Library › AI Evals › Business analysts

Rebuild a 20-case set so it matches Pedalbot's real traffic

  • For Business analysts
  • You practice Giving the right context
  • Time about 5 minutes
  • Level Beginner

About this exercise

Pedalbot's current test set has 20 cases, and every one is an easy question. Rebuild it as 20 cases whose mix matches last month's real traffic exactly (scale the traffic percentages to 20). Write a markdown table with the columns Category, Cases and Example input, one row per category in the order listed in the traffic data, then a final line "Total: 20". Each example input is a customer message in quotes. Plain text, under 190 words.

Common mistakes when you ask AI for this

  • Overweighting the risky cases. The AI follows the safety lead and puts half the tests on accidents. Try: Say: "Match last month's traffic percentages exactly: 8, 5, 4, 2, 1."
  • Keeping only easy cases. The AI adds a few edge cases but leaves the old mix mostly intact. Try: Say: "Scale the traffic counts to 20; every category gets its share."
  • Missing the total line. The AI ends with a paragraph of advice instead of a total. Try: Add: "End with exactly: Total: 20."
  • Describing, not writing, inputs. The AI writes "a question about refunds" rather than a message. Try: Add: "Each Example input is a real customer message in quotes."
  • Essay around the table. The AI adds a strategy section and bold headings. Try: Say: "Plain text, only the table and the total line."

What a strong prompt includes

  • Matches the real traffic
  • Asks for a table
  • Asks for example inputs in quotes
  • Asks for the total line
  • Asks for plain text

Practice this now ↑

Related exercises