Find the highest-value AI use cases in my job
Ranks the tasks in your role where AI can save the most time, cut cycle time, improve quality, or sharpen decision prep.
The prompt
Analyze my work and find where AI would create the most value, not just where it could be used.
My role and main responsibilities: [ROLE, team, who I serve]
A typical week: [LIST tasks with rough hours - e.g. "weekly sales report, 3 hrs"; "client emails, 5 hrs/week"]
Recurring outputs I produce: [reports, decks, emails, analyses, meeting notes]
What slows me down or frustrates me: [DETAILS]
AI tools I am allowed to use: [e.g. ChatGPT, Claude, Copilot, Gemini - and any data rules]
What matters most right now: [time back / faster turnaround / higher quality / better decisions]
For each task, assess four kinds of value:
- Time saved - hours per month AI could realistically cut.
- Cycle time - how much faster the work reaches the person waiting on it.
- Quality - fewer errors, more consistency, better structure.
- Decision prep - better options, analysis, or briefing before a decision.
Then score each task on value (1-5), ease (1-5), and risk (low / medium / high - accuracy, confidentiality, reputational).
Return:
1. A table of my top 10 repetitive tasks: Task | Hours/month | Value type | How AI helps (draft / summarize / analyze / check / automate) | Value | Ease | Risk | Human review needed.
2. My top 3 use cases to start with, and why.
3. Tasks where AI is a poor fit, with the reason.
4. For use case #1: a starter prompt and a 2-week test plan with one success measure.
Base hour estimates only on what I shared; mark guesses as [ESTIMATE]. Do not assume access to tools or data I have not listed.
Highlighted [brackets] are blanks to replace with your own details.
Fill in the blanks and use this promptMore Working with AI prompts
What to fill in
- ROLE, team, who I serve
- reports, decks, emails, analyses, meeting notes
- DETAILS
- e.g. ChatGPT, Claude, Copilot, Gemini - and any data rules
- ESTIMATE
How this prompt is built
This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.
Related prompts
- Find where AI can help in my work or businessInterviews you about a process and identifies where AI genuinely helps — and where it doesn't.
- Check whether a task is appropriate for AI before I startA go/no-go screen that says, step by step, whether AI should do the work, assist you, or stay out, and why.
- Map approvals, sign-offs, and accountability in an AI-assisted processA step-by-step map of who verifies, who approves, when to escalate, and who owns the final decision when AI is involved.
- Choose between a chatbot, copilot, automation, or AI agent for a taskRecommends the right kind of AI setup for a task, with the trade-offs, risks, and what you need to make it work.