert grouping Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power alert grouping work, these models can sometimes behave in ways that are inaccurate, incomplete, or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on or include content that sounds reasonable but is false or incomplete. In the case of the alert groups that you see, they might not precisely reflect the semantic similarity of their tags.

We’ve found that alert grouping is less useful in scenarios where:

  • You need current and accurate information about people, places, and facts.
  • You need alert grouping to have access to information that isn’t readily available to you to properly group the alerts. Alert grouping works within the boundaries of your team’s configured roles and permissions, so you’ll only have access to groups and insights for alerts you have permission to view.
  • The alert tags used by your team are not consistent or well-maintained. Because alert grouping works by grouping alerts based on the semantic similarity of alert titles and tags, the quality of the alert groups it generates depends on the consistency and hygiene of the alert tags used in your team and your organisation.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about ensuring that you and your team follow consistent practices in using alert tags.

Your data and alert grouping Copy link to heading Copied! Show
  

We understand you may have questions about how alert grouping uses your data. This section supplements the information available on our FAQ page

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as your alert data (alert titles, alert tags, priority, responder teams, description).
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

We process your alert data to train a version of the machine learning model to recognize patterns specific to your alerts. This version is used to serve only your experience:

  • We store the identified patterns to provide you with insights.
  • We do not use your alert data to train any LLM.

When it comes to your data, alert grouping applies the following measures:

  • Your inputs and outputs:
    • Are not available to other customers.
    • Are not sent to any third party LLM provider other than OpenAI, Google, or Anthropic on AWS Bedrock

    • Are not stored by any LLM vendor.

    • Are not used to improve LLM models.

    • Are used only to serve your experience.

  • All third-party LLM providers are subprocessors and listed as so on our Subprocessors page. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows your site's permissions. For instance, if Atlassian Intelligence groups 50 alerts based on their tags and semantic similarity and you have permission to view only 30 of them, you’ll only see those 30 in the group detail view. If you don't want your alerts to be available in response to other users in your site, please work with your org/site admin to ensure your permissions are set appropriately.
How Atlassian Intelligence summarizes pages and blogs in Confluence Copy link to heading Copied! Show
  

Summarize pages and blogs using Atlassian Intelligence is powered by large language models developed by developed by OpenAI, Google, and Anthropic, as well as a combination of open-source large language models (including the Llama series, Phi series, and Mixtral series) and other machine learning models. These large language models include OpenAI's GPT series of models, Google's Gemini series of models, and Anthropic's Claude series of models. 

Atlassian Intelligence uses these models to analyze and generate natural language within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, Google’s models and Anthropic’s models. For more information on open-source language models, see information on the Llama series and the Phi series.

Use cases for Confluence quick summary Copy link to heading Copied! Show
  

Save time and get the details you need to do your work faster by generating a quick summary of a Confluence page or blog with Atlassian Intelligence. Find out more about using Atlassian Intelligence in Confluence.

We believe that summarizing pages and blogs using Atlassian Intelligence works best in scenarios when:

  • There is a text-heavy page that takes a 5 minutes or more to read.
  • There is a lot of written content, with limited visuals and/or other formatting like expands on a page.
Considerations when summarizing pages and blogs using Atlassian Intelligence Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power summarizing pages and blogs using Atlassian Intelligence work, they can sometimes behave in ways that are inaccurate, incomplete, or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on or include content that sounds reasonable but is false or incomplete.

While we continue to build better support for macros, tables, and expand in summaries, we’ve found that summarizing pages and blogs using Atlassian Intelligence is less useful in scenarios where:

  • You need current and accurate information about people, places, and facts.
  • You need a summary of a very short Confluence page where there is not enough content.
  • You need a summary of a Confluence page where most of the content is in tables or expands.
  • You need a summary of a Confluence page with most of the content in macros.

We encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Asking Atlassian Intelligence to summarise pages that you know are heavy on text-based content.
Your data and summarizing pages and blogs using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how using Atlassian Intelligence for Confluence automation uses your data. This section supplements the information available on our FAQ page

We process:

  • Your prompts (inputs) and responses (outputs).

  • Context from your instance relevant to your prompt, such as content from the Confluence page you want to summarize.

  • Data about how you interact with our features, such as clickstream data and the people you work with

  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, summarizing pages and blogs using Atlassian Intelligence applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not sent to any third party LLM provider other than OpenAI, Google, or Anthropic on AWS Bedrock.
    • Are not stored by any LLM vendor.

    • Are not used to improve LLM models.
    • Are used only to serve your experience.
  • All third-party LLM providers are subprocessors and listed as so on our Subprocessors page. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows the permissions in your instance. For example, if you do not have access to a Confluence page, you will not be shown this feature or be able to summarize a page using Atlassian Intelligence. If you do not want your content to be available to other users in your instance, work with your org admin to ensure your permissions are set appropriately.
How Atlassian Intelligence defines terms Copy link to heading Copied! Show
  

Defining terms using Atlassian Intelligence in Confluence and Jira is powered by large language models developed by OpenAI, Google, and Anthropic, as well as a combination of open-source large language models (including the Llama series, Phi series, and Mixtral series) and other machine learning models. These large language models include OpenAI's GPT series of models, Google's Gemini series of models, and Anthropic's Claude series of models. 

Atlassian Intelligence uses these models to analyze and generate natural language answers within Confluence.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, Google’s models and Anthropic’s models. For more information on open-source language models, see information on the Llama series and the Phi series.

