# Packrat Documentation

Packrat verifies your code changes in production and directs your coding agent to follow up when they fall short.

See the [quickstart](https://packrat.sh/docs/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.

## Where to start

- **[Quickstart](https://packrat.sh/docs/quickstart)**
- **[Query API](https://packrat.sh/docs/api)**

---

## Agent instructions

This page is part of the Packrat documentation, published as plain markdown for coding agents: add `.md` to any docs address, or read the index at https://packrat.sh/docs/llms.txt. This page: https://packrat.sh/docs.md.

Before wiring Packrat into an app, ask the developer for the URL of their setup page at https://packrat.sh/orgs, and read it with `packrat open <URL>`. It has the steps and the org's ingest key.