Google Cloud details new AI agent observability for BigQuery and Looker
A Google Cloud blog outlines new AI agent observability and evaluation features across Google Data Cloud, covering agents that work with BigQuery and Looker.
- Google Cloud announced expanded AI agent observability and evaluation capabilities across Google Data Cloud for first-party data agents in BigQuery and Looker.
- The new capabilities also apply to custom third-party agents built with frameworks such as Agent Development Kit (ADK) and LangGraph.
- A unified telemetry framework captures agent telemetry, lands it in customer-owned BigQuery tables, and lets teams analyze it with their existing tools.
- BigQuery Studio provides prebuilt dashboards to monitor BigQuery Conversational Analytics agents, including usage, active sessions, top knowledge sources, and latency.
- Looker System Activity dashboards for Conversational Analytics, now GA, track engagement and token usage in Looker (Google Cloud core) and Looker (original).
Who it affects Teams who run AI agents on Google Data Cloud, including those using BigQuery and Looker for Conversational Analytics.
What to do
Enable Cloud Monitoring and Cloud Trace, opt in to per-agent conversation logging, add the BigQuery Agent Analytics SDK to custom agents, and use the provided dashboards and templates to monitor AI agents.
Source: cloud.google.com ·