Use cases for defining terms using Atlassian Intelligence Copy link to heading Copied! Show
  

One of the most challenging things about consuming content in Confluence and Jira can be getting the context you need to understand what you’re reading. Abbreviations, acronyms, unfamiliar terms, and team or project-specific names can lead to a lengthy search for the information you need.

Defining terms using Atlassian Intelligence will provide the definition of company-specific terms (such as acronyms, project, system, or team names) on a page in Confluence or in an issue description in Jira. This gives users the information they need, when they need it - all whilst helping teams work better together.

Atlassian Intelligence can save you time by defining these things for you, without navigating away from what you’re reading.

If you encounter a definition that you feel is inaccurate, you can edit or add a new definition, then set the visibility to be for that page or issue, the whole space or project, or access your entire organization.

We believe that defining terms using Atlassian Intelligence in Confluence works best in scenarios when:

  • A company has multiple pages in their Confluence instance that mention, describe, or explain what a specific term is for Atlassian Intelligence to reference.
Considerations when defining terms using Atlassian Intelligence Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to define terms using Atlassian Intelligence in Confluence work, these models can sometimes behave in ways that are inaccurate, incomplete or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that defining terms using Atlassian Intelligence in Confluence is less useful in scenarios where:

  • You need current and accurate information about people, places and facts.
  • You don’t have ample context on the term inside that Confluence instance (for example, if there are no pages that mention the specific term, that term’s definition will not be accurately generated).
  • The definition requires access to Confluence content that you don't have permission to view
  • You attempt to define multiple terms instead of one individual term at a time.

In addition, in Jira, we've also found that because defining terms using Atlassian Intelligence relies on search in Confluence, the feature will only work in Jira if you have permission to view a Confluence instance on the same site as your Jira instance.

It's also possible that you might find that defining terms using Atlassian Intelligence doesn't perform as expected in Confluence spaces or Jira instances that have content written in multiple languages.

Your data and defining terms using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how defining terms using Atlassian Intelligence uses your data. This section supplements the information available on our FAQ page

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as the term you want to define.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, defining terms using Atlassian Intelligence applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not sent to any third party LLM provider other than OpenAI, Google, or Anthropic on AWS Bedrock

    • Are not stored by any LLM provider.
    • Are not used to improve LLM models.
    • Are used only to serve your experience.
  • All third-party LLM providers are subprocessors and listed as so on our Subprocessors page. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows existing user access permissions, so users won’t be shown a definition from content they do not have access to. Instead, the feature pulls content and definitions only from pages and projects that the user has permission to view in the instance. If you do not want your content to be available in responses to other users in your instance, work with your org admin to ensure your permissions are set appropriately.
  • If a user edits or updates a definition manually, the definition is stored and retained for 1 year.
How Atlassian Intelligence in editing experiences works Copy link to heading Copied! Show
  

Atlassian Intelligence in editing experiences is powered by large language models developed by OpenAI, Google, and Anthropic, as well as a combination of open-source large language models (including the Llama series, Phi series, and Mixtral series) and other machine learning models. These large language models include OpenAI's GPT series of models, Google's Gemini series of models, and Anthropic's Claude series of models. 

Atlassian Intelligence uses these models to analyze and generate natural language within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, Google’s models and Anthropic’s models. For more information on open-source language models, see information on the Llama series and the Phi series.

Use cases for generative AI in the editor Copy link to heading Copied! Show
  

Atlassian Intelligence helps drive effective communication across all teams in an organization to improve efficiency, decision-making, and processes.

We believe that using Atlassian Intelligence in editing experiences works best in scenarios like:

  • Transforming existing content for different audiences. Atlassian Intelligence helps with changing tone, improving writing, and making technical information easier for other teams to understand. This works best for teams who want to make their writing more professional and concise.
  • Summarizing existing content. With Atlassian Intelligence, you can turn rough notes into useful strategy documentation, knowledge base articles, campaign plans, and more. You can also use it to analyze existing information to define action plans and items. This works best for text-heavy pages where there is a lot of context to pull from.
  • Generating new content. Atlassian Intelligence helps you draft new content such as strategy pages, project overviews, release notes, or user stories. This works best when teams use clear, specific prompts, with a specific goal in mind.
Considerations when using Atlassian Intelligence in editing experiences Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power Atlassian Intelligence in editing experiences work, they can sometimes behave in ways that are inaccurate, incomplete, or unreliable.

For example, the responses that you receive might not accurately reflect the content they’re based on or include content that sounds reasonable but is false or incomplete.

We’ve found that using Atlassian Intelligence in editing experiences is less useful in scenarios where:

  • You need current and accurate, up-to-date information about people, places, and facts.
  • You need to have access to information that isn’t readily available to you (for example, in your instance) to properly answer your request.
  • You need to generate content in a format beyond standard markdown (for example, generating an info panel from scratch).
  • You need to reference information that isn’t already present in the document being edited (for example, content present in another document, or another product).
  • You need to generate and transform content in languages other than English.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Being as specific as possible in what you ask Atlassian Intelligence to do.
  • Break down complex requests into smaller, more manageable tasks.
  • Incorporate relevant keywords to improve the accuracy of generated content.
  • Use proper grammar and punctuation in your input text.
  • Proofread, review, and edit the output generated by the AI writing assistant for accuracy and clarity.
  • Experiment with different prompts or variations of your input text to explore different ideas.
  • Collaborate with others to gather feedback and improve the quality of your output.
Your data and Atlassian Intelligence in editing experiences Copy link to heading Copied! Show
  

We understand you may have questions about how Atlassian Intelligence in editing experiences uses your data. This section supplements the information available on our FAQ page

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as the product you triggered Atlassian Intelligence from.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, Atlassian Intelligence in editing experiences applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not sent to any third party LLM provider other than OpenAI, Google, or Anthropic on AWS Bedrock.

