# New AI agent observability and governance across BigQuery and Looker > Source: > Published: 2026-11-13 17:00:00+00:00 As enterprises move AI agents from experimental prototypes into production, data and platform teams are discovering that deploying an agent is only half the battle — you also need to see how it reasons, which data it touches, and what it costs to run. Today, we are announcing expanded AI agent observability and evaluation capabilities across Google Data Cloud, giving you unified visibility into your first-party (1P) data agents in [BigQuery](https://cloud.google.com/bigquery) and [Looker](https://cloud.google.com/looker) as well as custom third-party (3P) agents built with agent development frameworks such as [Agent Development Kit (ADK)](https://google.github.io/adk-docs/) or LangGraph. Putting conversational and autonomous agents into production requires solving three operational challenges: tracing multi-step reasoning while protecting sensitive data, controlling token consumption and query spend, and evaluating answer accuracy before prompt or schema changes reach users. Let’s explore how our new agent observability and evaluation capabilities help you do this. Running agents at scale means you need to see how they perform, what they cost, and what actions they take. We're rolling out a unified telemetry framework across Google's Agentic Data Cloud that works the same way for every agent: Capture telemetry from the agent, land it in BigQuery tables you own, and analyze it wherever your teams already work. **1. Capture telemetry from every first-party and custom agent** **First-party data agents:** Out-of-the-box Conversational Analytics agents emit telemetry automatically with no setup required. Queries routed to BigQuery data agents in Gemini Enterprise through agent-to-agent (A2A) workflows (now GA) send Cloud Monitoring metrics, Cloud Trace spans, and BigQuery conversation logs straight into your agent's project. **Custom agents:** Agents built with ADK or LangGraph stream the same structured telemetry into BigQuery through single-line SDK instrumentation. **2. Land telemetry in one governed home in BigQuery** **Conversation logging in BigQuery (GA):** [Managed 1P conversation logging](https://cloud.google.com/bigquery/docs/conversation-logging-overview) writes to BigQuery tables you own, so you can inspect Conversational Analytics traces, including prompts and responses, directly in your data warehouse. **Governed by default:** The [Conversational Analytics API](https://cloud.google.com/gemini/docs/conversational-analytics-api/overview), now GA, includes always-on admin audit logs and optional data-read audit logs in [Cloud Audit Logs](https://cloud.google.com/gemini/docs/conversational-analytics-api/audit-logging), and supports VPC Service Controls, customer-managed encryption keys (CMEK), and [regional and multi-regional data residency](https://cloud.google.com/gemini/docs/conversational-analytics-api/data-residency). **3. Analyze with dashboards wherever your teams work** **In BigQuery (GA):** Agent monitoring provides prebuilt [dashboards in BigQuery Studio](https://cloud.google.com/bigquery/docs/create-data-agents#monitor_agents_and_conversations) to track usage, active sessions, top knowledge sources, and latency across BigQuery Conversational Analytics agents. Enterprise observability requires balancing diagnostic telemetry with strict data privacy boundaries. Because tracking features involve ingestion and storage costs, Google Data Cloud separates operational telemetry from conversation content so admins and agent owners can govern each layer independently. At the project or organization level, admins can enable Cloud Monitoring (aggregate metrics such as request volume, latency, and token usage) and Cloud Trace (step-by-step spans for each request) across their environment, using Cloud Trace observability scopes to consolidate telemetry across multiple agent projects. To protect sensitive data, these operational metrics and sanitized first-party trace spans exclude customer core content (such as user prompts, model responses, internal thoughts, and generated SQL). When you need deeper transcript auditing, agent owners and editors can opt in to conversation logging on a per-agent basis: **Governed conversation logging in BigQuery:** When enabled, a Google-managed service agent streams user prompts, responses, and turn-level telemetry into a customer-owned BigQuery table (`agent_events`) via the BigQuery Storage Write API, inheriting your dataset's IAM permissions, CMEK, and VPC Service Controls. [Built-in privacy guardrails](https://cloud.google.com/bigquery/docs/conversation-logging-overview#conversation-logging-privacy) enforce a fail-closed check before each turn — skipping logging whenever a knowledge source uses row-level security, column-level policy tags, or dynamic data masking — while fail-open execution keeps your users' chat sessions uninterrupted if a logging error occurs. **Full trace trees for custom 3P agents:** While 1P conversation logging intentionally strips low-level tool arguments and internal SQL, developers building custom agents on ADK or LangGraph can instrument their code with the open-source ADK plugin ([`BigQueryAgentAnalyticsPlugin`](https://docs.cloud.google.com/bigquery/docs/bigquery-agent-analytics)). With