AI Prompt Engineering
You can do a lot with AI – but it all starts with the instructions you give it. Learn how to write better AI prompts that deliver high-quality, relevant, useful responses.
PREP TIME
0m
Run TIME
5m
Persons
1
5-second summary
- Understand what AI prompt engineering is.
- Learn how to write good AI prompts.
- Keep the conversation going to get even better results.
WHAT YOU WILL NEED
- AI tool
PLAY resources
How to write better AI prompts
You can do a lot with AI – but it all starts with the instructions you give it. Learn how to write better AI prompts and get high-quality, relevant, useful responses.
What is AI prompt engineering?
AI prompt engineering is the practice of designing, refining, and testing the text instructions (or the “prompt”) that you input into an AI tool, such as Rovo, to get the desired output.
Why run the AI Prompt Engineering Play?
The results you get out of AI are only as good as the data and instructions you put in.
Despite its name, AI prompt engineering is more about communication than it is about engineering. Think of writing AI prompts like writing instructions for a teammate.
When you’re requesting something from a colleague or delegating a task, you think about the role that teammate is playing, what tasks you want them to do, what background information would be helpful, and any requirements for the deliverable. AI prompt engineering uses the same approach, helping you write clear, comprehensive instructions for your AI teammate to get the best output possible.
When should you run this Play?
This Play is most helpful for people who are new to using AI or trying to learn how to get better results. You can use it anytime you’re starting a new conversation with your AI tool or when the results of your request miss the mark.
3 benefits of AI prompt engineering
Writing good AI prompts leads to better, faster, and more relevant results from AI, empowers you to collaborate more effectively with AI tools, and helps you develop a future-ready skillset. It’s a foundational practice for getting the most out of AI in your daily work.
Benefits include:
- Improved productivity: Workers report AI increases their productivity by 33%, on average.
- Time-savings: People say AI saves them an average of 1.3 hours a day.
- Critical skill development: Writing clear AI prompts is the second most important AI-specific ability to develop in the coming year, according to workers.
1. Define AI’s role and the audience
Est. time: 1 MIN
Start by clearly stating who the AI is supposed to be (its role) and who it's helping (the audience).
The role could be a specific job function (like a marketer or an HR manager), a job level (like an entry-level professional or a C-Suite executive), or other persona you want the AI to embody.
The audience is who the output is for. Who will consume or benefit from what you’re creating?
This information helps shape how the tool solves your problem or responds to your request.
2. Define the task
Est. time: 1 MIN
Next, tell AI what task you want it to do or what action you want it to take. Be as specific as possible about the steps you want it to follow or the outcome you’re trying to achieve. (Vague requests like “Help me…” won’t produce great results.)
3. Outline requirements for the response
Est. time: 2 min
Then, list any requirements or preferences you have in mind for the AI’s answer. This could include:
* The tone or style you want the writing to be in
* How long you want the response or deliverable to be
* The format it should be in (such as an email, table, or bullet points)
Again, be as specific as possible. Unlike humans, AI doesn’t get overwhelmed or offended by too many details.
4. Provide context and background information
Est. time: 2 min
Like a teammate, AI needs context to produce relevant, useful responses. Give the tool as much relevant background information as you can think of.
Think about the “who, what, where, when, why, and how” of your task, such as:
- Who: Personas or details about the audience
- What: What you already know about the task, such as research or work that’s already been completed
- Where and when: Where and when the background information came from and/or where and when the output will be used
- Why: Why this task is important and the value you’re trying to provide
- How: How you want the AI to proceed, steps you want it to follow, and/or how the output will be used
提示：提前预定固定时间
安排固定的周期（例如每月一次），能让该演练更易成为常规惯例，而非一次性活动。
Follow-up
Don’t settle for the first response
Treat your AI interaction as a conversation, and provide more details or instructions to refine the output. For example, if you asked for help creating a project plan but the timeline it provided was too aggressive, give that feedback and tell the tool to extend the project plan over a longer period of time.
Put AI to work
Keep the momentum going, and run other Plays to make AI part of your team:
- AI Innovation Day: Build your team’s confidence with AI and explore more ways to use it to improve workflows.
- AI Training Workshop: Run a workshop to help anyone learn the basics of how to use AI at work.
- Fix It Friday: Schedule some time on a Friday to improve one workflow with AI.
- AI Teammate: Build your first AI agent.
还有问题？
与其他 Atlassian 使用手册用户开始对话、获取支持或提供反馈。
您可能喜欢的其他演练
利用人工智能进行优化
人工智能创新日
通过集中一天的学习和实践，让 GenAI 发挥最大作用。
利用人工智能进行优化
人工智能团队伙伴
构建您的第一个人工智能支持人员
用人工智能创新
人工智能培训研讨会
开展研讨会，帮助所有人学习在工作中使用人工智能的基础知识。
用人工智能创新
定义人工智能的项目角色
找出利用人工智能助力您下一个项目成功的机会。
了解最新信息
注册我们的时事通讯，获取最新的演练和 工作生活建议。
