Junjo Documentation

Junjo connects application execution traces with evaluation results, giving developers and coding agents a shared record to investigate failures and assess changes.

Your application owns execution and the meaning of quality. Your coding agent investigates and changes the code. Junjo preserves the evidence and makes it available through Studio and the evaluation CLI.

Get started

Start with one application feature you want to understand and improve.

1. Set up Junjo AI Studio.

   Deploy Studio to store traces, datasets, and evaluation results in an environment you control.

2. Connect your application.

   Configure OpenTelemetry traces. The Python SDK provides native Workflows and Agents with additional execution and state diagnostics. See the integration guides in the sidebar for supported external runtimes.

3. Evaluate a real feature.

   Follow Studio-connected evaluation to declare your application harness, define cases and criteria, and run a baseline against your application code.

4. Give your coding agent the evidence.

   Connect the evaluation skill so your coding agent can inspect failures, make a change, and compare the candidate against the same dataset.

Explore the platform

EvaluationApplication-owned harnesses, datasets, execution evidence, and run comparisons.

Junjo AI StudioSelf-hosted observability for inspecting application execution.

Python SDKBuild and instrument explicit Workflows and Agents.

Python API referenceGenerated reference for the public Python API.

Python is the currently released SDK. Future language SDKs will appear as separate guide and API sections without replacing the Python documentation.