← All news
Global · AI & Technology
Global·AI & Technology

Google Cloud expands AI agent observability across BigQuery and Looker

Google Cloud is rolling out a unified telemetry framework for its data agents and custom agents built with ADK or LangGraph. The update brings agent logs into customer-owned BigQuery tables and adds generally available logging and governance capabilities.

AI Hubs United Editorial ·

Google Cloud has announced expanded AI agent observability and evaluation capabilities across BigQuery and Looker. According to the company, its unified telemetry framework collects activity from Google's data agents and custom agents built with Agent Development Kit or LangGraph, then stores it in customer-owned BigQuery tables for analysis. The rollout targets production challenges including tracking agent actions, managing token and query costs, and checking answer accuracy before changes reach users.

Google says Conversational Analytics agents generate telemetry without additional setup, while custom agents can send structured telemetry through a single line of SDK instrumentation. Agent-to-agent workflows routing queries to BigQuery data agents in Gemini Enterprise are now generally available and send monitoring metrics, trace spans and conversation logs to the agent's project. BigQuery conversation logging is also generally available, allowing teams to inspect prompts and responses in their warehouse.

The Conversational Analytics API, now generally available, includes automatic administrator audit logging and optional data-read audit logs. It also supports VPC Service Controls, customer-managed encryption keys and regional or multi-regional data residency. These controls give teams ways to inspect agent behavior while applying access, encryption and data-location requirements.

AI Hubs United original short summary of the source linked above. It is not the original article; read the full story at the source.