# General Context platform

> General Context turns an AI agent's production workflows into RL and eval tasks: each confirmed failure becomes a task built from the conversation, with a synthetic environment that answers with what the agent's tools returned in production, a simulated person and a grader. The tasks together are the company's benchmark. Connect with `pip install generalcontext` or `npm install generalcontext`.

## Get started
- [Introduction](https://generalcontextlabs.com/docs/introduction.md): We turn your agent's production workflows into RL and eval tasks, and your tasks into a benchmark.
- [Quickstart](https://generalcontextlabs.com/docs/quickstart.md): Install the SDK, initialize it once, and see your agent's conversations in the console.
- [Use a coding agent](https://generalcontextlabs.com/docs/coding-agents.md): Hand the whole setup to Claude Code, Codex, Cursor or any agent that edits your repository.

## Concepts
- [How it works](https://generalcontextlabs.com/docs/how-it-works.md): From a real conversation to a benchmark: traces, environments, tasks and benchmarks.
- [A worked example](https://generalcontextlabs.com/docs/example.md): One support email, followed from production to a graded task.
- [Tasks and environments](https://generalcontextlabs.com/docs/tasks.md): What a task holds, how it is graded, and how to run it as an eval or an RL environment.

## Connect your agent
- [SDK reference](https://generalcontextlabs.com/docs/sdk.md): Sessions, named steps, workers, redaction and every option of the Python and Node SDKs.
- [OpenTelemetry](https://generalcontextlabs.com/docs/opentelemetry.md): Add General Context as one more OTLP destination. No code change if your spans already carry GenAI attributes.
- [Import past conversations](https://generalcontextlabs.com/docs/import.md): Start review before connecting anything live: upload a file, or pull from Langfuse or LangSmith.
- [Outcomes and events](https://generalcontextlabs.com/docs/outcomes.md): Tell us what actually happened, so a conversation that sounded fine but booked nothing is caught.
- [Command line](https://generalcontextlabs.com/docs/cli.md): Check the connection, download the benchmark, and run it from the shell or CI.

## Trust
- [Security and data](https://generalcontextlabs.com/docs/security.md): Where your conversations live, who can read them, and how long they are kept.

## Optional
- [Agent guide and skill file](https://generalcontextlabs.com/docs/agents.md): everything a coding agent needs to connect an app, in one page
- [Everything in one file](https://generalcontextlabs.com/docs/llms-full.txt)
- [SDK source](https://github.com/GeneralContext/sdk)