Skip to main content

Observability shows what your agent did. Testing tells you if it was right.

AI agent testing from the traces you already emit. See what happened in your tracing tool, then see whether the execution broke a rule in Mibo.

Two questions about the same execution

Traces give saved tests the evidence to check your rules. In the example below, the refund went through and the manager approval check failed.

ObservabilityTesting with Mibo
See which steps ran and which tools the agent called.Check whether the recorded actions followed your rules.
Inspect a trace for the sequence of events and the values recorded.See the verdict and the evidence behind a check.
Read the trace to investigate what happened.Pick a recorded trace. AI drafts a test for you to review and save, then Mibo runs it on later eligible traces.
Collect and inspect traces.Use those traces as evidence for tests.

One refund, two views

Check what the reply says

A semantic check asks whether the reply explains the approval policy.

Check what the agent did

A procedural check uses the recorded refund amount and approval step to check the rule.

Send one export to both tools

Point your agent’s OTLP/HTTP exporter at the OpenTelemetry Collector and configure both destinations. Enable message content capture in your instrumentation so spans include usable input or output. Run your agent and confirm the trace appears in Mibo with the evidence you need before drafting a test.

See both setup options
receivers:
  otlp:
    protocols:
      http:
        endpoint: 127.0.0.1:4318
exporters:
  otlp_http/mibo:
    traces_endpoint: https://api.mibo-ai.com/public/traces
    headers:
      x-api-key: ${env:MIBO_API_KEY}
  otlp_http/other:
    traces_endpoint: '<YOUR_OTHER_OTLP_HTTP_TRACES_ENDPOINT>'
service:
  pipelines:
    traces:
      receivers: [otlp]
      exporters: [otlp_http/mibo, otlp_http/other]
Set MIBO_API_KEY in the Collector environment. The other destination may need its own credentials. 127.0.0.1 requires the app and Collector to share a network namespace. Adjust existing exporter headers for the Collector; endpoint variables accept one URL, not a comma-separated list.

Keep each tool on its own job

Keep cost and latency dashboards in your observability stack and prompt management in your development workflow. Your app runs the agent and enforces its rules. Mibo evaluates traces after execution, outside the request path.

When your current setup is enough

If your existing evaluations already check the tool-call rules you care about on production traces, you can keep that setup.

Keep exploring