Systems | Development | Analytics | API | Testing

Join this session to learn about Agent Development Kit (ADK) and Model Context Protocol (MCP) integration methods that standardize how agents connect to your data while removing the need to build custom database connectors from scratch. Discover how to build agents with the ADK that accesses BigQuery for analysis, Google Maps for geospatial insights, and AlloyDB for transactions – all in a single workflow. Learn how to implement agent operations (AgentOps) for deep observability into both agent performance and cost with a single line of code.

Python UDFs now Generally Available (GA), you can run custom Python code natively, securely, and serverlessly inside your SQL statements. Write standard SQL, import libraries like BeautifulSoup, or run machine learning tokenizers with zero infrastructure management. Speaker: Products Mentioned: BigQuery, Python User Defined Function.

Check out the repo here. Manually vetting hundreds of project requests is a thing of the past. Imagine receiving every proposal with a built in risk score, resource check, and "Go/No-Go" recommendation—delivered in seconds. Join Kevin Blanco as he demonstrates how to build a powerful multi-agent system that seamlessly integrates Google Cloud and Asana. Watch along and see a real world example of automating an infrastructure request, returning instant historical pattern analysis and live workspace context without any manual steps.

Join Paul Ramsey, Product Manager at Google, for a demonstration of AlloyDB’s new Lakehouse Federation capability. Using a fictional financial services firm, Cymbal Investments, we show how analysts can research S&P 500 trends by combining real-time vector search with data in BigQuery and Google Cloud Lakehouse. In this video, you will see: Learn how AlloyDB enables cloud and AI transformation for your data platform.

For many, running generative AI over massive datasets has felt out of reach due to costs and slow processing times. Others settle for traditional ML techniques that require specialized skill sets and often deliver lower-quality results. With optimized mode for BigQuery AI functions, you can now get LLM-quality results at a fraction of the cost and at BigQuery speeds. In this video, we’ll show you how BigQuery uses model distillation and embeddings to process massive datasets, reducing query latency and token consumption.