Madison Faulkner and Hugo Santos explain why traditional CI/CD, built for human developers, is failing under the load of AI agents. They propose a new paradigm of 'Continuous Compute' centered on intent-driven agent loops, fast inline validation, and a pre-merge layer where humans review outcomes, not diffs, paving the way for a 'multiverse' of parallel development.
Anton Arhipov from JetBrains introduces Koog, a lightweight, Kotlin-native framework for building tool-using LLM agents. This session covers the rationale for using Kotlin in AI, the architecture of Koog agents, and how its graph-based DSL enables the creation of structured, type-safe, and reproducible agent workflows, moving beyond simple prompt-chaining to sophisticated orchestration.
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.
The Arize team shares lessons from building their AI agent, Alyx, which analyzes its own trace data. They detail their journey from failed attempts like naive truncation and summarization to a successful strategy combining head/tail preservation with a retrievable memory store and using sub-agents to manage context complexity.
Grant Miller from IBM explains Agentic Consent, a dynamic framework for governing AI agents. The model moves beyond static permissions, using identity, context, and just-in-time user prompts to ensure AI agents act with, not instead of, their human counterparts, enabling trust and safety as autonomy scales.
Co-founders of Trigger.dev discuss their journey through three product versions to find product-market fit, how their async infrastructure positioned them perfectly for the AI agent era, and their vision for the future of computing: programmatic checkpoint and restore.