AI Fact-Check — What ChatGPT & Perplexity Get Wrong
Pricing
$1,490.00 / 1,000 ai fact-checks
AI Fact-Check — What ChatGPT & Perplexity Get Wrong
Asks ChatGPT and Perplexity live (with web search) about a local business's hours, address, phone, and category, then verifies each stated fact against Google Business data. Returns a severity-ranked list of what AI gets wrong — conservative by design, so it never cries wolf.
Pricing
$1,490.00 / 1,000 ai fact-checks
Rating
0.0
(0)
Developer
moonlings
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
a day ago
Last modified
Categories
Share
AI Fact-Check — what do ChatGPT & Perplexity get wrong about your business?
AI assistants now answer "what are their hours?", "what's the address?", "are they open?" for millions of local businesses every day — and they get it wrong more often than you'd think. A wrong phone number costs you calls. "Permanently closed" costs you customers who never walk in.
AI Fact-Check asks ChatGPT and Perplexity live (with web search) about a specific business, extracts the facts they state — hours, address, phone, category — and verifies each one against Google Business data. You get a severity-ranked list of what the AI got wrong, with the AI's value next to the trusted value and its source.
It is conservative by design (see below) — the one thing worse than missing an error is inventing one.
What you get
One record per run:
| Field | Meaning |
|---|---|
matchedName | the business as Google lists it |
errorCount | confirmed errors — conflicts that reproduced across both AI engines |
findings[] | each: field, provider (ChatGPT / Perplexity), statedValue (what the AI said), truthValue + truthSource (what Google says), verdict, severity, reproduced |
trustedFacts[] | the ground-truth fields the check ran against |
providers[] | per-engine detail + the domains each AI answer cited |
conflationProviders[] | engines that answered about a different same-named business |
Verdicts: conflict (AI disagrees with a high-confidence Google fact), discrepancy (a difference worth checking — e.g. the AI cited the business's own site, which may be fresher than Google). Fields with no trusted source are reported as unverifiable, never as errors.
How it stays honest (why it won't cry wolf)
A false accusation — flagging a correct AI answer as wrong — is the worst outcome, so five guards sit in front of every error:
- A claim is only extracted if it actually appears in the AI's answer (no invented claims).
- A conflict is only counted as an error if it reproduces across both engines — a one-off is shown but flagged "seen once, may vary".
- If the AI cites the business's own website for a value, a mismatch with Google is treated as possibly-stale Google, not an AI error.
- Address and hours comparisons that are merely ambiguous (reworded, reformatted) resolve to a discrepancy, never a hard error.
- An answer about a different or same-named business elsewhere is flagged, and its facts are not graded as this business's errors.
How to use it
- Enter the business name and city, state (optionally a category and the website).
- Run. Results land in the dataset (JSON / CSV / Excel / API) in ~15–30 seconds.
Honest limits
- It checks the facts with a trusted Google source: hours, address, phone, category, rating. Services and prices aren't independently verifiable yet, so they're out of scope.
- AI answers vary between runs — this is a snapshot, and
reproducedtells you which findings held across engines. - For chains without an exact address, it checks the best-matched Google listing for that city.
For AI agents (MCP)
Agents can run this directly: add Apify's MCP server as a connector — https://mcp.apify.com/?actors=moonlings/ai-fact-check — and it appears as the moonlings--ai-fact-check tool, metered through your Apify account like any other run. It is also x402-payable — an autonomous agent can discover, pay for, and run a fact-check with no Apify account.
Who this is for
Local business owners, marketing agencies, and AEO / GEO (answer engine optimization) practitioners who need to catch AI misinformation before customers do — wrong hours, stale addresses, dead phone numbers, or "permanently closed" flags that ChatGPT and Perplexity repeat from outdated sources. It's the accuracy layer on top of AI-search visibility: being recommended by an answer engine only helps if what it says about you is actually right. Pairs with the AI Visibility Check (does AI mention you) — this one tells you whether what it says is true.
Other Actors by Moonlings
- AI Visibility Check — does ChatGPT recommend this business? Appearance rate, rivals, cited domains.
- Review Gap Check — Google rating vs. nearby rivals, with the gap math done.
- Local Business Competitor Analysis — full AI competitor scan and deep research reports.
