Your AI changed. Find the first step that did.
onetrace records each step of your pipeline as a receipt anyone can check. Compare two runs and it points at the first step whose output differs, and what was recorded there.
pip install onetrace "onetrace-console[neighbours]" "onetrace-explain[keyring]"

classify, where a rule setting changed.Record, compare, prove.
Record every step
One receipt per step: what went in, what came out, the tool and its settings. Add it with your coding agent, with no code change, or step by step.
Find the first difference
Open two runs in the console. It names the first step whose output differs, the settings that changed there, and the exact text.
Check without trusting the code
A separate verifier reads only the bytes on disk. Change a receipt after the run and it says which one.
Your invoice agent paid €4,000 on a €40 invoice. Where do you start?
Check it was recorded. Read the bad run. Compare it with a good one. Find runs like it. Ask what changed, and whether it's just noise. Re-run it without paying twice. Check who allowed it. Ask for an explanation you can check. Nine avenues, one record they all read from.
Walk through the nine avenues →An illustrative example, not a real event.
The wrong payment shows at pay. onetrace points at extract, the first step whose output differs.
Facts first. Then a model's reading, labelled as one.
onetrace-explain takes the two runs and separates what the record shows from what a model suggests.

Three ways in. Pick the one that fits today.
Ask your coding agent
Paste one prompt into Claude Code, Cursor, Copilot or another agent. It adds the recording, asks what only you know, and reports back.
Use the prompt → no code changeZero-config
Start your app with onetrace-run. Calls through httpx, requests and the openai client are recorded as steps.
Step by step
Two decorators on the functions you already have. You name each step and what it records.
Add decorators →Local, checkable, and clear about its limits.
No account
Runs are folders on your disk. Nothing is sent anywhere unless you ask: Explain with a model you configure, or an outside timestamp.
Independent check
onetrace-verify uses the Python standard library only and trusts none of the code that wrote the record.
Ready for CI
onetrace diff exits 0 when two runs match and 1 when they diverge, so a job can gate on it.
Stated limits
A faithfully recorded wrong answer still verifies. What it doesn't prove.
See it on real runs first.
The live demo holds 58 runs of 11 example pipelines, some broken on purpose. Or run the same demo locally with one command.
onetrace-console demo --open