> ## Documentation Index
> Fetch the complete documentation index at: https://www.usenotra.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent journeys

> A journey groups the pages one AI agent read in a session. Tag links to make journeys exact.

A journey groups the pages one agent read in a session. There are two kinds:

* **Tagged journey.** The agent followed a link with an `ntr` query parameter that your site minted, so the journey is exact.
* **Fingerprinted journey.** Notra matches requests with a heuristic that hashes the source, a truncated IP prefix and a 30 minute time bucket with a salt that rotates daily. For assistant browsing it uses the full IP and a 10 minute bucket instead. Because the match is a heuristic, fingerprinted journeys are estimates.

Journeys appear on the Overview page under the **Journeys** section and in the API. The **Agent journeys** table has **Journey**, **Source**, **Pages**, **Unique**, **Span**, **Last seen** and **Path** columns.

## Journey tagging

`@usenotra/geo/markdown` exports `mintJourneyId`, `getJourneyId` and `tagMarkdownLinks`. Use them to add an `ntr` id to the links you hand an agent in Markdown, so every follow-up request lands in the same journey.

On Next.js you can pass `tagLinks: true` to `createGeoProxy` instead, and the proxy then tags Markdown responses (`.md`, `llms.txt`, `llms-full.txt`) as it serves them to known AI agents. Add `html: true` to also tag the anchors in HTML pages. Human visitors and search crawlers always get the untouched origin response, and tagging needs no token.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.