Aug 15, 2026

Exo: Harnesses should see their own code and logs — Alex Krentsel

An introduction to Exo, a fully recursive AI agent harnessing a novel three-layer architecture (Executor, Harness, Sandbox) designed for autonomous self-improvement. It delves into how Exo surpasses current agent limitations by allowing the agent to edit its own code and policy at runtime, ensuring protected state and isolated execution, and discusses practical implications and the underlying systems philosophy enabling this paradigm shift.

Jul 28, 2026

How Forward Deployed Engineering is done at Cognition — Jia Wu

Cognition's deployed engineering team focuses on measuring customer outcomes, not just token usage, achieving significant productivity gains with their AI agent, Devin. This involves understanding deep business problems, strategically applying Devin's capabilities, and feeding insights back to product development, fundamentally reshaping the role of a deployed engineer.

May 01, 2026

Running AI Engineer with AI — swyx

Swyx, co-founder of the AI Engineer conference, reveals how his "tiny team" of nine people leverages AI agents like Cognition's Devin and Town Assistant to manage a multi-million dollar business and organize large-scale events. He shares practical examples of how agents have transformed their workflow, from converting Figma designs to pixel-perfect websites to managing complex conference schedules and even performing personal research tasks, arguing for a future focused on "Agent Experience" (AX).

Nov 10, 2025

Build Hour: Agent RFT

Will Hang and Theophile Sautory from OpenAI provide a deep dive into Agent RFT, a powerful method for fine-tuning large language models to become more effective, tool-using agents. They explain how Agent RFT enables models to learn directly from their interactions with custom tools and reward signals, leading to significant improvements in performance, latency, and efficiency on specialized tasks. The session includes a detailed code demo, best practices, and success stories from companies like Cognition, Ambience, and Rogo.

Jul 25, 2025

Devin 2.0 and the Future of SWE - Scott Wu, Cognition

Scott Wu, CEO of Cognition AI, discusses the exponential growth of AI capabilities in software engineering, likening it to a "Moore's Law for AI agents" with a doubling time of every 70 days. He chronicles the evolution of their AI agent, Devin, from handling repetitive code migrations to autonomously managing entire backlogs, highlighting the key technical challenges and paradigm shifts at each stage.