a single-line setup, the SDK streams full tool-invocation execution trees, time-series telemetry, and multimodal payloads straight into BigQuery. **In-warehouse root cause and drift analysis:** Because conversation logs land natively in your `agent_events` table, you don't need separate export pipelines to diagnose failures. You can run BigQuery AI functions (such as `AI.GENERATE` to summarize error patterns and `AI.EMBED` with `VECTOR_SEARCH` to cluster recurring issues) or use the open-source `bigquery-agent-analytics` Python SDK and [Colab starter notebook](https://colab.research.google.com/github/GoogleCloudPlatform/BigQuery-Agent-Analytics-SDK/blob/main/examples/bqca_prompt_response_logging_customer_notebook.ipynb) for post-hoc semantic drift clustering and LLM-as-a-judge sentiment analysis. As agent adoption grows, FinOps and platform teams need clear visibility into consumption alongside active controls to prevent runaway spend. With [promotional trial pricing](https://cloud.google.com/products/data-agents/pricing) currently available for Conversational Analytics, now is a good time to establish baseline usage and cost guardrails: **Granular token and latency tracking:** In BigQuery conversation logs, each turn records input, output, thought, cached, and total token counts alongside total turn latency, while Looker System Activity reports estimated input and output tokens across your business intelligence (BI) workloads. **Turnkey observability dashboards:** You can track projected token usage and engagement in the BigQuery Studio Monitoring tab and native Looker System Activity dashboards, or query `agent_events` log data via BigQuery SQL using the open-source seven-page Data Studio report template and self-hosted Streamlit app in the [BigQuery Agent Analytics GitHub repository](https://github.com/GoogleCloudPlatform/BigQuery-Agent-Analytics-SDK/blob/main/docs/guides/bqca-prompt-response-logging-manual.md). **Active query and token spend caps:** To prevent unexpected charges before they happen, you can configure per-query BigQuery byte scan caps (`big_query_max_billed_bytes`) on your agent, which use dry-run estimates to block oversized queries without incurring on-demand scan charges. For BigQuery and the Conversational Analytics API, you can also enforce daily input and output token quotas (in preview) per project, user, or agent in the Google Cloud console and `gcloud` CLI. Runtime observability works alongside systematic evaluation. While logs and traces tell you how an agent behaved in production, evaluation benchmarks verify whether updates to your prompts, models, or data schemas improve SQL accuracy and answer quality before users experience a regression: **Benchmarking with Prism:** Our open-source evaluation tool, [Prism](https://github.com/GoogleCloudPlatform/conversational-analytics-prism), lets you test Conversational Analytics agents grounded in BigQuery tables or Looker Explores via the Conversational Analytics API using reusable test suites, regex assertions, and multi-region agent discovery (deployed behind an access layer such as Cloud IAP). **Unified evaluation and production analytics:** Prism can stream completed evaluation runs directly into day-partitioned BigQuery tables in your project, placing your pre-deployment benchmark scores right alongside your production `agent_events` logs for side-by-side analysis in BigQuery and Looker. **Native BigQuery evaluations:** First-party agent evaluations in BigQuery (built on the Gemini Enterprise Agent Platform evaluation service with bring-your-own-service-account support) are available in preview via API and a guided Colab notebook. Ready to bring visibility, governance, and cost control to your AI agents? Here is how to get started in three steps: **Enable first-party agent observability.** Turn on Cloud Monitoring and Cloud Trace in your project and opt in to per-agent [conversation logging](https://cloud.google.com/bigquery/docs/conversation-logging-overview) using the [BigQuery agent monitoring guide](https://cloud.google.com/bigquery/docs/create-data-agents#monitor_agents_and_conversations), and track BI token consumption with the [Looker Conversational Analytics overview](https://cloud.google.com/looker/docs/conversational-analytics-overview) and [Looker System Activity documentation](https://cloud.google.com/looker/docs/system-activity-dashboards#ca-sa-token-usage). **Instrument custom agents and deploy analytics dashboards.** Add the [BigQuery Agent Analytics SDK](https://github.com/GoogleCloudPlatform/BigQuery-Agent-Analytics-SDK/blob/main/docs/guides/bqca-prompt-response-logging-manual.md) to your ADK or LangGraph agents, launch the open-source Data Studio report template or Streamlit app, and explore in-warehouse log analysis with the [Colab starter notebook](https://colab.research.google.com/github/GoogleCloudPlatform/BigQuery-Agent-Analytics-SDK/blob/main/examples/bqca_prompt_response_logging_customer_notebook.ipynb). **Benchmark your agents and set cost guardrails.** Run automated accuracy suites with [Prism](https://github.com/GoogleCloudPlatform/conversational-analytics-prism), and configure BigQuery byte scan caps and daily token quotas via [Manage BigQuery costs for agents](https://cloud.google.com/gemini/docs/conversational-analytics-api/manage-costs).