Current AI agents are powerful but lack memory, context, and safety, behaving like "genius goldfish." This summary explains the necessity of an AI Agent Operating System (OS) to provide essential infrastructure for managing memory, tools, identity, and governance, making agents reliable, scalable, and trustworthy.
Matthias Luebken explains the core principle of building with coding agents: make things easy for them. This talk deconstructs the Pi SDK, showing how a simple loop of an LLM calling CLI tools can lead to emergent capabilities. Luebken presents a real-world B2B sales pipeline built on this principle, where agents handle incoming emails, query CRM/ERP data via simple tools, and generate draft responses, keeping the human in their familiar email client.
This talk explores the journey of building Viktor, an AI employee that lives entirely in Slack. It details the unique challenges of scaling an AI agent from a personal tool to a company-wide coworker, focusing on memory isolation, context management across different Slack interactions (DMs, channels, threads), and the surprising importance of the AI's personality for user adoption.
Brandon Hill, co-founder and CEO of Vori, discusses how his company is digitizing the $1.5 trillion grocery industry with an all-in-one OS. He covers their journey from a simple ordering app to a full-stack platform, the use of AI agents to automate pricing and inventory, and their vision for the 'self-driving' grocery store.
Marc Andreessen discusses the current state of AI, arguing that real-world usage and productivity gains tell a story of euphoria and empowerment, directly contradicting the fear-based narratives prevalent in media and misleading polls. He explores how AI is creating hyper-productive “builders” and expanding work rather than eliminating it, while also touching on the breakdown of institutional trust and the stark generational divides in how technology and truth are perceived.
Averi Kitsch, Staff Software Engineer at Google, outlines a four-step evolution for securing AI agents that access databases, moving from dangerous, model-controlled tools to a zero-trust architecture. Drawing on insights from over 20 million monthly tool calls, the talk provides a practical roadmap for preventing data leaks by separating identities, constraining actions, and removing credentials and PII from the agent's control.