What teams build on the capture layer.

AI Search API is the API underneath AI-visibility dashboards, GEO platforms, share-of-voice reports and RAG pipelines. Each use case is the real workflow: the requests you send, the Envelope fields that do the work, and the limits stated honestly.

AI visibility monitoring

Your customers ask ChatGPT, Perplexity and Google before they ever reach your site, and what those surfaces say about your brand changes without notice. The dashboards that track this (Profound, Otterly, Peec) are products, not building blocks. If you are building the dashboard, or need the raw observations in your own warehouse, you need the capture layer underneath: real consumer-UI captures, re-run on a schedule by the Watch API, in a stable contract you can diff.

surfaces: ChatGPT · Perplexity · Copilot · Google AI Overview · Google AI Mode

The workflow, field by field

Generative Engine Optimization

GEO, getting your pages named and cited inside AI answers, fails without measurement. You cannot optimize for AI Overviews or ChatGPT answers if you cannot observe what they currently say, whether your brand or pages show up in the answer at all, and whether your change moved anything. Rank trackers watch positions on a SERP; GEO needs the answer itself, captured and diffed.

surfaces: Google AI Overview · ChatGPT · Perplexity · Google AI Mode

Field by field →

AI share of voice

When a buyer asks an AI surface "best X for Y", a shortlist comes back, and whoever owns that shortlist owns the category. Share-of-voice teams need the distribution: which brands get named, in what order, in what light, per surface and per market. That is an aggregation over many captures, which means it needs the real answers in one identical shape you can parse and aggregate, not screenshots pasted into decks.

surfaces: ChatGPT · Perplexity · Copilot · Google AI Mode

Field by field →

Citation tracking

Citations are the currency of AI search: being cited is the new ranking, and losing a citation is the new dropping off page one. Tracking them means capturing what the answer actually says and which sources it names or links, then watching that change over time. Answer engines do not announce citation changes; only captures reveal them.

surfaces: Perplexity · Google AI Overview · ChatGPT · Claude (API)

Field by field →

RAG & live grounding

RAG pipelines are only as good as what they retrieve, and model snapshots go stale the day they ship. Search-engine result APIs give you links without answers; model APIs give you answers without the live retrieval a consumer surface runs. Grounding on captured AI-surface answers gives you both, current, source-backed answer text your pipeline can quote, verify against, or decompose, in one contract per surface.

surfaces: Perplexity · Google Search · ChatGPT

Field by field →

You ship the product. We handle the capture.

Every workflow above runs on the same two endpoints and one canonical Envelope. Start with 500 free credits and the quickstart.

Start with 500 free credits Quickstart