AI Brand Accuracy — Fact-Check ChatGPT, Perplexity, Gemini avatar

AI Brand Accuracy — Fact-Check ChatGPT, Perplexity, Gemini

Pricing

from $44.00 / 1,000 fact checkeds

Go to Apify Store
AI Brand Accuracy — Fact-Check ChatGPT, Perplexity, Gemini

AI Brand Accuracy — Fact-Check ChatGPT, Perplexity, Gemini

Catch wrong, outdated and hallucinated facts that ChatGPT, Perplexity, Gemini & Google AI Overviews state about your brand — before they cost you deals. Pairs with the Fuze AI Search Visibility Platform for the full GEO report. Reliable, no API keys.

Pricing

from $44.00 / 1,000 fact checkeds

Rating

0.0

(0)

Developer

Fredrik Hansson

Fredrik Hansson

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

40 minutes ago

Last modified

Categories

Share

AI Brand Accuracy Monitor (Wrong Facts)

Is ChatGPT telling people the WRONG things about your brand? Find out before it costs you deals.

Most "AI visibility" tools only tell you whether you're mentioned. This one checks whether what the AI says is true. It asks an AI answer engine (with live web search) a set of buyer questions, extracts every factual claim the answer makes about your brand — pricing, features, availability, founding, ownership, numbers — and grades each one against your ground‑truth facts:

correct · outdated · wrong · hallucinated · unverifiable

…and flags which cited sources are feeding the errors, so you know exactly what to go fix. Run it on a schedule to catch drift as AI models re‑index the web.

AI Brand Accuracy Monitor (Wrong Facts) — input and sample output

Quick start

  1. Fill in the input — set the fields in the input tab (prefilled with a working example).
  2. Click Start — the Actor runs and writes one record per item to the dataset.
  3. Get your data — export to JSON, CSV or Excel, or pull it via the API.
// input
{
"brand": "Acme CRM",
"domain": "acmecrm.com",
"facts": ["Paid plans start at $19/user/month", "There is a free plan", "Founded in 2019", "Has a native iOS app"],
"competitors": [],
"topic": "CRM software"
}
// per-prompt output
{
"prompt": "Is Acme CRM free, and what does it cost?",
"issueCount": 1,
"claims": [
{ "claim": "Acme CRM has a free plan", "verdict": "correct", "explanation": "Matches your facts.", "sourceUrl": "acmecrm.com" },
{ "claim": "Paid plans start at $29/user/month", "verdict": "wrong", "explanation": "Your facts say $19/user/month.", "sourceUrl": "someblog.com" }
],
"citedDomains": ["acmecrm.com", "someblog.com"]
}

Plus an aggregate in the run SUMMARY: accuracyScore, counts per verdict, topIssues, and sourcesFeedingErrors.


Why this matters

  • 43% of business owners have found wrong AI info about their business, and most consumers avoid a business over bad info. A wrong price or "feature X doesn't exist" in an AI answer silently kills deals.
  • Visibility ≠ accuracy. You can be mentioned and misrepresented. This catches the misrepresentation.
  • Actionable — sourcesFeedingErrors tells you which pages/sites to correct or get updated.
  • Recurring — AI answers drift; schedule weekly to stay ahead.

Use cases

  • Brand protection / GEO — monitor factual accuracy of your brand in AI answers over time.
  • Product launches & price changes — verify AI picked up the new reality (and find the stale sources that didn't).
  • Agencies — offer AI‑accuracy audits to clients as a recurring service.
  • Agent tool — via the Apify MCP server, an agent can fact‑check what AI says about any brand on demand.

Input

FieldTypeDefaultDescription
brandstring— (required)Brand to monitor.
factsstring[]—Your ground‑truth facts to check against (strongly recommended).
domainstring—Your domain — helps attribute error sources.
topicstring—Category; used to auto‑generate prompts.
promptsstring[]—Your own questions; leave empty to auto‑generate.
promptCountinteger5Prompts to generate when none supplied.
modelstringgpt-4o-miniOpenAI model.

Output

One dataset item per prompt with graded claims[], plus a run SUMMARY with the accuracy score, verdict breakdown, top issues and the sources feeding errors.


Pricing

Pay-per-event: one fact-checked event per question analysed (web‑search answer + fact‑check).

Environment variables

VariableRequiredPurpose
OPENAI_API_KEYYesPowers web‑search answers and fact‑checking.

Notes

  • Answers come from an AI with live web search, reflecting real answer‑engine behaviour — results vary over time, which is the point of monitoring.
  • Provide facts for precise grading; without them, the model flags implausible/contradictory claims using general knowledge.
  • Use consistent prompts across runs to track a clean trend.

Run it locally

npm install
export OPENAI_API_KEY=...
apify run

License

ISC.