    • Are not stored by any LLM provider.
    • Are not used to improve LLM models.
    • Are used only to serve your experience.
  • All third-party LLM providers are subprocessors and listed as so on our Subprocessors page. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows the permissions in your instance. For example, if you do not have access to a certain Confluence page, you will not be suggested content from that page in the response you receive. If you don't want your content to be available in responses to other users in your instance, work with your org admin to ensure your permissions are set appropriately.

Summarize issue details in Jira Service Management

How Atlassian Intelligence summarizes issue details in Jira Service Management Copy link to heading Copied! Show
  

Summarize issue details using Atlassian Intelligence is powered by large language models developed by OpenAI, Google, and Anthropic, as well as a combination of open-source large language models (including the Llama series, Phi series, and Mixtral series) and other machine learning models. These large language models include OpenAI's GPT series of models, Google's Gemini series of models, and Anthropic's Claude series of models. 

Atlassian Intelligence uses these models to analyze and generate natural language within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, Google’s models and Anthropic’s models. For more information on open-source language models, see information on the Llama series and the Phi series.

Use cases for summarizing issue details in Jira Service Management Copy link to heading Copied! Show
  

Instead of reading through long descriptions and numerous comments on a Jira Service Management issue, you can use Atlassian Intelligence to quickly summarize this information for you. This helps agents quickly understand the context of the issue and any progress made, enabling them to take swift action and provide timely assistance.

We believe that summarizing issue details using Atlassian Intelligence works best for:

  • Issues with description and comments in English.
  • Issues with a large number of comments and/or lengthy comments and descriptions.
Considerations when summarizing issue details using Atlassian Intelligence Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power summarizing issue details using Atlassian Intelligence work, these models can sometimes behave in ways that are inaccurate, incomplete or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that summarizing issue details using Atlassian Intelligence is less useful in scenarios when:

  • You are using a language other than English
  • The issue has no history or details

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

Your data and summarizing issue details using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how summarizing issue details using Atlassian Intelligence uses your data. This section supplements the information available on our FAQ page.

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt includes details about the Jira Service. Management issue, such as the issue description, comments, and users involved in the ticket.
  • Data about how you interact with our features, such as clickstream data and the people you work with
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, summarizing issue details using Atlassian Intelligence applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not sent to any third party LLM provider other than OpenAI, Google, or Anthropic on AWS Bedrock.

    • Are not stored by any LLM provider.
    • Are not used to improve LLM models.
    • Are used only to serve your experience.
  • All third-party LLM providers are subprocessors and listed as so on our Subprocessors page. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows the permissions in your instance. Only agents and project admins have the visibility to the Summarize button.
How Atlassian Intelligence summarizes Smart Links Copy link to heading Copied! Show
  

Summarize Smart Links with Atlassian Intelligence (AI) is powered by large language models developed by OpenAI, Google, and Anthropic, as well as a combination of open-source large language models (including the Llama series, Phi series, and Mixtral series) and other machine learning models. These large language models include OpenAI's GPT series of models, Google's Gemini series of models, and Anthropic's Claude series of models. 

Atlassian Intelligence uses these models to analyze and generate natural language within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, Google’s models and Anthropic’s models. For more information on open-source language models, see information on the Llama series and the Phi series.

Use cases for summarizing Smart Links Copy link to heading Copied! Show
  

After you hover over a Smart Link from Jira, Confluence, and Google Docs, Atlassian Intelligence can help you summarize the content, which allows you to determine the importance and value of the link and decide your next action. This reduces the need to leave the current page and switch contexts.

We believe that Summarize Smart Links with AI works best in scenarios where:

  • You are viewing a page or issue with one or more Smart Links.
  • You are viewing a page or issue with one or more Smart Links that contain a lot of information or dense content, which will take time and attention away from the main content you wanted to read.
Considerations when summarizing Smart Links using Atlassian Intelligence Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power Summarize Smart Links with AI work, these models can sometimes behave in ways that are inaccurate, incomplete, or unreliable.

For example, the summaries you receive might not accurately reflect the content that they are based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that Summarize Smart Links with AI is less useful in scenarios where:

  • You need current and accurate information about people, places, and facts.
  • You need to summarise content that is incredibly short.
  • You need to summarise all the metadata and the content in a link. For example, if you wanted to understand all the field values in a Jira ticket as well as its description and comment content.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

Your data and summarizing Smart Links using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how summarizing issue details using Atlassian Intelligence uses your data. This section supplements the information available on our FAQ page.

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as the content of the link you want to summarize.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any responses you choose to share as part of your feedback.

When it comes to your data, Summarize Smart Links with AI applies the following measures.

  • Your summaries:
    • Are not available to other customers.
    • Are not sent to any third party LLM provider other than OpenAI, Google, or Anthropic on AWS Bedrock.

    • Are not stored by any LLM provider.
    • Are not used to improve LLM models.
    • Are used only to serve your experience.
  • All third-party LLM providers are subprocessors and listed as so on our Subprocessors page. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows the permissions in your instance. For example, if you do not have access to a page or ticket in Jira, Confluence, or Google, you will not be able to summarize content from that source. If you do not want your content to be available in responses to other users in your instance, please work with your org admin to ensure your permissions are set appropriately.

How Atlassian Intelligence writes custom formulas in Atlassian Analytics Copy link to heading Copied! Show
  

Writing custom formulas using Atlassian Intelligence is powered by large language models developed by OpenAI, Google, and Anthropic, as well as a combination of open-source large language models (including the Llama series, Phi series, and Mixtral series) and other machine learning models. These large language models include OpenAI's GPT series of models, Google's Gemini series of models, and Anthropic's Claude series of models. 

