Library › Research AI › Managers and team leads

Pick turnover benchmarks that actually match your restaurants

Practice: Setting limits and rules. About 5 minutes.

About this exercise

Your regional director wants your restaurants' turnover compared to a fair benchmark. From 6 sources, you want exactly 2 numbered picks that are US restaurant-industry data from 2025 or later with a stated method, each with its turnover figure and a reason under 15 words. Use only the details in your list, plain text, and nothing else.

Common mistakes when you ask AI for this

  • Not stating the criteria. The AI picks the most quotable numbers, like the UK report or the 2023 study, because they look rigorous. Try: Spell it out: "US only, 2025 or later, with a stated method."
  • Letting the AI add context. The AI explains what each source likely found beyond your list. Try: Add: "Use only the details in my list."
  • Getting an analysis. The AI compares your 71% to every number and writes a verdict you didn't ask for. Try: Say: "Output only the 2 picks, no comparison."
  • Not saying how many. The AI decides the length itself and usually returns more picks than you can use. Try: Be exact: "exactly 2 numbered picks."
  • Getting markdown back. AI defaults to bold labels and headings, which show up as stray symbols in a note to your director. Try: Ask for "plain text, no bold, no headings."

What a strong prompt includes

  • Gives the criteria
  • Says exactly how many
  • Asks for the figure
  • Limits each reason
  • Asks for plain text

Practice this now ↑

Related exercises