# Replay Vision - Docs

**Replay Vision is in closed beta**

Not yet available to everyone – [join the waitlist](/replay-vision.md) to get updates.

Replay Vision uses AI to automatically watch your [session recordings](/docs/session-replay.md) and turn what it sees into structured, queryable data. You configure **scanners** – named AI probes that describe what to look for – and PostHog applies them to your recordings, producing **observations** you can query, chart, and alert on.

The key idea is that Replay Vision actually *watches the video* of each recording alongside its events. This lets it pick up on visual and behavioral cues – hesitation, confusion, where a user's attention goes – that aren't captured by clicks and pageviews alone. Instead of manually reviewing hundreds of replays to spot a pattern, you describe what matters once and let it run continuously.

![The Replay Vision overview: observations over time, enabled scanners, the monthly usage meter, and the scanner list](https://res.cloudinary.com/dmukukwp6/image/upload/q_auto,f_auto/replay_vision_overview_app_light_9f82e7b066.png)![The Replay Vision overview: observations over time, enabled scanners, the monthly usage meter, and the scanner list](https://res.cloudinary.com/dmukukwp6/image/upload/q_auto,f_auto/replay_vision_overview_app_dark_73d0b2c435.png)

## How it works

Replay Vision is built around two concepts:

-   **Scanner** – a configured AI probe scoped to your project. A scanner has a natural-language prompt describing what to look for, a [scanner type](/docs/replay-vision/scanner-types.md) that determines what kind of output it produces, a set of recording filters that select which sessions it applies to, and a sampling rate.
-   **Observation** – one application of a scanner to a single recording. Each observation runs the scanner against that session and produces a structured result that's persisted and emitted as a queryable [`$recording_observed` event](/docs/replay-vision/observations.md#querying-observations-as-events).

When a scanner runs against a recording, PostHog:

1.  Renders the recording to a sped-up video (inactive periods are trimmed out).
2.  Sends that video, along with the session's raw events (clicks, pageviews, rage clicks, dead clicks, exceptions, and more), to a Google Gemini model.
3.  Asks the model to produce a structured response matching the scanner's type.
4.  Saves the result as an observation and captures it as a `$recording_observed` event in your project.

Each observation snapshots the scanner's configuration at the time it ran, so editing a scanner later doesn't change past observations.

## What you can do with it

A few examples of what teams use Replay Vision for:

-   **Spot dead ends** – flag sessions where users get visibly stuck on a page with no clear next action.
-   **Classify intent** – bucket sessions by what the user appeared to be trying to do (browsing, purchasing, getting support).
-   **Score frustration** – assign a numeric score to each session for how much friction the user experienced.
-   **Summarize sessions** – generate a short narrative of what happened in each session, so you can skim instead of watching.

Each of these maps to a [scanner type](/docs/replay-vision/scanner-types.md).

## Where to go next

-   **New to Replay Vision?** Walk through your [first scanner](/docs/replay-vision/start-here.md) end-to-end.
-   **Picking the right scanner type?** Read the [scanner types reference](/docs/replay-vision/scanner-types.md).
-   **Authoring a scanner?** See [creating scanners](/docs/replay-vision/creating-scanners.md) for prompt patterns, filters, and sampling.
-   **Already have observations?** Learn how to [read them and query them as events](/docs/replay-vision/observations.md) to build insights, dashboards, and alerts.
-   **Hit a snag?** Check [troubleshooting](/docs/replay-vision/troubleshooting.md).

## Further reading

-   [Session Replay](/docs/session-replay.md)
-   [Summarize sessions with PostHog AI](/docs/session-replay/session-summaries-ai.md)
-   [Find replays with PostHog AI](/docs/session-replay/find-replays-ai.md)

### Community questions

Ask a question

### Was this page useful?

HelpfulCould be better