Atlassian Intelligence uses these models to analyze natural language and then translates it to SQLite within Atlassian Analytics.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated by predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, Google’s models and Anthropic’s models. For more information on open-source language models, see information on the Llama series and the Phi series.

Use cases for custom formulas using AI Copy link to heading Copied! Show
  

Ask or describe to Atlassian Intelligence how you want to transform the data in your result table and it will translate it into a SQLite expression that’s used for custom formulas, rather than writing your own SQLite expressions from scratch. After you ask a question, Atlassian Intelligence uses the data in the result table of the previous Visual SQL step to generate an SQLite expression that applies calculations or operations to that data for your chart. This can also help you learn about SQLite functions and their syntax.

Writing custom formulas using Atlassian Intelligence works best in scenarios where:

  • You want to apply changes to a single column in your queried data.
  • You want to start with a generated SQLite expression and refine it where needed.
  • The natural language question includes words and concepts that are referenced in your column headers or row data.
  • You want to learn more about SQLite and discover available SQLite functions.
Considerations when writing custom formulas using AI Copy link to heading Copied! Show
  

When using custom formulas, remember that the models used in Atlassian Intelligence can sometimes behave inaccurately, incompletely or unreliably.

For example, the responses you receive might not accurately reflect the content they're based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that writing custom formulas using Atlassian Intelligence is less useful in scenarios where:

  • You want to apply changes to more than one column in a single custom formula.
  • You need this feature to have access to information that isn’t readily available in the result table’s data.
  • The prompt is asked in a language other than English.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Being as specific as possible in what you ask Atlassian Intelligence to do.
  • Ensuring that the data you’ve queried covers the data needed to answer your question.
Your data and writing custom formulas using AI Copy link to heading Copied! Show
  

We understand you may have questions about how using Atlassian Intelligence for Confluence automation uses your data. This section supplements the information available on our FAQ page

We process:

  • Your prompts (inputs) and responses (outputs).

  • Context from your instance relevant to your prompt, such as including the data from the result set in the previous Visual SQL step.

  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

  • Data about how you interact with our features, such as clickstream data.

When it comes to your data, writing custom formulas using Atlassian Intelligence applies the following measures.

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not sent to any third party LLM provider other than OpenAI, Google, or Anthropic on AWS Bedrock.

    • Are not stored by any LLM provider.
    • Are not used to improve LLM models.
    • Are used only to serve your experience.
  • All third-party LLM providers are subprocessors and listed as so on our Subprocessors page. They do not use your inputs and outputs for any purpose besides processing your request.
How create incident uses Atlassian Intelligence Copy link to heading Copied! Show
  

Create incident with AI using Atlassian Intelligence is powered by large language models developed by OpenAI, Google, and Anthropic, as well as a combination of open-source large language models (including the Llama series, Phi series, and Mixtral series) and other machine learning models. These large language models include OpenAI's GPT series of models, Google's Gemini series of models, and Anthropic's Claude series of models. 

Atlassian Intelligence uses these models to analyze and generate natural language within our products.

These models generate responses based on your input and are probabilistic in nature. This means that their responses are generated by predicting the most probable next word or text based on the data that they've been trained on.

Read more about the capabilities of OpenAI’s models, Google’s models and Anthropic’s models. For more information on open-source language models, see information on the Llama series and the Phi series.

Use cases for create incident with AI Copy link to heading Copied! Show
  

When escalating one or more alerts or alert groups to an incident in Jira Service Management, create incident with AI uses Atlassian Intelligence to quickly pre-populate all contextual information from for you to review as part of the incident creation process. This allows users to quickly understand the context of the incident created from those alerts or alert groups, and review and confirm pre-populated information including the title, description and priority of the alert when escalating it to an incident.

We believe that create incident with AI works best in scenarios where:

  • The alerts that you are escalating to an incident include title and descriptions in English.
  • The alerts that you are escalating to an incident have lengthy descriptions.
  • When you are creating an incident from more than one alert.
Considerations when using create incident with AI Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power create incident with AI work, these models can sometimes behave in ways that are inaccurate, incomplete or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that create incident with AI is less useful in scenarios when:

  • You need current and accurate information about people, places, and facts.
  • The alerts that you are escalating to an incident include their title or description (or both) in a language other than English.
  • The alerts that you are escalating to an incident contain only limited details.

For these reasons, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

To get the most useful results we suggest being as specific as possible in what you ask Atlassian Intelligence to do.

You might also want to think about being as specific as possible in what you ask Atlassian Intelligence to do.

Your data and create incident using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how create incident with AI uses your data. This section supplements the information available on our FAQ page.

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as the Jira Service Management alert description, title, and priority.
  • Data about how you interact with our features, such as clickstream data and the people you work with
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, create incident with AI applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not sent to any third party LLM provider other than OpenAI, Google, or Anthropic on AWS Bedrock.

    • Are not stored by any LLM providor.
    • Are not used to improve LLM models.
    • Are used only to serve your experience.
  • All third-party LLM providers are subprocessors and listed as so on our  Subprocessors page. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows the permissions for alerts in your instance. Only agents that have permission to view the alert and escalate it to an incident will see suggestions by Atlassian intelligence for filling the details for the incident getting created.

Create post-incident review

How create post-incident review uses Atlassian Intelligence Copy link to heading Copied! Show
  

PIR (Post-Incident Review) creation by Atlassian Intelligence is powered by large language models developed by OpenAI. These large language models include OpenAI’s GPT series of models. Atlassian Intelligence uses these models to analyze and generate natural language within our products.

