Self-driving – Proactive fixes from product data | PostHog

You have a new report in your inbox. (It already has a pull request.)
While you slept, PostHog dug through your product data, cut through the noise, and turned what matters into prioritized reports. When the fix is clear, an agent does the work. You decide what ships.
PostHog instruments your codebase, then combines that context with product data like analytics events, errors, and recordings to understand problems and propose fixes.
Supports Next.js, React, Python, and 24 more
MCP•Watch a demo•Talk to a human
Sources stream your product data into PostHog, and every notable finding becomes evidence for a report.
Exceptions and stack traces grouped into issues
Dead clicks, quick backs, long stalls
Tickets and conversations from your users
Zendesk, Linear, GitHub issues
Self-driving is autonomy from instruction, not from you. Agents work in the background without you prompting them to make progress, but nothing ships on autopilot.
The same Inbox and agents show up wherever your team works.
A desktop app for driving parallel agents to edit your product. The same Inbox and reports live here.
The full product in your browser. Explore your data, review proposed work, and dig into the evidence.
@PostHog brings reports, data answers, and agent work into the channels each team already watches.
Pull self-driving context into other tools, and pull context from your other tools into PostHog.
Self-driving from your terminal. Query your data and drive agents right where you already work, and wire it into your scripts and CI.
PostHog gives your product the context it needs to become self-driving: usage, errors, replays, flags, experiments, feedback, logs, and the tools agents use to act on what they learn.
Use PostHog as the full context layer for your product, or mix and match with your own tools.
Sync data in from your tools and databases, transform events as they arrive, and send data to the rest of your stack.
Store, query, and join your product and business data in one place without maintaining any infrastructure.
Define your metrics to keep them consistent across PostHog products, update them on a schedule.
Take any insight or SQL query and expose it as a stable API endpoint.
Ask questions about your data in plain English. Generates SQL, builds dashboards, and surfaces insights.
Write and run HogQL or standard SQL directly against your data. For when you know exactly what you want and just need to ask for it properly.
Combine insights, replays, flags, experiment results, and SQL into a single document. For when your analysis has a story and a dashboard isn't the right way to tell it.
Business Intelligence
Visualize your data with interactive dashboards and ad-hoc analyses right in PostHog.
The pocket guide to Self-driving
A quick overview of self-driving, plus real use cases. Each one walks through the report a scout files, the pull request it becomes, and the scout itself. You can also add each use case as a custom scout to your own product.
Work lands while you sleep. You wake up to diffs and reports waiting for review. Then what?
You're (still) the driver
Like a Waymo, a self-driving product doesn't decide where you're going (it just makes getting there easier). You choose where the product goes next.
Skip to the good part
Somebody's gotta clean up around here. Turns out it doesn't have to be you. Bug fixes and maintenance work land in your inbox. Hit merge and move on with your day.
Product capability used to scale with headcount. Now it's handled (without adding any). A small team with self-driving can outship companies 10x the size.
There are a few ways you can get answers to specific questions about self-driving products.
Read how Inbox, signal sources, scouts, reports, and pull requests fit together.
Use case books that walk through real scouts – each one ends in a one-click way to add it to your product.
Ask about the product, docs, examples, or how this fits your own workflow.