How to use this
Open Claude Code or Codex (or a regular chat), copy the prompt and replace the text in square brackets with your own. Read the answer critically and refine the prompt if needed.
Data: in all examples use anonymized or test data, not real company documents. How to decide what you may give AI is covered in the AI Champion Blueprint. Check every AI answer: it can invent facts, which is why each scenario has a "what to check" line.
1. One summary across several projects
What AI does. AI combines the statuses of several projects into one traffic-light report.
Prompt:
Here are the statuses of 4 projects:
[paste]
Build one summary: colour (green, amber, red), main risk, the decision needed from leadership. One line per project.
What to check. You assign the colours, not the AI. Check against the real state of things.
2. Dependency map between teams
What AI does. AI finds who is waiting on whom and where the bottleneck is.
Prompt:
Here is a description of work across several teams:
[paste]
Find dependencies: who waits on whom, which work blocks other work, where the bottleneck is. Answer as a table.
What to check. Show the map to the teams: they know which dependencies are real.
3. Release risks
What AI does. AI helps work out what could derail a release and what to check before shipping.
Prompt:
Here is the release plan and list of open issues:
[paste]
What could derail the release? What should be checked before shipping? Propose "go" and "no-go" criteria and questions for the final call.
What to check. Agree the "go" criteria with the team and customer; do not take them as given.
4. Blameless incident review
What AI does. AI turns a timeline into a review: what happened, causes, what we change.
Prompt:
Here is the incident timeline:
[paste]
Write a blameless review: what happened, impact, causes, what worked, what we change. List separately the questions the timeline cannot answer.
What to check. Causes must follow from the timeline facts, not from AI guesses.
5. The gist of a long thread
What AI does. AI summarizes a long thread on a task.
Prompt:
Here is the thread on a task:
[paste]
Briefly: the point, decisions taken, what is unresolved, the next step and who owns it.
What to check. Make sure the thread has no customer data before pasting it into AI.
Turn these scenarios into your own system
In the 6-session program you turn prompts like these into ready agents and templates for your role. Not sure the format fits? Book a free 15-minute call on Telegram.