AI agents, powered by LLMs, excel at reasoning but lack the procedural knowledge required for real-world workflows. Martin Keen explains how the 'agent skills' open standard solves this by packaging step-by-step instructions, enabling agents to automate complex tasks efficiently and reliably.
Sunil Pai from Cloudflare introduces "Code Mode," a paradigm where AI agents generate and execute code (like JavaScript) instead of using traditional JSON-based tool calling. This approach enables more efficient, stateful, and complex interactions with large-scale systems by leveraging the inherent capabilities of programming languages.
Nikhyl Singhal, a seasoned product executive and founder, provides an unfiltered look at the massive transformation reshaping product management. He argues that the rise of AI is creating a chaotic but ultimately joyful renaissance for "builders" while rendering the traditional "information mover" PM obsolete. Singhal predicts that half of current PMs are at risk and outlines the new skills—judgment, pace, and an "obsolescence mindset"—required to thrive.
OpenAI research lead Joy Jiao and product lead Yunyun Wang detail the development of specialized AI models for the life sciences. They discuss the new biochemistry-focused model series designed to accelerate research in genomics and protein understanding, the critical challenge of managing biosecurity risks through a "differentiated access" model, and the future vision of AI-powered autonomous labs that could revolutionize drug discovery and personalized medicine.
Dhaval Nagar chronicles the evolution of cloud economics from hourly-billed virtual machines a decade ago to the current 'capability economy.' The talk is structured in three acts, detailing the journey from the initial launch of AWS Lambda, through the maturation of the serverless ecosystem with frameworks and new platforms, to the present day where complex capabilities like AI models are consumed as millisecond-metered APIs. This shift demands a new developer mindset focused on composing services, event-driven architecture, and eliminating infrastructure management.
This workshop by Mahmoud Mabrouk, CEO of Agenta AI, delves into building calibrated LLM-as-a-judge evaluations that reliably align with human judgment. It highlights how miscalibrated judges lead to false confidence and presents a practical workflow, including designing use-case specific metrics, detailed data annotation, and optimizing judge prompts using the GAPA algorithm. The talk emphasizes the importance of iterative debugging, model selection, and custom reflection templates for achieving trustworthy and effective LLM evaluations.