The terms this product is built on — defined precisely enough to cite. Contract words like Envelope and absence-is-data mean exactly what the API enforces; category words like GEO get the working definition we measure against.
The contract rule that an AI surface returning nothing for a query is a valid, reportable result — not an error, and never a fabricated answer. If no AI Overview appears, the capture still completes: the surface is recorded as absent and the job is flagged, so downstream metrics can count the absence. Coercing absence to zero, retrying it away, or inventing content would corrupt visibility data.
Full entry: how it works in the API →also: Google AI Overview · AIO
Google’s AI-generated summary block shown above the classic results for many queries, composed by Google’s models from retrieved pages, with source links attached. Because it sits at position zero and answers the question directly, it reshapes what gets read and clicked — and there is no official Google API for it, so capturing one means rendering the real results page and extracting the block.
Full entry: how it works in the API →also: share of model · answer share
A brand’s proportion of presence in AI-generated answers relative to competitors: across a set of captured answers, how often each brand is mentioned or cited, in what position, and with what sentiment. Because AI answers differ by surface, phrasing and region, share of voice is only meaningful when computed from the actual rendered answers, captured and compared over time.
Full entry: how it works in the API →How often, how prominently, and in what light a brand, product or site appears in AI-generated answers across surfaces and regions. It is the AI-era counterpart of search visibility: instead of rank positions, the units are mentions inside answers, citations of your pages, position within the answer, and sentiment — all of which vary by surface, query phrasing and geography.
Full entry: how it works in the API →also: AEO
Optimizing content to be selected as the answer by answer engines — systems that respond with one composed answer instead of a list of links: Perplexity, Google’s AI Overviews, ChatGPT with search. AEO overlaps heavily with generative engine optimization; AEO emphasizes being the extracted, cited answer, while GEO names the broader practice across generative surfaces. In use, the two terms are often interchangeable.
Full entry: how it works in the API →also: api_surrogate
A capture fidelity level in which the answer is obtained from the model vendor’s official API as a stand-in — a surrogate — for the consumer product. It is a clean, stable baseline, but it is not what a person sees: consumer-UI-only layers such as shopping modules, ads, and the interface’s own source presentation are absent. Surrogate captures must be labeled as such, never passed off as UI captures.
Full entry: how it works in the API →also: consumer_ui
The higher-fidelity capture level: the response is taken from the actual consumer interface a person uses — the real ChatGPT app, the real Google results page — rendered in a real browser session. It includes what only the interface shows: the answer as presented, source treatment, AI Overview placement, shopping and ad modules. Contrast with an API surrogate, where the vendor’s API stands in for the UI.
Full entry: how it works in the API →The single, versioned response contract returned for every capture, regardless of surface or acquisition method. An Envelope carries the job header (status, warnings, artifact keys), provenance (how the capture was acquired and how each claim about it is known), the answer (text, markdown, blocks), evidence (sources, fan-out, mentions, shopping, ads) and raw (the verbatim upstream payload, by reference). One shape to parse, diff and store — instead of N per-provider formats.
Full entry: how it works in the API →also: query fan-out
The set of background search queries an AI surface issues to answer a single prompt. Surfaces like ChatGPT with search and Google’s AI Mode decompose one question into several sub-queries before composing the answer; capturing them reveals which searches your content must win to be retrieved and cited. Fan-out is only trustworthy with provenance attached: observed from the surface, inferred, or honestly absent.
Full entry: how it works in the API →also: GEO · LLMO
The practice of improving how generative AI systems — ChatGPT, Perplexity, Google’s AI Overviews and AI Mode — describe, cite and recommend your content or brand. Where classic SEO optimizes for ranked links, GEO optimizes for being used in the composed answer: cited as a source, named in a recommendation, and matched to the fan-out queries the engine actually runs underneath.
Full entry: how it works in the API →An AI surface that requires a signed-in account before it will answer: the Claude consumer app, Meta AI, DeepSeek, Amazon Rufus, Grok, and the Gemini web app. Anonymous proxy scraping structurally cannot reach them — there is no session to borrow. Reaching a login-walled surface takes either the vendor’s official API (a surrogate for the UI) or a real authenticated browser session.
Full entry: how it works in the API →also: own-fleet acquisition
The acquisition method where captures run on the provider’s own stealth-browser fleet — real browser sessions loading the real consumer surface — rather than through a third-party scraping vendor (managed-vendor) or the model vendor’s API (official-api). Owning the fleet is what makes durable artifacts possible, since the screenshot, proof-of-page HTML and raw capture are yours to keep, and what makes login walls a schedule rather than an architectural dead end.
Full entry: how it works in the API →The rendered-page HTML artifact retained with a browser capture, alongside a screenshot and the raw upstream payload. Together the three form a durable audit trail: when you need to demonstrate what an AI surface said on a given date, the page itself — not just someone’s parse of it — is still available. Proof only works if it outlives the capture, so retention must not expire in 24 hours.
Full entry: how it works in the API →also: observed vs inferred
The record of how a capture was acquired and how each claim about it is known. Observed facts are read directly from the surface; inferred ones are estimates and must be flagged as such with a confidence score — a UI model label is never silently equated with an official model ID. Provenance covers the acquisition lane, login state, region requested versus effective, delivered fidelity, and whether the surface was present at all.
Full entry: how it works in the API →Every definition above is enforced somewhere in the Envelope. See the surfaces you can capture, or run a query and read the fields yourself.
