# Eval-Driven Development

> TDD for AI agents that call tools. Write evals, mock MCP schemas, assert routing, gate PRs, and turn production misses into the next case.

## What this site is
Eval-Driven Development (EDD) is the same red → green → refactor loop as TDD, applied to prompts and tool schemas. The harness ships in Agent Lifecycle Kit (`kit eval run|ci|report`).

## Start here
- [Home](https://eval-driven-development.dev/)
- [EDD guide](https://eval-driven-development.dev/#guide)
- [Lifecycle](https://eval-driven-development.dev/#lifecycle)
- [Markdown guide](https://eval-driven-development.dev/docs/edd.md)
- [Eval suites](https://eval-driven-development.dev/evals/edd/README.md)
- [GitHub](https://github.com/mzworthington/agent-lifecycle-kit)

## Commands
```
kit eval run --suite evals/edd/architecture_routing.yaml --model scripted
kit eval ci --threshold-routing 95 --out out/reports
kit eval report --format md --out out/reports
```