Skip to main content
Log in Get started

See which scenarios your traffic reaches.

Find the scenarios with matching traffic, the ones still idle, and the traces that match none. Then decide where to add a test.

Get started freeExplore test cases

A test suite can look healthy while real conversations go untested.

Some scenarios appear in production traffic; others never come up. Start with the matches and the gaps to decide what to test next.

Covered scenarios

A conditional scenario is covered when classified production traces match it in the selected window. Its traffic count is not a pass rate or a completeness score.

Idle scenarios

Defined conditional scenarios with no matching traffic stay visible as no traffic. They may be important edge cases—or simply not observed during the window.

Unmatched traces

A classified trace that matches no conditional scenario is a concrete gap signal. Review it and decide whether the conversation deserves a new test.

Triage scenario coverage gaps

Review traffic gaps within a defined observation window.

  1. Fix the window and population

    Choose a time window and inspect captured traces. Trace export failures, sampling, and missing input can limit which interactions appear in the report.

  2. Separate traffic from verdicts

    Inspect scenarios with matches, scenarios with no traffic, and classified traces with no match. A matched scenario may still have failing checks.

  3. Choose the next scenario

    Review an unmatched request and decide whether to add or refine a conditional test. Inspect missing-input and unavailable-classification cases separately.

Use scenario coverage to choose the next test

Covered is not passed

A matching trace shows the scenario occurred. Open its results to see whether the checks passed.

Unmatched is not failed

No match means the classifier found no conditional scenario for that trace. Mibo keeps it separate from assertion failures and identifies cases to consider when expanding the suite.

Frequently asked questions

What does covered mean in Mibo?

A conditional scenario is covered when one or more classified production traces match the scenario during the selected time window. It describes observed traffic, not whether the assertions passed and not complete coverage of every possible interaction.

How does Mibo connect agent scenarios to real traffic?

Your system sends an execution trace over OTLP. Mibo classifies the trace input against conditional scenarios, evaluates applicable checks, and reports matching scenarios in Scenario Coverage.

What does an unmatched trace tell my team?

It tells you that a classified trace matched no conditional scenario in the selected window. That is a prompt to review the conversation and decide whether to add or refine a test—not proof that the agent failed.

Does Scenario Coverage prove my agent is fully tested?

No. Coverage reports classified traffic in a selected window, not whether checks passed. Unclassified inputs, missing evidence, and unobserved edge cases limit the signal.

Keep exploring