Agent architecture

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.

Aug 10, 2026

Codex, Behind the Harness — Dominik Kundel, OpenAI

Once GPT 5.3 Codex Spark achieved 1000 tokens/sec on Cerebras, network latency superseded inference as the bottleneck for agents. This talk details how the Codex harness addresses this and other agentic challenges through innovations like WebSocket mode for stateful context, deferred tools for efficient context construction, robust sandboxing (Seatbelt, Bubblewrap, custom Windows solution), and an auto-review subagent to mitigate approval fatigue while ensuring security. It also covers structured actions via 'apply patch' for file edits, shell tools for system interaction, and sophisticated long-horizon goal management, with most distinct features exposed through the open Responses API.

Jul 22, 2026

Claude for Long-Horizon Tasks — Lance Martin, Anthropic

Lance Martin from Anthropic shares insights into building reliable and secure long-horizon agents with Claude. He details architectural principles like decoupling the 'brain' from the 'hands' for reliability and security, implementing independent verifiers for self-correction, and developing advanced self-learning memory systems akin to human memory's in-band writing and offline 'dreaming' consolidation. The talk concludes with a vision for evolving agent harnesses towards organizational-level, proactive, and multiplayer capabilities.

Jul 11, 2026

Develop at Idea Velocity - Jeffrey Lee-Chan, Snapchat

Jeffrey Lee-Chan argues that the critical component for production AI agent systems is not the model but the "harness"—an orchestration layer providing persistent memory and contextual guardrails. He introduces Open Claw, a conceptual framework that separates agent orchestrator managers (handling task specs and history) from specialized workers (executing implementation details). This architecture enables deterministic teamwork, parallelization, and unbiased outcomes, supported by examples like AI RPGs and multi-AI analysis, alongside tools like tmux for enhanced developer productivity and careful token management strategies.

May 14, 2026

Make your own event-sourced agent harness using stream processors — Jonas Templestein, Iterate

Jonas Huckestein introduces a novel, event-sourced architecture for building AI agents. The core abstraction consists of three parts: a state, a synchronous reducer that derives state from events, and an after-append hook for side effects. This design ensures debuggability and allows state to be rebuilt without re-running expensive operations like LLM calls. A key innovation is the ability to deploy an agent by simply appending a 'dynamic worker configured' event—containing JavaScript code for a processor—to an event stream, eliminating the need for servers or complex deployment pipelines. This enables a distributed and composable ecosystem where processors from different authors can collaborate on a single stream.

May 11, 2026

A Piece of Pi: Embedding The OpenClaw Coding Agent In Your Product — Matthias Luebken, Tavon

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.