Your quality dashboard
Use the dashboard metrics to understand how your Agent’s traces score against your tests. They summarize completed evaluations and depend on the assertions and stage data your tests produce. They are not independent measurements of every response.
Choose a metric scope
Section titled “Choose a metric scope”If you have more than one Agent, use the selector beside Dashboard to choose which Agents the metric panels include. All agents includes every non-demo Agent. An Agent name limits the panels to that Agent. Demo shows the seeded demo data.
The selected scope applies to Quality, Determinism, Hallucination, Stage Pipeline Health, Scenario Coverage, Assertion Library In Use, and Test × Run. Latest Runs is separate and remains workspace-wide, including runs from other Agents.
Quality metrics
Section titled “Quality metrics”Your dashboard shows three summary metrics:
Quality
Section titled “Quality”The average assertion score across the completed test results included in the dashboard. It reflects the checks you wrote, not an independent assessment of overall response quality. A narrow test suite can produce a high score while leaving other behavior untested.
Determinism
Section titled “Determinism”The percentage of consecutive runs of the same test whose four stage statuses match: Router, Args, Tool, and Response. It measures stage-outcome stability, not identical response text. The dashboard needs at least two runs of the same test to calculate it.
Hallucination
Section titled “Hallucination”The failure rate of evaluated semantic assertions that you explicitly mark as hallucination_check. The metric stays unavailable until one of these checks has been evaluated. It does not independently detect hallucinations or review every response. To measure factuality, add criteria to a hallucination check and send a trace that the test applies to. See AI-powered quality checks.
A card can show — with a reason instead of a metric. For example, Quality can show Send your first trace, Determinism can show Needs ≥2 runs of the same test, and Hallucination can show Add a hallucination check. A metric that is not available on your plan shows Not available on your plan.
Stage pipeline health
Section titled “Stage pipeline health”The Stage Pipeline Health card shows where test results pass or fail. It has four stages:
| Stage | What it covers |
|---|---|
| Router | Intent-to-handler routing |
| Args | Argument validation |
| Tool | Tool execution |
| Response | Response quality |
Each stage shows its pass and fail percentages for the evaluated data. A stage with no evaluated data shows No data. If you have no evaluations yet, the card shows No evaluations yet. Send a trace to see stage health.
Select Show step-by-step per test to see the stage status for each test case. Select a test case to open its details. A row can show Passed, Skipped, No data, or the first failed stage.
Scenario coverage
Section titled “Scenario coverage”The Scenario Coverage card shows conditional scenarios over the displayed time window, which defaults to 7 days. It separates scenarios With traffic from scenarios with No traffic.
The card also reports:
- Traces that did not match any scenario. Consider adding a test for those conversations.
- Traces that could not be routed because the classifier was unavailable. Coverage counts can remain incomplete after routing recovers. Resending an accepted trace through Your API with the same identity returns
200 OKwithout queuing another evaluation. Identical OTLP retries do not reevaluate the trace either. - Traces without usable input, for which conditional coverage was skipped.
Other dashboard panels
Section titled “Other dashboard panels”- Assertion Library In Use lists each assertion type, its total count, and the number of test cases that use it.
- Test × Run shows test cases as rows and runs as columns. Its cells identify passed, failed, error, skipped, and pending results. Hover over a cell for its full date.
- Latest Runs lists the five most recent runs. Select a run to open its Agent’s test list.
Inspect an individual test result
Section titled “Inspect an individual test result”Open a test case from the Agent’s Tests page. Last Result shows the latest evaluation of that test: the test’s Input, any Error, the Assertions, and Raw output. Select an assertion to see details such as its reason, criteria, target, expected value, actual value, or semantic reasoning. Execution Logs shows the evaluation steps, and Last Run Trace shows the trace behind the result.
Until a trace is evaluated against the test, Last Result stays empty.
Read the result status
Section titled “Read the result status”The test list and Last Result use these statuses:
| Status | What it means | What to do next |
|---|---|---|
| Not Run | No trace has been evaluated against this test yet. | Check that the test is enabled and applies to your traces, then send a trace. |
| In progress | Mibo accepted a trace and is evaluating it. | Wait for the evaluation to finish, then refresh. |
| Passed | The trace met the configured assertions. | Review the result, then add tests for more scenarios if needed. |
| Failed | An assertion did not pass, or the evaluation hit a problem. | Check Error and the logs first. If assertions ran, compare the failed assertion with the recorded response. |
| Error | Mibo could not complete the evaluation. | Open Last Result, read Error, and check the logs. |
| Skipped | Mibo did not evaluate the test or check. | Check whether the test is disabled, whether it applied to the trace, or whether an assertion condition excluded it. |
A run can also appear as All Passed or Issues Found in the Latest Runs panel.
To clear a test’s past results, click Clear Runs on the test. In-progress runs are kept. Cleared results are permanently purged after 7 days.
Inspect traces
Section titled “Inspect traces”Open an Agent’s Traces page to review the traces Mibo evaluated. If your Agent sends an environment value, filter by All environments or a specific environment.
Select a trace to open its details. The detail view has four tabs:
- Overview shows the trace date and Conversation. When checks were evaluated, it also shows a Results summary with Tests ran, Passed, Failed, Skipped, and Did not apply. Scenario-routing information appears when it is available.
- Needs attention (N) lists failed, errored, and skipped tests. Select a review action to inspect a test and its failure details. Use View test to open the test case.
- All tests (N) lists every result for the trace. Select a test to inspect its assertions and evidence.
- Raw data shows the Raw trace payload and, when available, Execution metadata.
Trace content you see in Mibo has already been redacted. Secrets appear as placeholders such as [REDACTED:secret]. See Data handling.
If the trace has no extractable user or Agent text, the overview shows Conversation unavailable. Select View raw data to inspect the received payload. If an evaluation produces no result, the trace can show No checks were evaluated. It can also show Routing unavailable or No usable input when Mibo cannot route conditional tests. These states do not mean that the trace was rejected. For recovery steps, see If a trace appears without an evaluated result.
Using results to improve your system
Section titled “Using results to improve your system”If a semantic assertion has no usable evaluator score, follow Recover from a passive semantic evaluation issue before judging the Agent response. Once you have response evaluations, use this approach to improve their quality:
- Check Stage Pipeline Health. Look for the stage with the most failures, then expand Show step-by-step per test and open a relevant test case.
- Check the Error and logs first. An evaluation error can leave no assertion results.
- Review the Hallucination metric. If it is high, inspect the failed hallucination checks and their reasoning.
- Check Scenario Coverage. Find scenarios that have no traffic and traffic that matches no scenario.
- Save test edits, then send fresh traces. Mibo evaluates new traces against the saved version of each test.