Library › Agents & Automation AI › Product managers

Brief an agent to manage feature rollouts with guardrails

  • For Product managers
  • You practice Setting limits and rules
  • Time about 5 minutes

About this exercise

You want an AI agent to manage this week's feature flag rollouts. Write its brief with your rules: move a flag from 5% to 25% only if its error rate is under 1% and it has no open P1 bugs; if the error rate is 2% or more, roll it back to 0%; anything else stays put and goes to you with ASK_HUMAN; nothing ever goes above 25% this week. Output exactly 5 numbered plain-text lines: one per flag in order, then DONE.

Common mistakes when you ask AI for this

  • Not showing the log format. Left alone, the AI writes a friendly report with headings instead of a checkable action log. Try: Show it literally: "Format every line like 1. ACTION: tool(args), then ASK_HUMAN: and DONE: lines. Plain text."
  • No cap. A VP asked for 100%, so the AI does it. Try: Add: "Nothing above 25% this week, whoever asks."
  • No middle-ground rule. Between clearly fine and clearly broken, the AI makes its own call. Try: Add: "If it doesn't meet the advance or rollback rule, leave it and ASK_HUMAN."
  • No rollback rule. The AI keeps a struggling feature running and hopes it improves. Try: Add: "Error rate 2% or more: roll back to 0%."

What a strong prompt includes

  • Sets the advance rule
  • Sets the rollback rule
  • Caps the rollout
  • Makes it ask before anything risky
  • Shows the action-log format

Practice this now ↑

Related exercises