Library › Operations AI › Operations and supply chain
Score vendor on-time delivery with the grace-day rule applied
- For Operations and supply chain
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Intermediate
About this exercise
Write a prompt for plain text with exactly four lines: "Vendor X:", "Vendor Y:", "Vendor Z:" and "Below target:". Each vendor line shows on-time deliveries / total = percent, rounded to a whole percent, and then MEETS or BELOW against the 95% target. Per the contract, a delivery one day late counts as on time. The last line lists the vendors that are below target. Under 70 words.
Common mistakes when you ask AI for this
- Counting every late arrival. The AI uses the raw late count, as the buyer's sheet does. Try: Say: "A delivery 1 day late counts as on time."
- Wrong below-target list. The AI lists Vendor Z because it had late deliveries. Try: Say: "List only vendors whose percent is under 95%."
- Wrong lines. The AI writes a table or prose. Try: Quote the four labels.
- Getting markdown back. AI adds bold, headings and bullets by default, which show up as stray symbols where this is pasted. Try: Say "plain text, no bold, no headings, no asterisks".
- Trusting the AI to count words. AI is bad at counting and usually runs long, so a vague "keep it short" lands over the limit. Try: Cap each part instead of the total, for example "each line under 15 words".
What a strong prompt includes
- Quotes the four labels
- Applies the grace day
- Shows on-time over total
- States the target
- Asks for plain text
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)