Library › Research AI › Freelancers and creators

Catch inflated claims in an AI-written bio before you post it

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

About this exercise

An AI tool wrote a professional bio for your voice-over website from your credits list, and you want to check it before posting. You want one numbered line per claim, under 60 words total, labeled Accurate, Inflated, or Not in credits, with what your credits actually say after any Inflated label. Use only your credits list, plain text, nothing else.

Common mistakes when you ask AI for this

  • Trusting the polished bio. The AI rounds up to sound impressive and won't flag its own puffery unless you ask it to compare. Try: Say: "Check each claim against my credits list only."
  • No middle label. With only right or wrong, the AI may call a stretched claim accurate. Try: Add an 'Inflated' label for claims that overstate the credits.
  • Getting a new bio. The AI rewrites the bio instead of showing you what to fix. Try: Say: "Label each claim only, no rewrite."
  • Trusting the AI to count words. AI is bad at counting. Ask for a total word limit and it often lands 10-20% over. Try: Cap each line: "each line under 10 words."
  • Getting markdown back. AI defaults to bold labels and headings, which show up as stray symbols in your website notes. Try: Ask for "plain text, no bold, no headings."

What a strong prompt includes

  • Gives exact labels
  • Names the source
  • Asks what the credits say
  • Sets a length limit
  • Asks for plain text

Practice this now ↑

Related exercises