Explore traces

The Trace Explorer is where you search, filter, and inspect every trace flowing through your AI applications. It's available in Studio at Observability → Traces.

Before you can explore traces, your application needs to be instrumented. See Send traces for setup instructions.

Every trace is a tree of spans. Each span represents one operation in the execution chain.

Click any trace in the list to open the span tree. Expand individual spans to inspect inputs, outputs, latency, and token usage at each step.

Explorer accepts a search expression language: write conditions on trace fields and combine them with AND, OR, and NOT.

Use bracket syntax to filter on any OpenTelemetry span attribute:

span_attributes['gen_ai.request.model'] CONTAINS 'mistral-large'
span_attributes['gen_ai.operation.name'] = 'chat'
span_attributes['custom.tag'] EXISTS

span_attributes['gen_ai.request.model'] CONTAINS 'mistral-large'
span_attributes['gen_ai.operation.name'] = 'chat'
span_attributes['custom.tag'] EXISTS

For array fields like models_used:

# All failed traces from a specific service
service_name = 'my-agent' AND status_code = 'Error'

# Traces slower than 5 seconds
duration_ns > 5000000000

# Traces using a specific model
span_attributes['gen_ai.request.model'] CONTAINS 'mistral-large'

# All failed traces from a specific service
service_name = 'my-agent' AND status_code = 'Error'

# Traces slower than 5 seconds
duration_ns > 5000000000

# Traces using a specific model
span_attributes['gen_ai.request.model'] CONTAINS 'mistral-large'

Turn production spans into evaluation records. Use the resulting Studio Dataset to drive an offline evaluation.

1. Open a trace and select a span in the span tree.
2. Open the span actions menu (⋯) and click Add span to dataset.
3. Select a dataset, or create one from the dataset picker.
4. Review the payload in Preview and edit. By default, it contains the span's resource and span attributes as JSON.
5. Optionally click Keep input, output only to reduce the payload to the span's input and output messages, or edit the JSON directly. Click Reset changes to restore the original payload.
6. Click Add to dataset.

The payload must be a valid JSON object. After the record is created, click View record in the confirmation to open it in the dataset.

1. In Explorer, switch the view from Traces to Spans, then filter to the spans you want.
2. Select spans with the row checkboxes. You can select up to 500 spans at once.
3. Click Add to dataset in the selection bar, then pick a dataset or create one.
4. Map span fields to record fields. For each mapping, pick a Span field (a span or resource attribute) and name its Record destination, either an existing field of the dataset or a new one.
5. Check the Record preview and the import summary, then click Continue and confirm the import.

Each selected span becomes one record that contains only the mapped fields. Spans with no value for any mapping are skipped. The import runs in the background. A notification tracks its progress and links to the dataset when it completes.

All trace data is accessible via the REST API. The endpoints are documented in the API reference:

• Traces: search traces, get a single trace, list fields and field options.
• Spans: list spans for a trace, query span evaluations.

Reading traces requires an Enterprise organization and one of the following roles:

A Workspace Admin or Org Admin can assign the Observability Viewer role to grant read-only access without admin privileges.