Skip to main content
ReasonBlocks captures the model calls in your agent’s workflow and uses your application’s tasks to train and evaluate a smaller model. You keep your provider credentials and your existing Python client library throughout. How you connect depends on the provider. An OpenAI or Anthropic application connects to a data source in the dashboard, with nothing to install beyond a small helper. A Google Gemini or Amazon Bedrock application connects through the capture gateway, which runs in your own infrastructure.

​
Start with capture

For a Gemini or Bedrock application, start at Gemini and Bedrock instead — the steps below are the dashboard connection. Create a source in Data, copy its capture URL and key, and ask your coding agent to read the setup guide — its plain-text copy is /agent-setup.md — and integrate ReasonBlocks into the project. The exact instruction to paste is at the top of that guide. The setup CLI and skill generate a small Python helper and project configuration. Your coding agent connects the helper to the existing client and labels each task’s calls. The CLI and helper ship in rbtrace==1.1.1 on PyPI; the setup guide has the install commands. Capture does not require a sandbox or start training. Normal provider charges continue to apply when your application runs.

​
Train when your application is ready

Full-agent training needs representative tasks and a test copy of your tools and data that can reset between attempts. Your coding agent can help build the adapter for that environment. ReasonBlocks then prepares a plan, trains within the approved budget and reports complete-task results for review. Enabling a trained release is a separate decision. See Train your complete agent for the environment, evaluation and serving requirements.

​
Get started

Set up with your coding agent

One instruction, a setup CLI and a reusable skill.

Quickstart

Create a data source and connect your existing application.

Integrating your agent

Client settings, task headers and deployment checks.

Train your complete agent

Prepare a test environment, review training and evaluate a release.

Deploy your connected application

Ship the helper, connection configuration and runtime secrets.