All updatesJuly 1, 2026

Replay an agent run step by step

Session Replay turns a run into a player you can step through, watching the agent's structure unfold, where time went, and what each step decided, in order.

A span tree shows the shape of a run, but not how it played out. Replay lets you move through it in sequence, where it branched, where it stalled, what each step decided, which is usually faster than reading a static tree when you're trying to understand behavior.

A persistent shell wraps every replay: transport controls, a structure graph, a timeline that exposes concurrency and idle gaps, and an inspector for the selected step. Switch the center between a narrative Story walkthrough and a proportional Tree-plus-gantt view. It runs on your live traces or bundled demo architectures, and reads the same span data as Traces, so anything your instrumentation captures shows up with no extra setup.

Read the Session Replay docs
  • FeatureSession Replay player on the Sessions page: step or play through a run
  • FeatureStructure graph, timeline, and inspector views, plus a narrative Story walkthrough
  • FeatureRuns on live traces or bundled demo architectures (parallel fan-out, ReAct, delegation, multi-turn)