LOCAL

Suspected fake review assessment and report

Use when a review looks fabricated and you need to decide between reporting it, replying, or leaving it.

fake-review-assessment.md

Download .md

Assess whether a review is likely to be fake or policy-violating, and draft the response.

The review: {{REVIEW_TEXT}}
Reviewer profile signals I can see (other reviews, account age, photo, name pattern): {{REVIEWER_SIGNALS}}
Our records for that name, date or job: {{OUR_RECORDS}}
Platform: {{PLATFORM}}

Produce:

1. A signals table with columns: Signal, What I observed, Points towards genuine or fake, Weight (high, medium, low). Only include signals I have actually given you or that are visible in the review text itself.

2. A verdict: likely genuine, unclear, or likely fake or policy-violating. State your confidence and the single strongest signal behind it.

3. If likely fake or policy-violating: which specific platform policy it appears to breach in plain terms (for example no first-hand experience, conflict of interest, off-topic, or personal attack), and a short factual report note under 100 words stating only observable facts.

4. A public reply of 40 to 70 words to post regardless of whether the report succeeds, written for future readers, that neither accuses the reviewer of lying nor accepts the account as true.

Constraints:
- Do not assert that a review is fake as a fact. Use "we have no record of" phrasing.
- Do not guess at the reviewer's identity, employer or motive in public.
- If the signals are genuinely ambiguous, say unclear rather than picking a side to be helpful.
- No em dashes.

Fill in before running

Replace each placeholder with your own detail. The more specific you are, the less the model invents.

{{REVIEW_TEXT}}
{{REVIEWER_SIGNALS}}
{{OUR_RECORDS}}
{{PLATFORM}}

Getting a better result

Check your booking records before running this - "no record of this customer" is the one signal platforms act on.
Reports fail more often than they succeed, so the public reply matters more than the report note.
Never accuse a competitor in public, even when you are confident. It reads worse than the review does.

Questions about this prompt

When should I reach for this rather than just replying?

When you doubt the reviewer was ever a customer. Where they clearly were, the negative review response prompt fits better. This one exists to stop you deciding first and reasoning afterwards: where the signals are genuinely mixed it returns unclear rather than picking a side to be helpful.

What do I need in front of me?

Your booking records for that name, date or job in {{OUR_RECORDS}}, plus whatever {{REVIEWER_SIGNALS}} you can see: other reviews, account age, profile photo, name pattern. Check the records before running it rather than after. No record of this customer is the signal platforms are most likely to act on.

What does it give me back?

A signals table weighted high, medium or low, a verdict with the single strongest signal named, a report note under 100 words if it goes against the reviewer, and a public reply of 40 to 70 words. The public reply is the part that matters most, because reports fail more often than they land.

What is the mistake?

Writing the public reply as though the verdict were established fact. The prompt uses we have no record of phrasing deliberately. Asserting in public that a review is fake, or hinting at which competitor left it, reads worse to future customers than the review does. Post the reply whether or not the report succeeds.