Agent skill · data analytics · aradotso
bigquery-agent-analytics-sdk
Analyze, evaluate, and curate AI agent traces stored in BigQuery with observability dashboards, LLM-as-Judge evaluation, trajectory matching, and Agent Context Graph decision-trace extraction at scale.
Why this skill is useful
Adds advanced analytics capabilities for AI agent telemetry in BigQuery, including decision-trace extraction and drift detection scripts.
What it needs
Requires bigquery-agent-analytics installed locally. Requires google-cloud account access. About 7k tokens when loaded. Last updated 2026-08-05. 5 stars on the source repository.
What this skill does
BigQuery Agent Analytics SDK Skill by ara.so — Data Skills collection The BigQuery Agent Analytics SDK is an open-source Python toolkit for analyzing AI agent telemetry stored in BigQuery. It provides observability (trace reconstruction, DAG visualization), evaluation (LLM-as-Judge, trajectory matching, multi-trial pass@k), and advanced analytics (Agent Context Graph for decision-trace extraction, drift detection, memory service). Built on top of BigQuery Agent Analytics, it's designed for ML engineers running agents in production who need to measure quality, understand behavior, and detect regressions at scale. Installation Prerequisites: Python 3.10+ Google Cloud project with BigQuery enabled Agent traces in BigQuery (via ADK BigQuery Trace Exporter) GOOGLEAPPLICATIONCREDENTIALS or gcloud auth application-default login configured Core Client API Initialize Client Retrieve and Visualize Traces Event Semantics CLI Commands The SDK includes bqaa (or bq-agent-sdk) CLI with 12+ commands: Diagnostics Views Management Evaluation Agent Context Graph Observability Create Event-Type Views Trace Visualization Evaluation System Evaluator (Code-Based Metrics) LLM-as-Judge Evaluation Trajectory Matching Multi-Trial Evaluation (pass@k) Grader Composition Eval Suite Lifecycle Management Agent Context Graph (Decision-Trace Extraction) The Agent Context Graph extracts decision traces from your agent's context: what requests it handled, what options it weighed, and what outcomes it committed, materialized as a BigQuery property graph. Deploy Context Graph (One-Time Setup) Extract Decision Traces (Python API) Extract Decision Traces (CLI) Schedule Periodic Materialization See Agent Context Graph Codelab for the full 35-minute guided walkthrough. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/bigquery-agent-analytics-sdk