# Trajectories

> See user behavior in your app before, during, and after an agent conversation.

## Overview [#overview]

<video
  src="/videos/trajectories/overview.mp4"
  poster="/images/trajectories/overview.jpg"
  aria-label="A person clicks and edits a task in a React app with capture on, then asks the agent a question. In the Intelligence dashboard, the saved Trajectory shows the clicks and form edits on a timeline, with a link to the agent Thread."
  className="my-8 w-full rounded-xl border border-[var(--border)]"
  loop
  playsInline
  controls
  autoPlay
  muted
/>

A Trajectory records a session in your app. It can include clicks, form edits, page changes, and network requests.

CopilotKit Intelligence stores these events and links related agent conversations. You can inspect what a person did before, during, and after a conversation.

<Callout type="info" title="Early access with our engineering team">
  Trajectories are in early access for proofs of concept with our engineering team. If you need help with access, [book time with our engineers](https://www.copilotkit.ai/talk-to-an-engineer).
</Callout>

Start with the [quickstart](/intelligence/trajectories-quickstart) to record your first session in self-hosted Intelligence.

## Choose a guide [#choose-a-guide]

| Guide | What you will do |
| --- | --- |
| [Quickstart](/intelligence/trajectories-quickstart) | Run Intelligence locally and find your first saved Trajectory. |
| [Capture interactions](/intelligence/capture-interactions) | Add capture to an app that uses CopilotKit. |
| [Captured data](/react-native/ms-agent-python/intelligence/captured-data) | Review the recorded fields, redaction limits, and controls that exclude data. |
| [API reference](/react-native/ms-agent-python/intelligence/trajectories-reference) | Look up `learning` options, Core methods, and capture error codes. |

## How Trajectories relate to Automatic Learning [#how-trajectories-relate-to-automatic-learning]

Trajectories provide evidence about how people use your app. [Automatic Learning](/react-native/ms-agent-python/learning) analyzes evidence and proposes Skills for you to review.

Capture alone does not start an analysis or change an agent. To use a Trajectory as evidence, add it to a Learning Space. See [Assign browser activity to a Learning Space](/react-native/ms-agent-python/learning#assign-browser-activity-to-a-learning-space).

After you review and publish a Skill, [Skill delivery](/react-native/ms-agent-python/intelligence/learned-skills) makes it available to an agent.

[User Memory](/react-native/ms-agent-python/intelligence/memories) stores facts about a person across conversations. It is a separate feature. You do not need User Memory or Automatic Learning to record and inspect a Trajectory.