These models generate responses based on users' inputs and are probabilistic in nature. This means that the responses are generated by predicting the most probable next word or text, based on the data that they’ve been trained on.

Read more about the capabilities of OpenAI’s models, or about this approach in OpenAI’s research papers.

Use cases for create post-incident review with AI Copy link to heading Copied! Show
  

PIRs are a core part of the incident management process, helping incident responders and managers learn from current incidents and pass along insights to prevent similar incidents in the future. Atlassian Intelligence helps to accelerate the often time-consuming task of compiling a PIR by suggesting a PIR description based on relevant contextual information in your Jira Service Management instance and chat tools like Slack for you to review.

We believe that PIR creation using AI works best in scenarios where:

  • Your organization has a consistent practice of compiling PIRs for incidents.

  • Your team has incident details scattered across chat tools like Slack and Jira Service Management, which requires you to spend more time compiling a PIR from those sources.

  • Your organization records incidents in Jira Service Management with complete, up-to-date information.

Considerations when using create post-incident review with AI Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power PIR creation work, they can sometimes behave in ways that are inaccurate, incomplete, or unreliable. For example, the responses that you receive might not accurately reflect the content that they are based on or include content that might sound reasonable but is false or incomplete.

We’ve found that PIR creation using AI is less useful in scenarios where:

  • You need current and accurate information about people, places, and facts.
  • You need PIR creation to have access to information that isn’t readily available to you (for example, chat channels which you don’t have access to) to properly generate the PIR description.
  • The data available in your Jira Service Management instance is incomplete or insufficiently detailed, so the PIR creation may not be able to generate an accurate description.

For this reason, we encourage you to think about situations where you can use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Being as specific as possible in what you want Atlassian Intelligence to do.
  • Ensuring that you and your team follow incident management practices consistently. For example, by recording complete and accurate details of incidents in your Jira Service Management instance and linking the relevant chat channels to the incident.
Your data and create post-incident review using AI Copy link to heading Copied! Show
  

We understand you may have questions about how create post-incident review using AI uses your data. This section supplements the information available on our FAQ page

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as incident data (such as summary, labels, priority, responder teams, and description), linked alerts, and linked Slack chat channels.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, PIR creation using AI applies the following measures.

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.

    • Are not sent to any third party LLM provider other than OpenAI.

    • Are not stored by OpenAI.

    • Are not used to improve OpenAI models.

    • Are used only to serve your experience.

  • All third-party LLM providers are subprocessors and listed as so on our Subprocessors page.

  • This feature follows the permissions in your instance. For example, if you do not have access to the linked alerts of the incident or linked Slack channels, you will not be suggested content from these sources in the response you receive. If you do not want your content to be available in responses to other users in your instance, please work with your org admin to ensure your permissions are set appropriately.

How Bitbucket Cloud uses Atlassian Intelligence to generate pull request descriptions Copy link to heading Copied! Show
  

Generating pull request descriptions with Atlassian Intelligence is powered by large language models developed by OpenAI, Google, and Anthropic, as well as a combination of open-source large language models (including the Llama series, Phi series, and Mixtral series) and other machine learning models. These large language models include OpenAI's GPT series of models, Google's Gemini series of models, and Anthropic's Claude series of models. 

Atlassian Intelligence uses these models to analyze and generate natural language and code within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated by predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, Google’s models and Anthropic’s models. For more information on open-source language models, see information on the Llama series and the Phi series.

Use cases for generating pull request descriptions with Atlassian Intelligence Copy link to heading Copied! Show
  

Atlassian Intelligence can help you generate, transform, and summarize content while you're writing pull request descriptions or comments in the Bitbucket Cloud code review experience. This includes:

  • Generating a pull request description based on the code changes contained in the pull request.
  • Summarizing, improving, or changing the tone of a pull request description.
  • Summarizing, improving or changing the tone of a pull request comment.

We believe that generating Bitbucket Cloud pull request descriptions with Atlassian Intelligence works best in scenarios where:

  • As a code author, you want Atlassian Intelligence to assist you with writing or improving a pull request description. This works best for teams who are able to review and confirm that the content generated by Atlassian Intelligence is appropriate to describe the pull request.
  • As a code reviewer, you want Atlassian Intelligence to assist you with improving the tone or content of a pull request comment you have already drafted.
Considerations when generating pull request descriptions with Atlassian Intelligence Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power this feature work, these models can sometimes behave in ways that are inaccurate, incomplete, or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on or include content that sounds reasonable but is false or incomplete.

We’ve found that generating Bitbucket Cloud pull request descriptions with Atlassian Intelligence is less useful in scenarios where:

  • You need your pull request description to reference information that isn’t already present in the code changes (for example, source code contained elsewhere in the repository).
  • You are not able to review and confirm that the content generated by Atlassian Intelligence is an accurate reflection of the pull request.
  • You need current and accurate information about people, places, and facts.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Being as specific as possible in what you ask Atlassian Intelligence to do.
  • Proofread, review, and edit the output generated by the AI writing assistant for accuracy and clarity.
  • Collaborate with others to gather feedback and improve the quality of your output.
Your data and generating pull request descriptions with Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how defining terms using Atlassian Intelligence in Confluence uses your data. This section supplements the information available on our FAQ page.

