Library › Leadership AI › Executives

Stack-rank six projects against a capacity limit and show who is cut

  • For Executives
  • You practice Setting limits and rules
  • Time about 5 minutes
  • Level Intermediate

About this exercise

Rank the six projects by value per engineer-week (value points divided by engineer-weeks, one decimal; break ties by fewer weeks first), then fund them in rank order until the 24 engineer-week limit is reached without exceeding it. Output a markdown table with columns Rank, Project, Score, Weeks, Funded (yes/no). Then one line: Funded weeks: N of 24. Use the revised estimate for Atlas.

Common mistakes when you ask AI for this

  • Old estimate. The AI uses 12 weeks for Atlas. Try: Say: "Atlas is 9 weeks now."
  • Not skipping. The AI stops at the first project that does not fit. Try: Say: "Skip projects that don't fit and keep going."
  • Favoring the CEO's pick. The AI funds Ember. Try: Say: "Ranking is by score only."
  • Missing the total. The AI omits the funded-weeks line. Try: Say: "End with Funded weeks: N of 24."
  • 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 it: "table cells hold only short values."
  • 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."

What a strong prompt includes

  • Columns
  • Score
  • Skip rule
  • Total line
  • Revised

Practice this now ↑

Related exercises