Martin Fowler and Kent Beck, two authors of the Agile Manifesto, reunite for an unscripted conversation about their 30-year friendship and the evolution of software engineering. They delve into their practical, daily use of AI (the "Genie"), reflect on the legacy of Extreme Programming and the Agile Manifesto, and offer timeless advice to the next generation of developers.
95% of GenAI pilots fail due to feedback integration issues, not deployment challenges. Alessandro Cappelli argues that Reinforcement Learning (RL) provides the only systematic way to incorporate business metrics and production signals to continuously improve models, especially for complex agent-based systems.
Delivery Hero presents "Asya", an open-source framework that replaces traditional AI pipelines with a distributed, asynchronous actor model. This paradigm shift dramatically lowers GPU costs and improves scalability by treating each processing step as an independent, auto-scaling microservice on Kubernetes.
Rod Johnson explains the high failure rate of enterprise GenAI projects, attributing it to the misuse of the technology and a disconnect from established software engineering principles. He argues for a paradigm shift away from Python-centric approaches towards the JVM, introducing Embabel, a framework designed to build reliable, testable, and domain-integrated AI agents by tackling non-determinism and leveraging the strengths of the enterprise Java ecosystem.
In an interview with James Lewis, Martin Fowler recounts his journey into the Agile movement, starting from the object-oriented community to the pivotal Chrysler C3 project where Extreme Programming (XP) was born. He discusses the shift from upfront to evolutionary design, the creation of the Agile Manifesto, and offers modern perspectives on developer productivity, the role of GenAI in software analysis, and the enduring importance of XP's technical practices.
Lak Lakshmanan presents a robust architecture for building production-quality, framework-agnostic agentic systems. He advocates for using simple, composable GenAI patterns, off-the-shelf tools for governance, and a strong emphasis on a human-in-the-loop design to create continuously learning systems that avoid vendor lock-in.