We process:

  • Your prompts (inputs) and responses (outputs)
  • Context from your instance relevant to your prompt, such as:
    • the code changes and commit messages in your pull request
    • the content of your pull request description
    • the content of your pull request comment
  • Data about how you interact with our features, such as clickstream data and the people you work with
  • Feedback you choose to provide about this feature

When it comes to your data, generating pull request descriptions with Atlassian Intelligence applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not sent to any third party LLM provider other than OpenAI, Google, or Anthropic on AWS Bedrock.

    • Are not stored by any LLM provider.
    • Are not used to improve LLM models.
    • Are used only to serve your experience.
  • All third-party LLM providers are subprocessors and listed as so on our Subprocessors page.

Generate SQL queries in Atlassian Analytics

How Atlassian Intelligence generates SQL queries in Atlassian Analytics Copy link to heading Copied! Show
  

Generating SQL queries using Atlassian Intelligence in Atlassian Analytics is powered by large language models developed by OpenAI, Google, and Anthropic, as well as a combination of open-source large language models (including the Llama series, Phi series, and Mixtral series) and other machine learning models. These large language models include OpenAI's GPT series of models, Google's Gemini series of models, and Anthropic's Claude series of models. 

Atlassian Intelligence uses these models to analyze and understand natural language, then translates it to structured query language (SQL) within Atlassian Analytics.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, Google’s models and Anthropic’s models. For more information on open-source language models, see information on the Llama series and the Phi series.

Use cases for generating SQL queries using Atlassian Intelligence Copy link to heading Copied! Show
  

Ask Atlassian Intelligence a question in natural language and have it translated into SQL, rather than writing your own SQL queries from scratch. After you ask a question, Atlassian Intelligence uses the Atlassian Data Lake schema of your selected data source to generate an SQL query that can be used to build charts on your Atlassian Analytics dashboards, and can also help you learn about the schema in the Data Lake.

We believe that generating SQL queries using Atlassian Intelligence works best in scenarios where:

  • You want to build a custom chart starting with the generated SQL and refining the query where needed.
  • The natural language question includes words and concepts that are referenced in the Atlassian Data Lake schema, where you are as specific as possible.
  • You want to explore and learn about the Atlassian Data Lake schema.

Not sure what questions to ask?

Here are some suggestions:

  • What are the top 5 labels by count of open Jira issues?
  • How many Jira issues have been completed in the x project in the last month?
  • What’s the average time in status for the top 5 status?
  • What are the top 5 most favorited Confluence pages in the last month?
  • How many requests have been raised in the last 5 days in our x Jira Service Management project?
Considerations when generating SQL queries using Atlassian Intelligence Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to generate SQL queries using Atlassian Intelligence work, these models can sometimes behave in ways that are inaccurate, incomplete or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that generating SQL queries using Atlassian Intelligence is less useful in scenarios where:

  • You need current and accurate information about people, places, and facts.
  • You need this feature to have access to information that isn’t readily available in the Atlassian Data Lake schema (for example, data for Advanced Roadmaps) to properly answer the question.
  • The question includes references to custom fields.
  • The question is asked in a language other than English.
  • You don’t have enough familiarity with SQL to validate the SQL returned by Atlassian Intelligence.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Being as specific as possible in what you ask Atlassian Intelligence to do.
  • Ensure that the Atlassian Data Lake data source you are using covers the data needed to answer your question.
Your data and generating SQL queries using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how generating SQL queries using Atlassian Intelligence uses your data. This section supplements the information available on our FAQ page

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, including the publicly available Atlassian Data Lake schemas applicable to your instance.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, generating SQL queries using Atlassian Intelligence applies the following measures.

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not sent to any third party LLM provider other than OpenAI, Google, or Anthropic on AWS Bedrock.

    • Are not stored by any LLM provider.
    • Are not used to improve LLM models.
    • Are used only to serve your experience.
  • All third-party LLM providers are on our  Subprocessors page. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows the permissions in your Atlassian Data Lake connection. For example, if you do not have access to an Atlassian Data Lake connection, you will not be able to build SQL to query it.
How Atlassian Intelligence searches answers in Confluence Copy link to heading Copied! Show
  

Search answers in Confluence using Atlassian Intelligence is powered by large language models developed by OpenAI, Google, and Anthropic, as well as a combination of open-source large language models (including the Llama series, Phi series, and Mixtral series) and other machine learning models. These large language models include OpenAI's GPT series of models, Google's Gemini series of models, and Anthropic's Claude series of models. 

Atlassian Intelligence uses these models to analyze and generate natural language within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, Google’s models and Anthropic’s models. For more information on open-source language models, see information on the Llama series and the Phi series.

Uses cases for searching answers in Confluence Copy link to heading Copied! Show
  

Knowledge bases are growing too fast for users to keep up. Searching answers in Confluence using Atlassian Intelligence provides a faster path to key information that customers need to move their work forward. This feature helps you easily find the information you need. It understands the types of questions you would ask a teammate, and answers them instantly. Find out more about using Atlassian Intelligence to search for answers in Confluence.

We believe that searching answers in Confluence using Atlassian Intelligence works best when your Confluence site is full of detailed, complete, and up-to-date content.

This feature does not generate new content, but searches Confluence pages and blogs (while respecting restrictions) to find an answer to your question. Atlassian Intelligence generates answers solely based on what’s in your Confluence, and what you, specifically, have access to.

Not sure what questions to ask?

Here are some suggestions

  • When is the next marketing team offsite?
  • What is the work from home policy?
  • What is Project Sunrise?
  • When is our next marketing campaign?
  • Where are the release notes for SpaceLaunch’s newest product?
  • How do I submit expenses for reimbursement?
Considerations when searching answers in Confluence using Atlassian Intelligence Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to search answers in Confluence using Atlassian Intelligence work, these models can sometimes behave in ways that are inaccurate, incomplete, or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on or include content that sounds reasonable but is false or incomplete.

