# Echo Program

> One call, a sealed engine, a verdict. Everything a training team or its coding agent needs to take a forecast, act on it, and report what happened.

## Documentation
- [Full API reference](https://echo-program.com/llms-full.txt): every endpoint, field, limit and error, plus the agent guide
- [Reference client](https://echo-program.com/client/echospace_pilot.py): Python 3, no dependencies
- [OpenAPI schema](https://api.echo-program.com/v1/openapi.json)
- [Agent skill](https://echo-program.com/agents/SKILL.md): drop into .claude/skills/echospace/SKILL.md
- [AGENTS.md section](https://echo-program.com/agents/AGENTS.md)

## Guides
- [Guides index](https://echo-program.com/guides): what to decide before spending training compute

## The program
- [The pilot](https://echo-program.com/pilot): what partners send, what comes back, terms
- [Benchmarks](https://echo-program.com/benchmarks): every verdict and the training curve it came from
- [Log in](https://echo-program.com/login): members' dashboard with their API key and ledger