List what to remove before pasting into an AI tool

About this exercise

You want to paste this customer complaint into the public AI chatbot to draft a reply. Your company's AI policy bans 4 kinds of data. List every item you must remove first, numbered, one line per item (the street address and apartment count as one item), as 'exact text - category', using only the policy's 4 category names. Don't list things the policy allows. Plain text, under 80 words.

Common mistakes when you ask AI for this

• A yes/no answer. The AI says 'remove personal info' without listing what exactly. Try: Ask: "List every item to remove, with the exact text."
• Its own categories. The AI labels things 'PII' or 'sensitive', not your policy's terms. Try: Say: "Use only the policy's 4 category names."
• Over-redacting. The AI removes the product and date too, leaving nothing to draft a reply from. Try: Add: "Don't list things the policy allows: first names, products, dates, the problem."
• Trusting the AI to count words. AI is bad at counting. Ask for "under 80 words" and it often lands well over. Try: Ask for less than the limit and cap each line: "each line under 15 words, under 60 words total."
• Letting markdown in. AI adds bold and headings by default, and in your notes they show up as stray symbols. Try: Add: "Plain text only, no bold, no headings."

What a strong prompt includes

• Uses the policy categories
• Asks for the exact text
• Keeps allowed items
• Sets a word limit
• Asks for plain text

Practice this now ↑

Related exercises

• Accept a job offer and confirm the exact terms (Writing AI · Job seekers)
• Allocate shared rent by headcount using the right roster (Finance AI · Accountants)
• Announce a seasonal offer with its real terms and no fake scarcity (Sales AI · Small business owners)
• Answer a 'where is my order' email with the real new date (Writing AI · Customer support teams)
• Answer a big discount ask with two priced options (Writing AI · Sales and customer success)