How Traceback works

Traceback uses a combination of a browser automation runtime and a reasoning model to execute tests the way a real user would — without selectors, without mock data, and without a test harness.

The execution loop

When you run a test, Traceback:

  1. Opens a real browser session against your staging or production URL
  2. Interprets your test prompt and breaks it into a sequence of actions
  3. Executes each action — clicks, types, scrolls, waits — while capturing screenshots
  4. Evaluates whether each step passed, failed, or needs a retry
  5. Packages the full run as a result with timestamped evidence
Note

Traceback runs against live URLs. It is not a unit test framework — it tests the actual user experience, including network requests, third-party scripts, and auth flows.

How issues are created

When a test step fails, Traceback:

  • Captures a screenshot at the point of failure
  • Records the browser console log leading up to the failure
  • Asks the reasoning model to propose a root cause and fix
  • Creates an Issue with severity, evidence, and the proposed fix attached

Triggers

Tests can be triggered from:

  • Dashboard — one-click from the Tests page
  • CLItraceback run <test-id> in CI/CD
  • PR checks — automatic run on every pull request
  • Schedule — cron-based recurring runs
  • MCP — triggered by a coding agent mid-session

Autonomous mode vs. deterministic mode

ModeHow it worksBest for
AutonomousReasoning model drives the session end-to-endOpen-ended flows, exploratory QA
DeterministicFixed action sequence, no deviationCritical paths, regression testing