Prefer the guided path? Quickstart installs Kensa, finds and approves the production function or class used to start a conversation, and lands your first eval.
Run your first eval
Add Kensa, run
kensa init, and turn one realistic case into a passing eval.Learn the mental model
Understand how cases, traces, assertions, judges, and trials fit together.
Drive it from your agent
The
kensa-evals skill walks Claude Code, Codex, or Cursor through the eval lifecycle.Look up a command
init, doctor, connect, import, and eval - every flag in one place.How it works
Traces in
Import minimized, redacted trace evidence from Langfuse or a JSON / JSONL / OTLP export - or capture it locally.
Behavior out
Your coding agent mines imports into reviewable eval ideas you approve and materialize as pytest files.
Assertions gate the judge
Deterministic assertions run first. The
judge(...) call only runs if they pass, so obvious regressions never spend tokens.Ship in CI
Evals are plain pytest. Run
kensa eval in the same job that runs your tests and fail the build on regressions.Where to start
Data flow
Traces from real runs become regression tests. Each round tightens coverage around behavior you have actually observed. Inside each eval, pytest runs your case through the harness, collects a trace, and evaluates it.Compatible coding agents
Kensa scaffolds setup instructions and thekensa-evals skill for Claude Code, Codex, and Cursor. If none are detected, kensa init still prints a copyable setup prompt.