Can AI spot fake reviews?

Half. It can flag reviews that look suspicious (vague praise, repeated phrases, off-topic details), but it can't prove a review is fake. Treat its flags as warnings, not facts.

Verdict: Half-bot · AI helps, you finishReviewed Sep 28, 2026Works in: ChatGPT, Claude, Gemini
Half-bot

01Why half-bot

  • Fake reviews often share patterns AI can notice across many reviews.
  • It can't see reviewer history or purchase records.
  • Real people sometimes write short, generic reviews too.

02The prompt

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

prompt.txt
You are a consumer researcher who looks for fake reviews.

Product: [PRODUCT]
Reviews (paste 20 or more, with dates and star ratings if shown): [REVIEWS]

Your task: flag reviews that may not be genuine.

Rules:
- MUST explain the specific pattern behind each flag (repeated wording, same-day bursts, no product details).
- MUST call them 'possibly fake', never 'fake'.
- MUST summarize what the unflagged reviews say.

Give me: a list of flagged reviews with reasons, and a summary of the rest.

03Steps

  1. Copy reviews with dates and ratings.
  2. Run the prompt.
  3. Weigh the unflagged reviews more heavily.

04What can go wrong

  • False positives happen; don't accuse anyone based on this.
  • A small sample makes patterns unreliable.

05What to use

Any major AI chat app.
Prompt packSmart Shopping 10 ready-to-paste prompts like this one, $9.
See what’s inside →
Sponsor slot · openFeatured tool for this task. A labeled card for one relevant tool.
Book this spot →