Dexter Horthy of HumanLayer critiques the initial Research-Plan-Implement (RPI) framework for AI coding agents, revealing its tendency to encourage 'outsourcing thinking'. He introduces CRISPR, a new structured methodology that emphasizes smaller, focused prompts, human-agent alignment through artifacts like Design Discussions, and engineer ownership to combat 'slop' and improve code quality in complex projects.
Simba Khadder of Redis introduces Context Engineering 2.0, a new paradigm for AI agents that unifies structured data, unstructured data (RAG), and memory into a single, schema-driven surface. He critiques current methods like Text-to-SQL and direct API wrapping, proposing a unified context engine to provide reliable, observable, and performant data access for agents.
This talk explores the challenges of using multi-agent systems for mass personalization, highlighting the inconsistencies and inaccuracies that arise from traditional methods like RAG and function calling. The speaker introduces Cortex UCM, a unified customer memory system that proactively infers and standardizes customer insights. This shared, structured memory layer enables agents to achieve a deep, consistent understanding of customers, leading to high-quality, scalable generative personalization for emails, websites, and product pages.
Harrison Chase, co-founder of LangChain, explains the evolution of AI agents from early, rigid scaffolding to modern, flexible "harnesses." He argues that "context engineering"—managing what an LLM sees—is the key to building effective long-horizon agents. Chase also explores how agent development differs from traditional software, highlighting the critical role of traces as the new source of truth and memory systems that enable agents to improve themselves over time.
Panos Stravopodis, CTO of Elyos AI, shares the infrastructure and orchestration challenges of building production-ready voice AI agents. He details the four pillars for success—latency, consistency, context, and recovery—and provides engineering patterns for error handling, context management, and achieving conversational coherence in real-time systems.
In an era of the "Infinite Software Crisis" where AI-generated code outpaces human understanding, this talk argues for choosing "simple" design over "easy" generation. The speaker presents a three-phase methodology—Research, Planning, and Implementation—that forces developers to think critically before generating code. This approach leverages AI for mechanical tasks while ensuring that human judgment, context, and a deep understanding of the system remain the core of the software development process, turning human insight into the ultimate competitive advantage.