Diana Todea, Head of Developer Relations at VictoriaMetrics, demonstrates how Model-Controller-Pair (MCP) servers enhance observability stacks for faster, smarter troubleshooting. She highlights the use of AI-driven anomaly detection, natural language querying, and customizable "skills" to investigate production issues, manage metrics, and generate alerts, showcasing practical applications with two interconnected MCP servers.
Discover how top-performing teams achieve 100-150% productivity gains with AI by strategically restructuring workflows, automating wisely, prioritizing design, fostering deep work, reducing cognitive load, investing in growth, and optimizing tools. This goes beyond mere AI adoption, focusing on human-centric practices and intelligent measurement to drive real impact and retention.
AI has shifted the software development bottleneck from coding to defining *what* to build. This talk emphasizes the critical role of human skills in eliciting true requirements and understanding business value, detailing practical tools like story mapping, a 4-question value framework, and the VAD thinking path to ensure valuable AI-driven solutions are built, focusing on impact over mere feature delivery.
Kent Beck introduces the 'Forest vs. Desert' metaphor to describe two parallel universes of software development. He contrasts the 'Forest' mindset, based on abundance, trust, and collaboration (akin to Extreme Programming), with the 'Desert' mindset, rooted in scarcity, control, and pressure. Beck argues that while the Desert is internally consistent and can be profitable, it settles for 'crumbs', whereas the Forest aims to realize the full potential value of software—the 'whole cake'.
KREA.ai's cofounder Diego Rodriguez discusses the critical failure of current AI evaluation metrics in understanding human perception and aesthetics, advocating for a new paradigm of personalized, perceptually-aware evals.