02 / RUNS

Execution History

Every job, workflow and agent run captured end to end — inputs, outputs, retries, timing and cost. Replay any run, diff any two.

100M+
steps/day ingested
2.7s
median run capture
1-click
replay
step nesting

Step-level traces

Nested spans for every call in a run, with payload snapshots and duration breakdowns you can share with a customer.

Deterministic replay

Re-execute a run against pinned inputs to reproduce a failure locally or in staging.

Run diffing

Compare two executions field by field to see exactly which input drift caused a behavior change.

Retry intelligence

Attempt trees, backoff timelines and failure clustering so flakiness stops being folklore.

Agent-native

First-class capture of prompts, tool calls and token spend for LLM workflows.

Customer-visible history

Expose a scoped run timeline inside your own product — no dashboard rebuild.

Wired in one afternoon

  • Wrap any function to trace it
  • Automatic retry + timing capture
  • Replay and diff from the API
  • Scoped per-tenant run views
santati · runs.track
const run = await bb.runs.start('wf_reconcile', { org: org.id })

await run.step('fetch_ledger', () => ledger.fetch(period))
await run.step('match_lines',  () => matcher.run(lines))

await run.succeed({ matched: 1204, unmatched: 3 })
// -> replay: bb.runs.replay('run_31ba')

Ship execution history this quarter