Find the regression hiding behind a rising overall score

About this exercise

Spokewise patched Pedalbot to say 'not covered' when the policy is silent, then reran 50 test cases. The overall score went up, so the PM wants to ship. Write a plain text message to Dana in exactly 3 lines: 'Improved:', 'Regressed:' and 'Call:'. Write before and after exactly like 36 of 40 = 90% -> 32 of 40 = 80%. Improved is the column that got better; Regressed is the column that got worse plus what the bot now does wrong; Call starts with 'Call: Hold' or 'Call: Ship' and gives a reason. Under 85 words.

Common mistakes when you ask AI for this

• Cheering the overall score. The AI repeats 80% to 84% and says the patch worked. Try: Say: "Check every column, not just the overall score."
• Missing the hidden drop. The AI reports only the column the patch targeted. Try: Add: "Find any column that got worse."
• Percent without counts. The AI gives 'up 60 points' with no counts. Try: Say: "Format: X of Y = Z% before and after."
• Not saying what went wrong. The AI says a column dropped but not what the bot now does. Try: Say: "Say what the bot now does wrong."
• Long and formatted. AI adds bold headings and a summary. Try: Ask for "3 lines, plain text, under 85 words."

What a strong prompt includes

• Asks to check every column
• Asks for before and after math
• Asks what got worse
• Asks for a ship or hold call
• Asks for plain text

Practice this now ↑

Related exercises

• Accrue unpaid wages for the working days after the last pay period (Finance AI · Accountants)
• Age a returns queue in business days and flag the ones over the limit (Customer Support & Success AI · Customer support teams)
• Alert sales to a competitor's price change, facts only (Research & AI Search · Product managers)
• Annualize recurring revenue without the one-time fee (Data AI · Finance and accounting)
• Answer a credit dispute with the full-hour rule and the math (Customer Support & Success AI · Customer support teams)