3-Week Schedule
Theme: Build Your First Agent – Tools, Prompts, and Use Cases
Theme: Build Your First Agent – Tools, Prompts, and Use Cases
Theme: Agent Collaboration and Real-World Task Automation
David Parry, Developer Advocate | Qodo
In this hands-on lab, we will explore the process of creating intelligent agents that integrate with your IDE’s AI-powered plugin. These agents will assist you during your normal development workflow, solving everyday problems that are specific to your projects and teams.
By the end of this session, you will have a customized AI assistant embedded in your IDE, capable of providing context-aware suggestions, automating repetitive tasks, and enhancing your overall coding experience.
Theme: Designing Scalable and Intelligent Agent Systems
Ivan Nardini, Developer Relations Engineer | Google Cloud; Annie Wang, Developer Relations Engineer | Google Cloud
Description Coming Soon!
Micheal Lanham, Principle AI Engineer | Brilliant Harvest
In this two-hour course, participants will explore the design and implementation of behavior-driven conversational agents using Agent Flows—a flexible and powerful framework for modeling intelligent, context-aware, and autonomous interactions. Agent Flows extend traditional behavior modeling by embedding agency, enabling agents to reason, act, and communicate dynamically within multi-agent systems.
Through conceptual deep dives and practical hands-on activities, attendees will gain the skills to architect conversational agents that not only manage dialogue but also coordinate tools, access Model Context Protocol (MCP) servers, and engage in agent-to-agent communication.
The course will also cover debugging, tracing, and evaluation techniques critical for building reliable and adaptable agentic systems.
David Hughes, Principal Data & AI Solution Architect | Enterprise Knowledge
You've built your Graph RAG system with agentic workflows in the last session—now comes the critical question: How do you know it's actually working? Traditional LLM evaluation metrics fall short when measuring Graph RAG performance in production environments where agents make autonomous decisions based on retrieved knowledge.This advanced session tackles the unique challenges of evaluating agentic Graph RAG systems. Unlike simple question-answering scenarios, agentic workflows require evaluation frameworks that measure not just accuracy, but decision quality, reasoning consistency, and operational reliability under real-world conditions.
Lesson 1: What Makes Graph RAG Evaluation DifferentWe'll explore why standard retrieval metrics miss the mark for agentic systems. When agents use Graph RAG to make decisions, you need to evaluate retrieval quality, reasoning coherence, and downstream task performance simultaneously. We'll define evaluation frameworks that capture how well your Graph RAG system enables agents to achieve their goals, focusing on metrics that directly impact business outcomes rather than traditional accuracy measures.
Lesson 2: Practical Benchmarking with OPIKYou'll get hands-on experience setting up comprehensive evaluation pipelines using OPIK, an open-source platform designed for production LLM evaluation. We'll demonstrate how to create evaluation datasets that reflect real agentic scenarios, implement automated benchmarking workflows, and interpret results to identify system weaknesses. You'll learn to benchmark not just individual queries, but entire agentic decision sequences that reveal how well your Graph RAG supports agent reasoning.
Lesson 3: Production Monitoring and Continuous ImprovementWe'll conclude by looking forward and investigating strategies for ongoing system health monitoring in production environments. You'll learn techniques for detecting performance degradation, handling dynamic data environments, and implementing feedback loops that help your workflows improve over time. We'll cover essential aspects like monitoring data freshness, query performance, and agent decision quality.
We'll also explore multi-agent coordination strategies and how frameworks like Google ADK and A2Acan enhance your agentic workflows to ensure your Graph RAG system maintains reliability as it scales.By the end of this session, you'll have the tools and methodologies to confidently deploy and maintain Graph RAG systems that your agents can rely on for critical decision-making.
Philipp Schmid , AI Developer Experience | Google DeepMind
As AI continues to evolve, we will a shift from static chatbots to dynamic agentic AI systems capable of autonomous reasoning, tool integration, and multi-step problem-solving.
This hands-on workshop teaches you how to design and build agentic systems that go from basic chatbots to leveraging structured outputs, function calling, and workflow orchestration to solve enterprise-scale challenges. It bridges theoretical concepts with hands-on implementation strategies using models like Gemini 2.5 Pro.
Chi Wang, Founder of AutoGen (Now AG2) and Senior Staff Research Scientist | Google DeepMind
In this workshop, you’ll learn about AG2, a powerful open-source AgentOS for building AI agents capable of reaching high level of agentic freedom in terms of communicating, acting, and adapting in dynamic environments.Participants will gain hands-on experience using AG2 and Waldiez, a drag-and-drop UI for rapid agent workflow design.
From automating research tasks used in University of Cambridge to deploying agents in real-world production environments, this workshop equips you with the skills to harness agentic AI for rapid prototyping, research and business use cases.By the end of the session, you’ll understand the core principles of agentic systems, how to create and control AI agents, and how organizations like BetterFutureLabs use them for deep analysis, decision-making, and beyond.
Chris Alexiuk, Co-Founder & CTO | AI Makerspace and DL | NVIDIA
In this event, we’ll explore the latest on agent evaluation from the leading LLM application evaluation framework: RAG ASsessment (RAGAS).Join us live to learn about best practices for evaluating agentic workflows, including Topic Adherence, Tool call
Accuracy, and Agent Goal accuracy.
