Turn your Claude Code sessions into evals

Every Claude Code session is already a rich agent trace sitting on your disk — tool calls, results, errors, the lot. No instrumentation, no export step: pick a session file and analyze it.

Drop your traces here

JSONL · JSON · NDJSON · CSV · TSV · TXT · GZ · ZIP

Finding your session files

  1. 1Your sessions live in ~/.claude/projects/<encoded-project-path>/<session-id>.jsonl.
  2. 2List the most recent ones: ls -lt ~/.claude/projects/*/*.jsonl | head
  3. 3Drag one straight in. Files up to 200MB stream fine — a 9MB session parses in about 30 milliseconds.
  4. 4Subagent (sidechain) turns are excluded by default so the main thread stays readable, and the report says how many were set aside.

Sessions can contain file contents and secrets. Everything is parsed in your browser, and only bounded excerpts of individual traces go to the judging model — but if the code is sensitive, redact first or run GetEvals locally with your own key.

What you get back

A self-contained HTML report: the failure modes discovered in your own traces (not a generic checklist), a heatmap of which traces hit which mode, the exact quoted evidence behind every verdict, and the judge's own reliability numbers. Plus downloadable evals — a promptfoo config, an OpenAI Evals data file, and a portable judge suite — so the analysis turns into a regression suite you keep.

Related