Samuel Colvin, creator of Pydantic, demonstrates a hands-on workflow for continuously optimizing AI agents in production. The session covers using Logfire for running evaluations, GEPA (Genetic Pareto) for autonomously evolving better prompts, and managed variables to deploy these improvements to live services without redeployment.
A practical guide on improving LLM coding agent performance by giving them direct access to a library's source code. The session demonstrates cloning the Effect repository to extract patterns and guide the agent in building a type-safe application from scratch.
Nick Nisi and Zach Proser from WorkOS explain how to build, manage, and scale AI 'skills'—reusable, portable instructions that make AI agents like Claude more powerful and consistent. They cover the core anatomy of a skill, best practices for writing them, advanced techniques like progressive disclosure, and their application beyond coding, from video generation to automating business workflows.
Jesse Vincent, creator of the Claude plugin Superpowers, explains his methodology for agentic software development. He details a system of spec-driven development using brainstorming, planning, and execution skills that turn developers into managers of AI agents, emphasizing the importance of explaining the 'why' to LLMs and pressure-testing skills to prevent rationalization.
Liam McGarrigle demonstrates how to build secure, observable, and controllable AI agents in n8n. The workshop covers creating a human-in-the-loop workflow for managing Gmail and Google Calendar, focusing on n8n's visual system for tool configuration, prompting strategies, and implementing essential approval steps to prevent unintended actions.
Danilo Campos of PostHog details the common failure modes of LLM-based code generation—from model rot to security risks—and shares the practical, prose-driven strategies his team uses to make their autonomous coding agent reliable for thousands of users.