We’ve found that searching answers in Confluence using Atlassian Intelligence is less useful in scenarios where:

  • You need current and accurate information about people, places, and facts.
  • You need current and accurate information about information that tends to change frequently (for example, a roadmap that updates monthly).
  • You need current and accurate information about specific people and the role that they play in your organization.
  • You need access to information that isn’t readily available to you (for example, restricted pages in your Confluence instance) to properly answer your question.
  • The answer consists of a range of different values or categories (for example, metrics that update each week).
  • You need answers that require nuance, complexities, or human-like levels of reasoning.

It’s also possible that you might find that searching answers in Confluence using Atlassian Intelligence doesn’t perform as expected in Confluence spaces that have documents written in multiple languages.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Being as specific as possible in what you ask Atlassian Intelligence to do.
  • Asking questions about things that you know are documented in your Confluence instance and that you have access to.
Your data and searching answers in Confluence using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how searching answers in Confluence using Atlassian Intelligence uses your data. This section supplements the information available on our FAQ page. 

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as content from the top three pages returned from Confluence search.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, searching answers in Confluence using Atlassian Intelligence applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not sent to any third party LLM provider other than OpenAI, Google, or Anthropic on AWS Bedrock.

    • Are not stored by any LLM provider.
    • Are not used to improve LLM models.
    • Are used only to serve your experience.
  • All third-party LLM providers are subprocessors and listed as so on our Subprocessors page. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature follows the permissions in your instance. For example, if you do not have access to a certain Confluence page, this feature will not use content from that page in the response you see. If you do not want your content to be available in responses to other users in your instance, work with your org admin to ensure your permissions are set appropriately.

Search issues in Jira

How Atlassian Intelligence searches issues in Jira Copy link to heading Copied! Show
  

Search issues using Atlassian Intelligence in Jira is powered by large language models developed by OpenAI, Google, and Anthropic, as well as a combination of open-source large language models (including the Llama series, Phi series, and Mixtral series) and other machine learning models. These large language models include OpenAI's GPT series of models, Google's Gemini series of models, and Anthropic's Claude series of models. 

Atlassian Intelligence uses these models to analyze and understand natural language, then translates it to Jira Query Language (JQL) code within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means their responses are generated by predicting the most probable next word or text based on the data they have been trained on.

Read more about the capabilities of OpenAI’s models, Google’s models and Anthropic’s models. For more information on open-source language models, see information on the Llama series and the Phi series.

Use cases for searching issues in Jira Copy link to heading Copied! Show
  

You can now ask Atlassian Intelligence what you want in everyday language instead of coming up with complex queries. By searching issues using Atlassian Intelligence, your prompt is translated into a JQL query which quickly assists you in your search for specific issues.

We believe searching issues using Atlassian Intelligence works best in scenarios where:

  • You're querying for Jira issues using issue fields available in your Jira project.
  • The query has specific fields and values that can help narrow down your issue search.
  • The fields and values you're searching for exist in your Jira project.
  • Your query is in English.
  • The query is translatable to JQL. Since Atlassian Intelligence converts prompts to JQL code, inputs containing keywords that can be translated to JQL can provide better results.
Considerations when searching issues using Atlassian Intelligence Copy link to heading Copied! Show
  

It's important to remember that because of the way that the models used to search issues using Atlassian Intelligence work, these models can sometimes behave in ways that are inaccurate, incomplete, or unreliable.

For example, the responses you receive might not accurately reflect the content they are based on or include content that sounds reasonable but is false or incomplete.

We've found that searching issues using Atlassian Intelligence is less useful in scenarios where:

  • You need current and accurate information about people, places, and facts.
  • You’re searching for Jira entities that are not issues, such as projects, boards, or users.
  • You’re searching in a language other than English.
  • You need the search to analyze the issues to create charts, summaries, or other representations of your data.
  • The search requires functions not currently available in JQL (for example, a question such as “Find issues I have commented on” that can’t be translated into a JQL function).

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about being as specific as possible in what you ask Atlassian Intelligence to do. Make sure to include the exact fields and values you're looking for.

Your data and searching issues using Atlassian Intelligence Copy link to heading Copied! Show
  

We understand you may have questions about how searching issues using Atlassian Intelligence uses your data. This section supplements the information available on our FAQ page

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as the current project you are in.
  • Data about how you interact with our features, such as clickstream data and the people you work with
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, searching issues using Atlassian Intelligence applies the following measures:

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not sent to any third party LLM provider other than OpenAI, Google, or Anthropic on AWS Bedrock.

    • Are not stored by any LLM provider.
    • Are not used to improve LLM models.
    • Are used only to serve your experience.
    • Are stored on our database for 90 days and your prompts will be presented back to you as part of your search history.

  • All third-party LLM providers are subprocessors and listed as so on our Subprocessors page. They do not use your inputs and outputs for any purpose besides processing your request.
  • Your search responses will be based on the issues and fields you have access to (for example, if you don't have access to a specific Jira project, you won't receive search results for issues and fields from that project).

Glean instant insights from your data

Select an Atlassian Intelligence feature below to get a transparent look at use cases and data use.

How Chart insights uses Atlassian Intelligence Copy link to heading Copied! Show
  

Chart insights is powered by large language models developed by OpenAI, Google, and Anthropic, as well as a combination of open-source large language models (including the Llama series, Phi series, and Mixtral series) and other machine learning models. These large language models include OpenAI's GPT series of models, Google's Gemini series of models, and Anthropic's Claude series of models. 

