Skip to main content
Every Mo session keeps one report. The session agent owns it, merges complementary entries, and removes duplicates as the sub-agents submit their work.

​
Test cases

A test case is the coverage Mo decided on, written so a person or a Momentic test can follow it: Two cases are duplicates when they check the same behavior under the same meaningful conditions, so Mo keeps distinct roles, permissions, and outcomes as separate cases.

​
Verdicts

A bug bash agent submits one verdict per case:
  • Verified: the case behaved as its acceptance criteria require.
  • Issues found: the agent saw behavior that does not match the criteria.
  • Blocked: the case could not be checked. Access, missing data, or a sandbox limit stopped it.
Each verdict carries a summary, the parts the agent verified, and the gaps it could not close. Alongside the verdict, the agent records the individual controls it exercised, each marked checked, failed, partial, or out of scope.

​
Bugs

Only a reproduced bug reaches the report. Each one holds: The report records which agent reproduced the bug, so you can open that conversation and read the run that confirmed it. From a bug you make a triage decision.

​
Review the coverage

Read the case list before you rely on a pass. A flow that is missing from it was not tested. Message Mo to widen or narrow the scope, or tell it which behavior is expected. That reason goes to the knowledge base as a triage decision.

​
Export the report

mo report writes everything above to a directory your coding agent can read:
--require-idle exits without writing unless Mo is idle and every sub-agent is done; omit it for an in-progress snapshot. The directory holds report.json, the manifest into four finding files, plus the bug recordings: Each recording download lands in the manifest’s artifacts list as { bugName, path } or { bugName, error }. Read every category findings names, since newer servers can add more. This is the handoff for the fix loop: hand mo-report/ to Claude Code, Codex, Devin, or Cursor, and the agent has the reproduction steps and videos it needs to fix the bugs. After the fix deploys to the same target, mo send asks Mo to rerun the original reproduction, and a second export into a separate directory shows the new verdicts. See fix what it found, then recheck.