Agent failures are unlike traditional software failures. This workshop provides a practical framework for monitoring production agents, moving beyond evals to real-world observability by using explicit signals (errors, latency) and implicit signals (user frustration, refusals, self-diagnostics) to catch regressions and understand agent behavior.
This presentation by Janak Agarwal from AWS provides a deep dive into scaling serverless applications for mission-critical, high-traffic workloads. It explores AWS Lambda's rapid scaling capabilities for handling extreme traffic bursts and introduces advanced patterns like Provisioned Concurrency for cost optimization during steady-state operations.
Co-founders of Ricursive Intelligence, Anna Goldie and Azalia Mirhoseini, outline their thesis that AI should design the chips that train AI. They detail their three-phase plan to first accelerate chip design with AI tools 100,000x faster than current software, then become a 'design-less' platform for custom silicon, and finally achieve vertical integration by building their own chips and models.
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.
Naveen Rao, CEO of Unconventional AI, argues that the 80-year-old digital computing paradigm is hitting a fundamental energy wall. He proposes a new approach to AI hardware, inspired by neuroscience, that replaces matrix math with nonlinear dynamics, leveraging the time domain for computation to approach the thermodynamic limits of efficiency.
Explore the AI industry's "Y2K moment" in cybersecurity, as major players like OpenAI, Anthropic, and CrowdStrike form coalitions to tackle threats. This summary also delves into a new framework for AI agent identity based on Zero Trust principles and analyzes the "Copy Fail" Linux vulnerability, a decade-old flaw uncovered by AI, highlighting the escalating need for proactive vulnerability research.