AI Brand Visibility + Fact Check: ChatGPT, Claude, Gemini, Perplexity

Do AI assistants mention your brand, and do they get your business facts right? This Actor asks AI models the questions you choose, with web search switched on, using your own API keys. English and Turkish.

Two modes

Visibility (mode: visibility, default). For every question and model you learn whether your brand, your domain and your competitors appear, in which position, with which sources and with what tone. Add a category (for example "ceramic mugs" or "seramik kupa") to also ask discovery questions that do not contain your brand name: does AI recommend you unprompted?

Fact check (mode: fact-check). You enter the true facts (phone, address, opening hours, price range, founding year, main product). The Actor asks the models about them and your facts are compared with the answers. Result per answer: matches (the answer states the fact as you gave it), differs (it states it differently) or not-stated (the answer does not give it). The summary adds unclear when answers disagree, and flags a fact when repeated answers state the same wrong value. Your fact values are not written to the results.

Try it without a key

If you enter no API key, the Actor does not fail. It writes a preview row: the questions it would ask and the number of checks (events) a real run would use. No model is called and nothing is charged.

Input

Field	Description
mode	visibility or fact-check
brand, domain	Your brand name and website domain (required)
language	en, tr or auto (Turkish when brand, category or questions contain Turkish letters)
competitors, questions, category	Visibility: up to 5 competitors, up to 50 questions (empty = 10 template questions), optional category
phone, address, hours, priceMin, priceMax, currency, foundedYear, mainProduct, repeats, includeAnswerExcerpt	Fact check: the true facts and options
models	Subset of openai, anthropic, gemini, perplexity (empty = every model you entered a key for)
openaiApiKey, anthropicApiKey, geminiApiKey, perplexityApiKey	Your own keys, stored as secrets, sent only to the matching provider

{ "mode": "visibility", "brand": "Acme", "domain": "acme.com", "category": "ceramic mugs", "language": "en", "openaiApiKey": "..." }

Output

Visibility rows (one per question and model): brandMentioned, mentionCount, domainCited, domainMentionedInText, position, competitors, sentiment, citedUrls, citedDomains, answerExcerpt, kind (brand, category or custom). Fact-check rows: field, question, model, result, a non-readable deviationId. A final summary row (also saved as SUMMARY): mention rate overall, per model and per question type, competitor share and most cited domains (visibility), or flagged facts per model (fact check).

sentiment and fact comparison are simple rule-based checks, not an AI judgement. They can be wrong. The Actor reports what the models answered, not what is true about your business.

Not included

Google's AI Overviews are not read by this Actor. Gemini with Google Search grounding is the closest option that works with your own key.

Pricing and your costs

Pay per event: one event per question asked to one model (see the Pricing tab). Failed calls and preview runs are not charged. The AI providers bill you directly for their calls. Hard limit: 300 checks per run. You can also set a maximum cost per run.

Privacy and safety

API keys are used only in request headers. They never appear in logs, results or errors. Answer text is not stored in fact-check mode unless you turn on includeAnswerExcerpt, and e-mail addresses are removed from excerpts.

Full report: https://ruesandora.com