Library › Operations AI › Operations and supply chain
Pick the cheapest carrier that still arrives by Friday
- For Operations and supply chain
- You practice Catching mistakes and made-up facts
- Time about 5 minutes
- Level Intermediate
About this exercise
A shipment is ready Monday and must arrive by Friday. Write a prompt for plain text with exactly four lines: "Carrier A:", "Carrier B:", "Carrier C:" and "For approval:". Each carrier line shows the pickup day, transit days, arrival day, price and MEETS or MISSES. Count transit in business days from the pickup day. The last line names the cheapest carrier that meets the deadline; the logistics manager approves. Under 100 words.
Common mistakes when you ask AI for this
- Pickup on Monday. The AI ignores the cutoff and counts from Monday. Try: Say: "The shipment misses the 3 p.m. cutoff, so pickup is Tuesday."
- Choosing the cheapest overall. The AI picks Carrier B because the rep says Friday is doable. Try: Say: "Pick the cheapest carrier that MEETS the deadline."
- Wrong lines. The AI writes a comparison table. Try: Quote the four labels in order.
- 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
- Handles the cutoff
- Counts business days
- Names the approver
- 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)