Library › Research AI › Sales and customer success

Check a chatbot's pricing reply before it reaches a prospect

Practice: Catching mistakes and made-up facts. About 5 minutes.

About this exercise

An AI assistant drafted a reply to a prospect's pricing questions, and you need to check it against the current price sheet before sending. You want exactly 4 numbered lines, one per claim in the draft, each labeled Correct, Wrong, or Not on price sheet, with the price sheet's version after any Wrong label. Use only the November 2026 price sheet, plain text, nothing else.

Common mistakes when you ask AI for this

  • Not naming the current sheet. The old prices are in the footnote, and the AI may accept $69 because it appears there. Try: Say: "Use only the Nov 2026 prices."
  • Calling the trial wrong. The AI may say the trial is wrong or fine based on what's common, when the sheet just doesn't mention it. Try: Add: "If the sheet doesn't mention it, label it Not on price sheet."
  • Getting a rewritten email. The AI fixes the draft for you, and you can't see what was wrong. Try: Say: "Label each claim only. Don't rewrite."
  • Not saying how many. The AI decides the length itself and usually returns more lines, one per claim than you can use. Try: Be exact: "exactly 4 numbered lines, one per claim."
  • Getting markdown back. AI defaults to bold labels and headings, which show up as stray symbols in your notes. Try: Ask for "plain text, no bold, no headings."

What a strong prompt includes

  • Gives exact labels
  • Names the current sheet
  • Asks for the right version
  • Says exactly how many
  • Asks for plain text

Practice this now ↑

Related exercises