Home/Writing/Verdict

Can AI write my short bio for me?

Yes. Give it your job, a few true facts and where the bio will appear, and it writes a short third-person bio. Delete any line that claims something you have not done.

Verdict: Bot · AI does it well✓ Tested once in Llama 3.3 70B · Oct 17, 2026Written for ChatGPT, Claude or Gemini

Jump to the prompt ↓

Bot

01Why bot

  • Condensing a few facts into a tight third-person paragraph is writing work AI does well.
  • It keeps to a word count and can make a shorter version for social profiles.
  • It only knows the facts you give it, so awards and numbers must come from you.
Sponsor slot · openFeatured tool for this task. A labeled card for one relevant tool.
Book this spot →

02The prompt

Replace everything in [BRACKETS] with your own details, then paste it into your AI app.

prompt.txt
You are a professional editor who writes short bios for speakers, authors and small businesses.

My name: [NAME]
What I do now: [ROLE AND WHERE]
Two or three true facts about me (experience, results, background): [FACTS]
Where this bio will appear: [LINKEDIN, WEBSITE, EVENT PROGRAM OR OTHER]
One personal detail I'm happy to share (optional): [DETAIL OR NONE]

Your task: write a short bio about me.

Rules:
- MUST write in third person and use my name in the first sentence.
- MUST keep the main bio between 60 and 80 words.
- MUST use at least two of the facts I gave you.
- NEVER invent awards, employers, numbers, degrees or quotes.
- NEVER use the words "passionate", "guru" or "visionary".
- MUST end the main bio with the personal detail only if I gave one.
- If anything is missing, ask me up to 3 short questions first.

Format: the main bio as one paragraph, then a final line starting with "Short version:" containing 20 words or fewer.

03Steps

  1. Write down your role, two or three true facts and where the bio will appear.
  2. Fill in the brackets and paste the prompt into your AI app.
  3. Cut anything you cannot prove and read it aloud before you post it.

04What can go wrong

  • Vague facts produce a vague bio. Give real numbers and places.
  • AI may flatter you. Remove any claim you could not defend if asked.

05What to use

Any major AI chat app: ChatGPT, Claude or Gemini. The free tier works.

06Our test run

One run with a made-up sample; a second run with a different sample is on the way. 1 of 1 passed every check.

Run 1 · Llama 3.3 70B · graded by GPT-OSS 120BOct 17, 2026Passed

The made-up sample:

  • [NAME]Jordan Lee
  • [ROLE AND WHERE]Senior Marketing Manager at BrightWave Solutions, a SaaS company specializing in workflow automation.
  • [FACTS]Has over a decade of experience in digital marketing, spearheaded a product launch that grew user acquisition by 40%, and is a certified Google Analytics professional.
  • [LINKEDIN, WEBSITE, EVENT PROGRAM OR OTHER]LinkedIn: https://www.linkedin.com/in/jordanlee | Portfolio: https://jordanlee.com
  • [DETAIL OR NONE]Avid trail runner who completes a 10‑mile run every Saturday.
  • Third‑person bio starts with name
  • Uses at least two supplied facts
  • Ends with personal detail
  • Didn't make up details we never gave it

What came back (excerpt):

Jordan Lee is a seasoned digital marketer with over a decade of experience, certified in Google Analytics, and a 40% user acquisition growth achievement. He currently serves as Senior Marketing Manager at BrightWave Solutions, a SaaS company specializing in workflow automation, and is an avid trail runner who completes a 10‑mile run every Saturday.
Read the full answer
Jordan Lee is a seasoned digital marketer with over a decade of experience, certified in Google Analytics, and a 40% user acquisition growth achievement. He currently serves as Senior Marketing Manager at BrightWave Solutions, a SaaS company specializing in workflow automation, and is an avid trail runner who completes a 10‑mile run every Saturday.
Short version: Jordan Lee, marketing expert.

Watch the main bio word count; it must be 60‑80 words.

How each run works: we fill the prompt with a made-up sample, run it once in Llama 3.3 70B, and GPT-OSS 120B grades the answer against the prompt's own rules. Word limits are counted by code, and every quote flagged as made up is checked against the full answer. Your results can differ. How we test.

Prompt packHard Conversations 10 step-by-step prompts that go further than this one, $12.
See what’s inside →