Replay Vision
Contents
Not yet available to everyone – join the waitlist to get updates.
Replay Vision uses AI to automatically watch your session recordings 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.
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 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_observedevent.
When a scanner runs against a recording, PostHog:
- Renders the recording to a sped-up video (inactive periods are trimmed out).
- Sends that video, along with the session's raw events (clicks, pageviews, rage clicks, dead clicks, exceptions, and more), to a Google Gemini model.
- Asks the model to produce a structured response matching the scanner's type.
- Saves the result as an observation and captures it as a
$recording_observedevent 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.
Where to go next
- New to Replay Vision? Walk through your first scanner end-to-end.
- Picking the right scanner type? Read the scanner types reference.
- Authoring a scanner? See creating scanners for prompt patterns, filters, and sampling.
- Already have observations? Learn how to read them and query them as events to build insights, dashboards, and alerts.
- Hit a snag? Check troubleshooting.