📚 You’ll learn:
- How to think about assessing your agent applications quantitatively, with leading best-practice metrics
- How agentic workflows are being assessed at the LLM edge
🤓 Who should attend the event:
- Aspiring AI Engineers who want to build and evaluate production-grade agent applications
- AI Engineering leaders who want to instrument their agent deployments with leading evaluators
Free with Any Paid ODSC West 2025 Conference Pass; Find more details on the Conference on https://odsc.com/california/
$2,500+ in credits to multiple AI platforms Full access to all 3 weeks of Training Live access to all sessions, workshops, and Q&A. On-demand replay of all sessions. Participation in community channels (Slack/Discord). Certification or digital badge upon completion.
Free access to Invited speaker sessions, Talks & Office hours. No access to Training or Hands-On Sessions & Recordings
Meet Our Speakers & Instructors
Week 1: Foundations of Agentic AI – Learn the building blocks of autonomous agents, including core architectures, planning methods, memory systems, and leading development frameworks.
Week 2: Advanced Techniques and Collaboration – Dive into advanced reasoning, multi-agent coordination, tool chaining, self-healing workflows, and emerging security challenges.
Week 3: Evaluation, Improvement, and Deployment – Focus on real-world applications with sessions on agent evaluation, reliability, deployment strategies, and cumulative demo showcases.
Learn step-by-step, guided by experts.
Interactive Workshops: Participate in live, expert-led sessions where you’ll build real agentic systems.
Cutting-Edge Tools:
Experiment with the latest agent frameworks, memory systems, and orchestration platforms.
Exclusive Builder Credits: Receive free credits from partners to immediately start building and scaling your own autonomous AI agents.
Dive into live, expert-led sessions where you’ll work on real-world AI challenges and learn by doing
Expert-Led Sessions
Learn directly from pioneers in autonomous agents, multi-agent coordination, and agentic workflows.
Real-World Insights:
Engage in live Q&A, hands-on demos, and hear from innovators behind today’s leading agent technologies.
From Research to Deployment: Understand both cutting-edge research and practical deployment strategies for agentic AI.
Immediate Impact: Build, Deploy & Scale AI Agents with Credits
✔ Deploy real autonomous agents with no upfront cost
✔ Access premium APIs, frameworks, and cloud tools
✔ Experiment, build, and test in real-world environments
✔ Compete in build challenges and mini-hackathons
✔ Start building with industry-grade platforms — immediately and for free
Featured Topics
Agent Architecture and Design
Foundations for building autonomous, capable AI agents.
Agent Types and Patterns
From ReAct and ToT to planning and reflex agents.
Agent Design Paradigms
Explore emerging design philosophies behind effective agentic systems.
Agentic Frameworks
Compare CrewAI, AutoGen, LangGraph, LangChain, and more.
Advanced Reasoning and Learning for Agents
Explore self-critique and other cutting edge techniques that allow agents to irmpove via reasoning
Agent Planning Techniques
Dive into CoT, LATS, and multi-step reasoning strategies.
Agent Memory Systems
From RAG to persistent long-term context.
Multi-Agent Collaboration
Strategies for building agent teams that coordinate and communicate.Featured Topics at the Agentic AI Summit
Error Handling in Agent WorkflowsFeatured Topics at the Agentic AI Summit
Agent Evaluation and Benchmarking
Methods and tools to measure performance, reliability, and safety.
Techniques to reduce hallucinations, recover from failure, and ensure robustness.
Autonomous Web Agents
Explore agents that navigate and interact with live websites.
Self-Healing Agents
Build agents that can detect, adapt, and recover from failures.
Agent Security
Address prompt injection, tool exploits, and inter-agent vulnerabilities.
Open vs. Closed Agent Ecosystems
Understand the trade-offs between proprietary and open agent platforms.
Tool Chaining and Composition
Equip agents to reliably sequence and execute complex tool workflows.Featured Topics at the Agentic AI Summit
We are accepting hands-on workhop submissions for a limited time. Alternatively, If you are interest in sponsorship please contact partners@odsc.com
Who Should Attend
✔ AI Engineer/ Developer
✔ Machine Learning Engineer
✔ Data Scientist
✔ Tech Lead Architect
✔ or any technical professional building AI-powered systems
✔ Startup Founder/ Product Leader
✔ Business Process Analyst
✔Executive / Non-Technical Founder
✔ AI Enthusiasts
✔ or any leader focused on driving business impact with intelligent automation
Partners
Media Partners
✔ Expanded Training: Over 40+ Hands-on Tutorials, Workshops, and training sessions
✔ Leading Experts: Taught by top instructors and experienced practitioners in AI and ML
✔ Breadth and depth: Beginner to Expert season ensures we have all levels covered
Discover a dynamic space where connections fuel innovation. The AI Builders Summit offers unparalleled networking opportunities with a global community of engineers, data scientists, and AI leaders. Engage in insightful conversations, exchange expertise, and collaborate with professionals who share your vision for advancing AI. This is more than networking—it’s your chance to join a thriving space of creators and problem-solvers driving the future of technology.
Sessions
Sessions
Sessions
Sessions