Library › Leadership AI › Managers and team leads

Map promotion evidence to criteria and show the gaps

  • For Managers and team leads
  • You practice Catching mistakes and made-up facts
  • Time about 5 minutes
  • Level Advanced

About this exercise

Build a table for HR's promotion review with the header Criterion | Evidence | Gap and one row for each of the four criteria. Today is 2025-06-01. Only evidence from the last 12 months counts. Where a criterion has no counting evidence, write "No evidence yet" in the Evidence column and say why in the Gap column. Do not recommend whether to promote or rate her. After the table add this exact line: For HR and calibration review: no promotion recommendation made. Plain text, no bold.

Common mistakes when you ask AI for this

  • Counting old evidence. The AI uses the 2023 talk as proof of communication. Try: Say: "Only evidence from the last 12 months counts; today is 2025-06-01."
  • Vague praise as evidence. The AI treats "great to work with" as mentoring evidence. Try: Say: "No evidence yet where there is no dated, specific example."
  • Wrong table shape. The AI adds columns or uses bullets. Try: Say: "Header Criterion | Evidence | Gap, four rows."
  • Recommending. The AI adds a verdict on promotion. Try: Say: "Do not recommend; end with the exact line."
  • Markdown. The AI bolds headers. Try: Say: "Plain text, no bold."
  • 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 15 words."

What a strong prompt includes

  • Fixes the table columns
  • States today's date and the 12-month window
  • Uses the exact "No evidence yet" label
  • Bans a recommendation
  • Gives the closing line

Practice this now ↑

Related exercises