Library › Data AI › Managers and team leads
Pick between two definitions of on-time delivery
- For Managers and team leads
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Advanced
About this exercise
Two teams define on-time delivery differently and the COO wants one definition. Write exactly 3 plain-text lines under 90 words with the math shown: 'Strict:' (delivered by the promised date), 'Grace:' (within 1 day after it) and 'Recommendation:'. Apply the decision criterion in the notes, name which definition to use, and say what the other team's number should be called.
Common mistakes when you ask AI for this
- Splitting the difference. The AI recommends a blend or a 'depends' answer. Try: Add: "Pick one headline definition using the agreed criterion."
- No numbers. The AI discusses the pros and cons without 82% and 94%. Try: Add: "Show 1,640 / 2,000 = 82% and 1,880 / 2,000 = 94%."
- Dropping the other team. The AI discards the Grace metric entirely. Try: Add: "Say the grace number can be reported under a different name."
- Leaving the format to chance. The AI picks its own length and layout unless told the exact shape. Try: Add: "Plain text, no bold or headings."
- 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
- States the criterion
- Shows the math
- Fixes the three labels
- Asks to rename
- Caps length
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)