Skip to main content
Effort sets how long Mo tests and how many sub-agents it runs at once. Set it in the composer’s Session settings or with qa start --effort. The default is medium.

How the clock works

  • Testing time counts minutes while Mo or its sub-agents work, or while Mo waits on them. Time spent clarifying the request doesn’t count.
  • Mo and its sub-agents get reminders as the deadline approaches.
  • At the deadline, Mo stops the sub-agents still working, lets bug reproductions in progress finish, and reports what it covered and what it left unfinished.
  • If you change the request mid-session, Mo can restart the clock for the new scope.

Area splitting at high and max

On web, Mo can split a broad request into areas and hand each to a coordinating agent that plans and steers its own sub-agents. Mo covers the rest itself. Sessions started for a GitHub pull request don’t split. In Momentic’s evaluations on a full open-source web app, a one-hour high session finds several times as many confirmed bugs as a general-purpose coding agent given the same hour. Splitting at max finds more than three times as many confirmed bugs as the same session without the split.

Cost

A session bills:
  • The active runtime of its agents, not the session’s wall time.
  • Hosted browser time for web, or simulator and emulator time for mobile.
  • Model inference, at cost.
Higher effort runs more agents for longer. max runs many more flows than the other levels, so its total is higher even when its cost per bug found is lower. Reserve it for full-application coverage. The Mo tab in Settings > Usage shows estimated usage for a date range, with a daily chart and CSV export.