Fill an RFP scoring template and catch weights that do not total 100

About this exercise

Write a prompt for a scoring sheet with exactly seven lines: "Price:", "Technical fit:", "Delivery:", "References:", "Sustainability:", "Total:" and "Flag:". The first five give the points from the notes. Total shows the addition. Flag says whether the weights equal 100 and, if not, that the procurement lead decides what to change. Do not fix the weights yourself. Plain text, under 90 words.

Common mistakes when you ask AI for this

• Fixing the weights. The AI quietly trims price to 35 or sustainability to 0 so the total is 100. Try: Say: "Do not change the weights; the procurement lead decides."
• Not adding them up. The AI assumes the weights total 100. Try: Say: "Total: show the addition."
• Wrong lines. The AI writes a table. Try: Quote the seven 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 labels
• Asks for the addition
• Says who decides
• Bans fixing the weights
• 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)