Jose Hernan Ortiz Ocampo

LangGraph and Strands Agents: Core Concepts, Patterns, and Tradeoffs

The agent framework landscape has consolidated fast. Among the options available today, two stand out for their architectural depth and production relevance: LangGraph, with its graph-based, developer-controlled orchestration model; and Strands Agents, with its model-driven, minimal-scaffolding approach. They are not interchangeable — they represent different answers to the same fundamental question of how much control a developer should retain over agent behavior. This workshop is a structured, hands-on exploration of both. Participants will work through a shared codebase covering real scenarios: tool calling, state management, multi-turn reasoning, and multi-agent coordination. Each scenario is implemented in both frameworks side by side, making the architectural differences concrete and comparable rather than theoretical. The session is organized around three axes: core concepts (how each framework models state, tools, memory, and control flow), practical patterns (what each one makes easy, what it makes hard), and honest tradeoffs (where each framework earns its complexity and where it doesn't). No polished demos — just real code, real outputs, and an open discussion of what each approach costs and buys you. By the end, participants will have a working mental model for both frameworks, hands-on exposure to their key patterns, and enough grounded perspective to make an informed architectural decision on their next agentic project. Suitable for: Python developers with some familiarity with LLMs or agent concepts. Production experience is a plus but not required — the workshop is designed to reward depth of engagement, not prior framework knowledge.

Multi-Agent Teams in AI-Assisted Development: A Glimpse Into the Future of Programming

Programming has gone through a quiet but radical transformation in the last few years. We went from writing every line, to autocomplete, to AI proposing whole functions, to reviewing and steering AI-generated code. What comes next? Multi-agent systems, where you have a team of specialized agents working in parallel. This workshop is a hands-on, honest look at what that shift means today, and what it points to tomorrow. We'll start by mapping the current landscape together: what tools exist, how they approach multi-agent orchestration, what each one gets right, and where the real tradeoffs are. The goal isn't to pick a winner — it's to build a shared vocabulary and a realistic picture of the state of the art. From there, we'll move into live demos. Rather than polished showcases, these are honest explorations: what these systems can actually do today, where they break down, and what those breakdowns tell us about the deeper challenges in multi-agent coordination. Token costs, context limits, agent miscommunication, and the question of how much to trust your agents — these are real problems worth examining together. The talk closes with the bigger question: what does all of this mean for us as developers? What skills are becoming more important, which ones are becoming less so, and how do we stay relevant as the abstractions keep deepening? Not predictions, but a grounded reflection based on what's already visible in these early systems. The practical question isn’t whether this future is coming; it’s how to get ahead of it. Audience takeaways: A clear mental model for what multi-agent coding actually is (vs. single-agent tools and vs. orchestration frameworks) A working setup guide for multi agent works effectively Practical demos actually showcasing what to do with these tools A grounded perspective on what these experimental systems tell us about the next years of AI-assisted development and programming Suitable for: Python developers with some familiarity with AI tooling. No deep ML background required — this is a practical developer talk, not a research talk.