> For the complete documentation index, see [llms.txt](https://docs.icustomer.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.icustomer.ai/ireveal/ai-referral-measurement.md). # AI-referral measurement AI-referral measurement in iReveal: agents and LLM referrals as a first-class, identified, measurable channel. AI agents acting on your behalf, and on your visitors' behalf, are invisible to session analytics. A browsing agent does not accept a cookie banner the way a person does, does not stitch into a session model built for humans, and does not show up in a channel report that only knows paid, organic, and direct. Traffic from AI assistants and LLM answers is already arriving; most measurement stacks cannot see it, let alone credit it. ## Agents are first-class actors iReveal treats humans **and agents** as first-class, identified actors. An agent's visit resolves to an immutable ID the same way a person's does, its actions are captured server-side at full fidelity, and what came of them lands in the same trace, from event to identity to outcome. ## LLM referrals as a channel That makes AI referral a channel you can measure rather than a mystery slice of direct traffic: see the visits AI referrals drive, follow them to resolved people and accounts, and read what those referrals produced in pipeline and revenue, on the same [outcome tracking](/ireveal/outcome-tracking.md) every other channel gets. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.icustomer.ai/ireveal/ai-referral-measurement.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.