Library › Leadership AI › Managers and team leads

Rewrite blame statements from a retro into blameless findings

  • For Managers and team leads
  • You practice Getting the tone right
  • Time about 5 minutes
  • Level Intermediate

About this exercise

Rewrite five blame-style comments from an incident retro into blameless findings about the process. Write exactly 5 numbered lines in the format: 1. Finding: ... Fix: ... Do not name any person, do not use the words careless, failed, forgot or blame, each line stays under 30 words, and every Fix starts with one of the verbs Add, Require, Route, Assign or Create. Use only what the comments say.

Common mistakes when you ask AI for this

  • Naming people. The AI keeps 'Raj' or 'Priya' in the finding. Try: Say: "Don't name anyone; describe the process gap."
  • Judgmental words. The AI keeps 'careless' or 'forgot'. Try: Say: "Ban the words careless, failed, forgot, blame."
  • Vague fixes. The AI says 'communicate better'. Try: Say: "Each fix is a concrete process change from the facts."
  • Wrong format. The AI writes a paragraph or merges findings. Try: Say: "Format: 1. Finding: ... Fix: ..."
  • Trusting the AI to count words. AI is bad at counting. Ask for a total word limit and it often lands over it. Try: Cap each line: "each line under 30 words."
  • Trusting the AI to count words. AI is bad at counting. Ask for a total word limit and it often lands over it. Try: Cap each part instead, for example: "each line under 12 words."
  • Adding headings and bold. The AI writes a formatted report with headings and an action list. Try: Say: "Plain text: only the 5 numbered lines."

What a strong prompt includes

  • Shows the format
  • Bans names
  • Bans words
  • Wants process fixes
  • Counts lines

Practice this now ↑

Related exercises