THE DAILY EDITION · 13 NOVEMBER 2026
Google adds AI agent observability and governance tools in BigQuery and Looker
Why this story?
Google’s announcement ties AI-agent monitoring, evaluation and spending controls to products already used for analytics and reporting.
Google said it is expanding AI agent observability and evaluation capabilities across its Data Cloud, with unified visibility into first-party data agents in BigQuery and Looker and custom third-party agents built with frameworks such as Agent Development Kit or LangGraph. The company said the tools are meant to let enterprises see how agents reason, what data they touch and what they cost to run.
The rollout includes a unified telemetry framework that captures logging data from first-party and third-party agents into BigQuery tables that customers own. Google said that approach is intended to surface performance and usage information across developer and administrator tools.
Google also said users can track projected token usage and engagement in the BigQuery Studio Monitoring tab and Looker System Activity dashboards, or query agent event logs through BigQuery SQL. The company said BigQuery conversation logs record token counts and turn latency, and that users can set query byte-scan caps and daily token quotas, the latter in preview, to help control spending.