Packrat Documentation
Packrat verifies your code changes in production and directs your coding agent to follow up when they fall short.
See the quickstart for setup instructions.
How it works
You dual-ship telemetry data from your existing monitoring agents (ex: Sentry, DataDog, OpenTelemetry) and Packrat queries our copy of the data to validate the change. No Packrat-specifc tooling is installed within your application.
Besides telemetry data like exceptions, traces, logs, and session replays, Packrat also collects change context: GitHub PRs and coding agent session logs. This context combined with your telemetry data lets Packrat determine if a change is working as intended.
When Packrat determines a change needs an adjustment, your coding agent uses Packrat-provided tools to generate the followup PR. Your coding agent can also query our copy of the data for additional context.