Tokenless

Harness engineering

Reading Group July 2026 - Loop Engineering

Reading Group July 2026 - Loop Engineering

This session provides an in-depth exploration of Loop Engineering, a paradigm shift from manual AI prompting to designing autonomous systems that orchestrate AI agents. Speakers share practical experiences, from building production-grade platforms with automated code generation and adversarial AI reviews to experimental loop structures and foundational infrastructure layers. Key discussions address challenges like managing token costs, preventing agent chaos, and implementing robust verification mechanisms for industrializing software development.

Agents, codebases, and teams — Aditya Khandelwal, Amazon AGI Lab

Agents, codebases, and teams — Aditya Khandelwal, Amazon AGI Lab

Aditya Khandelwal argues that scaling AI agent adoption within engineering teams is a leadership challenge, not an individual contributor problem. He highlights common pitfalls like agent "babysitting" and "slop," and provides a playbook emphasizing progressive disclosure, high-value automation, robust feedback loops, and a critical mindset shift to successfully integrate agents into team workflows.

Extreme Harness Engineering for the 1B token/day Dark Factory — Ryan Lopopolo, OpenAI Frontier

Extreme Harness Engineering for the 1B token/day Dark Factory — Ryan Lopopolo, OpenAI Frontier

Ryan Lopopolo of OpenAI's Frontier team discusses "Harness Engineering," a new paradigm where AI agents manage the entire software development lifecycle. He details an experiment building a 1M LOC product with zero human-written code, shifting the engineer's role from coding to designing systems and context for agents. The conversation covers the Symphony orchestration framework, the concept of "agent-legible" software, and the future of AI-driven development.

Build Hour: API & Codex

Build Hour: API & Codex

A deep dive into building agent-powered engineering workflows with Codex and OpenAI APIs, covering the shift from pair programming to agentic delegation, the principles of 'Harness Engineering' to make agents reliable, and practical examples from OpenAI and Basis.