5 agent patterns to master
Google Developer Expert, Sam Witteveen shares five patterns to consider when building agents. Speakers: Sam Witteveen Products Mentioned: Gemini
1 889
9.4
What's new with Gemini from Google DeepMind
Join Google DeepMind for an exclusive look at what’s new with Gemini and the research breakthroughs defining the next generation of multimodal intelligence.
232
14.7
Power intelligent agents with AI-native databases
AI-native databases are essential for powering agents with enterprise data. Learn how they enable highly relevant context, automate operations, and manage risk.
156
Building an AI app: A low-code guide for small teams
Build intelligent experiences without a team of AI experts.
17
13.4
Boost AI context with hybrid search in Spanner
Go beyond keyword search to get the most out of your operational data. In this session, learn to build sophisticated, AI-powered experiences with Spanner.
16
Generative UI for any agent, anywhere: A2UI, AG-UI, MCP Apps, and more
The future of the web isn’t just interactive – it’s adaptive. Break the “chat wall” with agents that customize UIs for any context.
14
15.9
What's new in Cloud Run
Explore new Cloud Run capabilities that simplify application deployment for AI agents and inference.
12
16.4
What's new in Google Cloud's agent platform
Explore the next evolution of Google Cloud’s agent platform, designed to empower developers and enterprises to build, scale, and govern sophisticated AI agents.
8
20.1
Build connected AI: Orchestrate tools and agents with registries and ADK
Move beyond simple prototypes and build agents that can access your organization’s most critical data – whether it lives in third-party SaaS or legacy on-premises systems.
6
What's new in Google Cloud databases for the agentic era
The agentic era demands a unified, real-time architecture for delivering relevant, accurate experiences at scale with your enterprise data.
6
13
The agent-quality flywheel: Using Gemini Enterprise Agent Platform evaluations to optimize agents
Treating agent quality as a rigorous engineering discipline is the only way to scale. Stop guessing and start measuring.
5
Agent context engineering for production
Homegrown sessions and state management can get you started, and local development environments can rely on filesystems and Git. But for scalable, maintainable deployed agents, you need more.
5
9.8
Agent development and AgentOps with BigQuery, ADK, and MCP
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
4
Engineering the future of Kubernetes for AI at scale
As the primary workloads of the enterprise shift to AI agents, inference, and large-scale batch processing, architecting hardware-aware platforms with high elasticity becomes essential.
4
Under the hood for startups: How Google DeepMind makes modeling decisions
What actually happens between a research breakthrough and an API release?
4
Build connected AI: Orchestrate tools and agents with registries and ADK
Move beyond simple prototypes and build agents that can access your organization’s most critical data – whether it lives in third-party SaaS or legacy on-premises systems.
4
What's new in Looker: Empowering business users in the governed agentic era
Trusted data defines the agentic era. Learn how Looker and Gemini redefine business intelligence by grounding AI in a governed semantic layer.
3
15.8
What's new for AI on GKE: Training, serving, and agents
The requirements for AI infrastructure are shifting rapidly, moving from frontier model serving to complex reinforcement learning and agentic workflows.
3
Scale AI agents in production
Take agents from prototype to scaled production with Google’s modular, generally available agent platform services.
3
27.3
From prompts to production: Startup multi-agent workflows
Autonomous multi-agent systems are speeding up how startups build and scale.
3
Beyond the hype: Orchestrating end-to-end developer workflows with agents
The latest DORA report tells us that while 80% of developers feel AI is enhancing their individual productivity, at the organizational level, more AI means more instability.
3
What's new in Google Cloud databases for the agentic era
The agentic era demands a unified, real-time architecture for delivering relevant, accurate experiences at scale with your enterprise data.
3
NoSQL for modern apps and AI: The future of Memorystore, Firestore, and Bigtable
Explore the latest non-relational database advancements across Memorystore, Firestore, and Bigtable.
2
From prototype to production: 45 minutes to a reliable Gemini Enterprise Agent Platform agent
Simple agents are easy. Reliable agents are hard. Join us for a high-velocity master class on the production-first approach to Gemini Enterprise Agent Platform.
2
12.8
Vibed into reality: Bring your ideas to life with Firebase and Google AI
As we enter the era of agent-native development, Firebase provides deep integrations with Google AI Studio to transform your vibed prototypes into feature-rich, production-ready apps.
2
Build AI agents on Cloud Run
Move beyond the prototype and scale your AI agents into production with a robust serverless infrastructure. In this session, discover why Cloud Run is an ideal platform for running agents.
2
22.1
Beyond the hype: Orchestrating end-to-end developer workflows with agents
The latest DORA report tells us that while 80% of developers feel AI is enhancing their individual productivity, at the organizational level, more AI means more instability.
2
Accelerate R&D with Gemini-based agents Co-Scientist and AlphaEvolve
Gemini-based agents like Co-Scientist and AlphaEvolve enable research and development organizations to accelerate knowledge discovery and scientific innovation.
2
16.1
The Gemini 3 playbook: Optimizing for quality, cost, and scale
Join this session for insights and best practices to optimize Gemini 3 applications for quality, cost, and scalability, gathered from our collaboration with top Google Cloud enterprise customers.
2





