Atlassian Intelligence uses these models to analyze and generate natural language within our products.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated by predicting the most probable next word or text based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, Google’s models and Anthropic’s models. For more information on open-source language models, see information on the Llama series and the Phi series.

Use cases for Chart insights Copy link to heading Copied! Show
  

Chart insights uses Atlassian Intelligence to help speed up your understanding of data in any chart in Atlassian Analytics. It does so by using the dashboard title, chart title, and chart data (including column headers and row values) to generate a natural language summary of that chart and its data. It will also aim to identify any trends or anomalies to provide you with certain insights into that chart.

We believe that Chart insights work best in scenarios where:

  • Charts have many rows of data.
  • Charts have a dashboard title.
  • Charts have column headers.
  • Charts have values in all of the rows and columns.

Bar charts, line charts, and bar-line charts work best with this feature since they typically have trends, dates, and many rows of data.

Considerations when using Chart insights Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to power Chart insights work, these models can sometimes behave in ways that are inaccurate, incomplete, or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that Chart insights is less useful in scenarios where:

  • You have charts with one or just a few rows of data.
  • You have charts that are of the single value type.
  • You have charts missing titles, axis-labels, and column headers.

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Double checking the accuracy of the insights with other users who may have more context on the specific data displayed in the chart.
  • Taking into account that Atlassian Intelligence is only using the context of a single chart and not the entire dashboard when providing a response.
Your data and Chart insights Copy link to heading Copied! Show
  

We understand you may have questions about how Chart insights uses your data. This section supplements the information available on our FAQ page.

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt, such as the data in your chart.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, Chart insights applies the following measures.

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not sent to any third party LLM provider other than OpenAI, Google, or Anthropic on AWS Bedrock.

    • Are not stored by any LLM provider.
    • Are not used to improve LLM models.
    • Are used only to serve your experience.
  • All third-party LLM providers are subprocessors and listed as so on our Subprocessors page. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature only uses information from the dashboard you have access to and have requested insights for.
How Atlassian Intelligence suggests request types in Jira Service Management Copy link to heading Copied! Show
  

Suggest request types using Atlassian Intelligence is powered by large language models developed by OpenAI, Google, and Anthropic, as well as a combination of open-source large language models (including the Llama series, Phi series, and Mixtral series) and other machine learning models. These large language models include OpenAI's GPT series of models, Google's Gemini series of models, and Anthropic's Claude series of models. 

Atlassian Intelligence uses these models to analyze natural language input and generate recommendations for request type names and descriptions for you within Jira Service Management.

These models generate responses based on your inputs and are probabilistic in nature. This means that their responses are generated through predicting the most probable next word or text, based on the data that they have been trained on.

Read more about the capabilities of OpenAI’s models, Google’s models and Anthropic’s models. For more information on open-source language models, see information on the Llama series and the Phi series.

Use cases for suggesting request types in Jira Service Management Copy link to heading Copied! Show
  

Spend less time figuring out what kind of request types you need to create for your project, and instead get suggestions from Atlassian Intelligence. Simply describe your work and what your team typically manages, to see what types of requests you could create. Select one of the suggestions generated by Atlassian Intelligence to create a request type. Find out more about how to use Atlassian Intelligence to suggest request types.

We believe that using Atlassian Intelligence to suggest request types works best in scenarios where:

  • You have very specific use cases that existing request type templates don’t cater to.
  • You have very general requirements and are looking for some ideas.
  • You are using a widely spoken language (for example, English or Spanish).
Considerations when using Atlassian Intelligence to suggest request types Copy link to heading Copied! Show
  

It’s important to remember that because of the way that the models used to suggest request types using Atlassian Intelligence work, these models can sometimes behave in ways that are inaccurate, incomplete or unreliable.

For example, the responses that you receive might not accurately reflect the content that they are based on, or include content that sounds reasonable but is false or incomplete.

We’ve found that using Atlassian Intelligence to suggest request types is less useful in scenarios where:

  • You need current and accurate information about people, places and facts.
  • You need this feature to have access to information that isn’t readily available to you (for example, in your instance) to properly answer your request.
  • You provide prompts that are too vague or irrelevant to service management.
  • You are not using a widely spoken language

For this reason, we encourage you to think about the situations when you use Atlassian Intelligence and review the quality of the responses you receive before sharing them with others.

You might also want to think about:

  • Being as specific as possible in what you ask Atlassian Intelligence to do.
Your data and using Atlassian Intelligence to suggest request types Copy link to heading Copied! Show
  

We understand you may have questions about how using Atlassian Intelligence to suggest request types uses your data. This section supplements the information available on our FAQ page

We process:

  • Your prompts (inputs) and responses (outputs).
  • Context from your instance relevant to your prompt.
  • Data about how you interact with our features, such as clickstream data and the people you work with.
  • Feedback you choose to provide about this feature, including any prompts or responses you choose to share as part of your feedback.

When it comes to your data, using Atlassian Intelligence to suggest request types applies the following measures.

  • Your prompts (inputs) and responses (outputs):
    • Are not available to other customers.
    • Are not sent to any third party LLM provider other than OpenAI, Google, or Anthropic on AWS Bedrock.

    • Are not stored by any LLM provider.
    • Are not used to improve LLM models.
    • Are used only to serve your experience.
  • All third-party LLM providers are subprocessors and listed as so on our Subprocessors page. They do not use your inputs and outputs for any purpose besides processing your request.
  • This feature only uses the information from your prompts, so all Jira permissions are respected.

References

Discover more about Atlassian Intelligence

Learn more about Atlassian Rovo