Step-level traces

A waterfall view of every step with timing, so you can spot the slow tool call or runaway loop instantly.

Structured logs

Full inputs and outputs for each step, searchable and filterable by agent, status, model, or custom tags.

Token & cost accounting

Per-run and per-agent spend broken down by model. Set budgets and get alerted before you blow past them.

Deterministic replay

Re-run any production trace with the same inputs and tool responses to reproduce a bug exactly.

Live alerts

Trigger on error rates, latency spikes, or cost thresholds — routed to Slack, PagerDuty, or webhooks.

Eval & feedback loop

Attach scores and human feedback to runs, then build datasets to evaluate prompt and model changes.

Export & integrate

Plays nicely with your existing stack

AgentArc traces are OpenTelemetry-native, so they flow into the tools your team already watches.

  • OTel export to Datadog, Grafana, Honeycomb, and more.
  • Webhook stream of every run event for custom pipelines.
  • Configurable retention from 7 days to multi-year on Enterprise.
100%
Steps traced
<1s
Trace search latency
Replays per run

Stop guessing what your agents did

Get full traces on every run from your very first deploy — free.