Master the full stack of agentic AI.
Workshops take place on the afternoon of Day 2, March 31, starting at 1:00 PM. Go beyond theory with deep-dive sessions led by industry pioneers from NVIDIA, AWS, Google, Redis, and more.
Mastering Agentic Coding & GPUs
A hands-on workshop focused on building, deploying, and scaling production-ready agentic systems. Learn how to structure agentic coding workflows, ensure reliability and safety, and effectively use GPUs and Kubernetes to run agent-driven workloads from experimentation through production.
Multi-Agent Architecture using Google ADK
Build collaborative multi-agent systems using Google's Agent-to-Agent (A2A) protocol, MCP, and the Google Agent Development Kit (ADK). See how agents communicate, share context and tools, and coordinate tasks on complex problems.
Optimizing Retrieval for Agentic Systems
Core techniques and design patterns behind modern AI-powered retrieval. Since RAG quality is driven largely by retrieval, we focus on how to design and optimize retrieval for agentic systems. That includes agentic search, where agents coordinate retrieval through tool calls and relevance feedback loops.
Optimizing LLM Training & Inference on GPUs
How to optimize GPU performance and reduce operational costs when training and serving large language models. Practical strategies for high-throughput training and low-latency inference, including modern parallelism techniques and disaggregated serving architectures used in production-scale LLM systems.
Building an AI-Native Career
How agentic CLI tools go beyond coding, how 'vibe insights' reduce the distance between data and action, and how ephemeral software helps you solve niche problems quickly. Learn to see the world through 'software vision' and develop the mindset to stay productive in an AI-driven era.
Context Engineering with Redis & LangChain
Master the discipline of structuring memory, retrieval, and reasoning workflows so LLMs behave reliably in production. How Redis and LangChain enable high-performance agent systems through semantic caching, vector search, and intelligent context management.
OpenClaw: How to Actually Use It
The first wave of AI gave us chatbots. Now we have agents that act: managing email, triaging GitHub issues, monitoring systems. Most teams get stuck managing infrastructure. This workshop shows you how to deploy and run a fully-managed OpenClaw agent with KiloClaw, so you can focus on what your agent should actually do.
Trustworthy Agentic AI
Agentic systems are moving from experimentation to production: autonomously browsing the web, executing code, and calling APIs. Their autonomy and probabilistic reasoning introduce new risks. Explore prompt injection, API abuse, data leakage, and the governance, guardrails, and observability needed to deploy safely.
Production-Ready Agentic AI Systems
Build AI agents for real-world apps using the Strands SDK. Strands simplifies agent development by leveraging state-of-the-art models to plan, chain thoughts, and call tools. Hands-on experience creating agents across diverse use cases.