Google Cloud Next '26
2026-04-22..2026-04-24
Las Vegas, United States
as the organisers put it
Registration is live for Google Cloud Next 2026 in Las Vegas. Get your spot with early bird pricing to experience AI, labs, and keynotes.
who it's for
machine learning engineers, platform engineers, site reliability engineers, data scientists, security engineers, developer advocates, AI product managers
topics
multi-agent AI systems; retrieval-augmented generation (RAG); Gemini Enterprise integrations; Agent Development Kit (ADK) workflows; Model Context Protocol (MCP) visibility; sandboxed agent execution on GKE; Cloud Run agent deployments; continuous evaluation pipelines for agents; GPU-accelerated drug screening; multimodal agents with memory; vector search and BigQuery property graph
| title | author | length |
|---|---|---|
| use cases: Workflow automation for everyone | Holt Skinner, Tilde Ann Thurium | 52m |
Gemini Enterprise connects Google Drive plus SaaS like SharePoint, Jira, Confluence, ServiceNow, Salesforce and Slack into a single, access‑controlled search… | ||
| Build a production-ready RAG agent | Aron Eidelman, Balaji Subramaniam | 01h 32m |
Builds a production RAG system: a Streamlit RAG agent wired to Gemini 3.5 Flash via the Google Agent Development Kit, seeded with a small JSON menu (eight… | ||
| How to build and scale multi-agent AI systems | Mofi Rahman, Lucia Subatin, Olivier Bourgeois | 01h 42m |
Shows how to deploy and secure agentic workloads on GKE with the Kubernetes-sigs Agent Sandbox (including a warm pool of sandboxes to avoid cold starts), use… | ||
| How to build AI agents | Pierrick Voulet | 55m |
Shows how to configure Gemini Enterprise connectors and MCPs to give agents real Workspace access, then demos calling Gemini Enterprise Agent Runtime from Apps… | ||
| Secure distributed multi-agent systems | Aron Eidelman, Leonid Yankulin | 01h 07m |
A demo web app deploys four Cloud Run agents (orchestrator, researcher, judge, content builder) that create courses and shows how to stop attacks before… | ||
| From vibe-code to production | Tilde Ann Thurium, Billy Jacobson | 01h 05m |
Prototype converts to deployable app: Google AI Studio wires a backend to Cloud SQL (Postgres) or Firestore, auto-creates schemas and connection strings, and… | ||
| How to build a continuous evaluation pipeline for multi-agent systems | Vlad Kolesnikov, Leonid Yankulin | 01h 25m |
Shows a runnable codelab that builds an automated regression pipeline for distributed agents using Gemini Enterprise Agent Platform, Cloud Run and the Gemini… | ||
| Coding with ADK to beat a text adventure game | Tilde Ann Thurium, Abdel Sghiouar | 57m |
Live demo builds a Python agent with the Agent Development Kit, connects via Vertex AI or AI Studio to Gemini 2.5 Flash, reads the game’s OpenAPI spec, and… | ||
| GPU-accelerated virtual drug screening | Tilde Ann Thurium, Jeff Nelson, William Hill, Saee Paliwal | 55m |
GPU-accelerated pipeline turns 2.9M compounds into production predictions: feature engineering with RDKit to Morgan fingerprints and scaffold splits, training… | ||
| Sneak peek: Vibe coding AI agents course | Anant Nawalgaria, Brenda Flynn, Smitha Kolan | 38m |
Five-day intensive teaches how to build autonomous agents that code from natural language and graduate them to governed, observable fleets using Google tools… | ||
| Building distributed multi-agent systems | Priya Pandey, Shir Meir Lador | 01h 54m |
Walks through building a self‑correcting Course Creation Pipeline that runs each specialist as its own Cloud Run service, using the Agent Development Kit and… | ||
| Building GPU-accelerated multi-agent apps | Chelsie Czop, Jay Rodge | 57m |
Shows a working GPU‑accelerated sustainability intelligence app that pulls satellite imagery, live telemetry and pre‑embedded policy PDFs to produce a… | ||
| Getting started with MCP Toolbox for Databases | Kurtis Van Gent, Stephanie Wong | 44m |
MCP Toolbox for Databases is an open source Go service (GitHub) that connects LLM agents to Cloud SQL, AlloyDB and BigQuery with production features: 15,000… | ||
| Developer recap of | Stephanie Wong, Mofi Rahman, Ivan Nardini, Casey West, Craig Labenz, Khanh Nguyen, Lucia Subatin, Jack Wotherspoon, Cynthia Wang, Aja Hammerly, Jigyasa Grover, Rody Davis, Richard Seroter | 01h 38m |
Live demo shows a three‑agent system that plans a Las Vegas marathon for 10,000 runners by combining an Agent Development Kit (ADK) planner, a GIS Python skill… | ||
| Developer keynote deep dive | Stephanie Wong, Michele Catasta, Sarah Kennedy, Ricky Robinett, Karl Weinmeister, Jeff Whelpley, Ankur Kotwal, Salman Ladha, Harrison Chase, Jason Davenport, Kevin Moore, Rody Davis, Ines Envid | 02h 58m |
Live coding shows which announcements actually work: hands-on demos of Gemini Enterprise and the new Agent Engine, Replit’s agent already builds >50% of its… | ||
| From the main stage to the terminal | Jason Davenport, Addy Osmani, Dave Elliott, Ben Gilbert, David Rosenthal, Shubham Saboo, Philip Kiely, Jay Rodge, Stephanie Wong, Yasmeen Ahmad, Khulan Davaajav, Katie Nguyen, Aja Hammerly, Tomek Porozynski, Muhammad Farooq, Omar Sanseviero, Logan Kilpatrick, Sam Witteveen | 05h 56m |
Gemini Enterprise Agent Platform now ships an end‑to‑end stack for building, scaling, governing and optimizing agents: Agent Development Kit… | ||
| The road to: The ultimate developer sneak peek | Stephanie Wong, Richard Seroter, Emma Twersky | 41m |
Preview shows concrete launches and playable demos: three keynotes, 600 sessions, a 67,000 sq ft showcase with 125 demos and 75 lightning talks, and hands-on… | ||
| Accelerate data science and analytics with GPUs | Greg Baugues, Jeff Nelson, William Hill | 01h 02m |
Live demo scans a 340‑million‑row weather table and returns city‑level aggregates in ~80–95 ms on an NVIDIA L4 attached to Cloud Run versus ~8–10 s on a CPU… | ||
| Hands-on AI workshop: Graph RAG, Memory & Multimodal Agents | Ayo Adedeji, Annie Wang | 01h 34m |
Live build produces a working multimodal rescue pipeline: Cloud Spanner Graph stores entities and vectors, Gemini Pro and a text embedding model generate… | ||
| Supercharge your AI agents: Inside the new ADK integrations ecosystem | Kristopher Overholt, Shubham Saboo | 01h 03m |
Demo shows a concrete end-to-end pipeline: ADK spins up a multi-agent summarizer+translator in less than two minutes, the Hugging Face → GitHub → Notion… | ||
| Hands-on AI workshop: Multimodal agents | Ayo Adedeji, Annie Wang | 01h 34m |
90 minutes of hands‑on steps show how to build and deploy multimodal agents that see, hear, and reason: code clones and Colab link, Vertex AI models (Gemini /… | ||
| Getting started with Antigravity | Stephanie Wong, Andy Zhang, Kevin Hou | 01h 04m |
Demo shows the Antigravity Editor and Agent Manager using Gemini Flash plus a specialized Computer Use model to run browser actions, take screenshots and… | ||
| nothing matches | ||