Snapshots

A snapshot stores every step of a known-good run, in order, with the input your agent sent to each step and the output it got back. Comparing a new run against it shows exactly what your agent now does differently.

How snapshots fit in

You save a snapshot under a name, from a trace ID or from a run you just executed. The snapshot is stored self-contained. The snapshot and its source trace are pinned, so trace retention doesn’t remove them. Pinned snapshots are limited per plan, and saving again under the same name replaces the baseline and keeps its pin. See Save a baseline. You then compare runs against it:

• In tests, with the MatchesSnapshot assertion. A missing baseline fails the assertion.
• In production, with CompareSnapshotAsync. Each result is recorded in the dashboard, with expected and actual steps side by side.

What a comparison reports

Every change comes with its position and, for input and output changes, a line diff.

Snapshots and replay

In a replay, model outputs are recorded, so step inputs are where a code or prompt change shows up. A snapshot catches that change with no LLM call. Whether the change made outputs better or worse is a question for a live Judge run.

Deep dives