Databricks MLflow now ingests native OpenTelemetry traces from Claude
Databricks says its MLflow platform is now a supported destination for native OpenTelemetry export from the Claude Platform, released in Public Beta. Traces from Anthropic's SDKs, the Messages API and Claude Managed Agents arrive through Zerobus Ingest and are stored in Unity Catalog tables tied to an MLflow experiment, where they can be inspected alongside traces from other services or queried with SQL. Setup takes three steps: create an experiment with a Unity Catalog storage location, configure the Databricks destination using workspace ID, region and spans table, then run an agent and open the trace. Captured inputs and outputs require opting into the "full" content mode. MLflow Issues is also in Beta.
Why it matters
Agent failures often hide behind plausible answers, so trace-level records let teams find repeated tool calls and missing context, hand cases to domain experts for review, and re-run evaluations to check whether a fix helped while Unity Catalog governs access to the captured data.
Sources
- PrimaryDatabricks
Written by AIToolMaps from the source above and checked against it sentence by sentence.