Harness Engineering

Harness Engineering

Harness engineering is the practice of making a codebase, toolchain, and team process legible enough that coding agents can work, verify, review, and hand off changes with less human babysitting.

Key points

  • OpenAI frames the move from autocomplete and pair programming into agent delegation as requiring a better "harness" around the model, not only a better model [src-084].
  • The API & Codex Build Hour demo builds an "agent legibility score" for repositories, with criteria such as bootstrap self-sufficiency, task entry points, validation harnesses, linting, formatting, documentation, and modular boundaries [src-084].
  • Worktrees are part of the harness because they let multiple agent tasks run in parallel on separate branches without clobbering each other [src-084].
  • High-quality validation is central: tests, lint, build commands, browser checks, logs, and other acceptance signals let Codex decide whether the work is actually done [src-084].
  • Skills and subagents encode repeatable team standards, such as PR creation, commit style, code review, architecture review, standards enforcement, and pull-request follow-up [src-084].
  • Team knowledge should move from individual heads and chat history into version-controlled files, docs, specs, skills, notes, and local decision records so every agent benefits from the same context [src-084].
  • The source also adds a company-context version: an "Atlas" style repo for operating principles, strategy, and non-code context can make Codex useful beyond production code [src-084].
  • [src-094] defines the harness as the surrounding machinery that turns a raw model into a working agent: prompts, tools, context policies, hooks, sandboxes, sub-agents, orchestration, observability, and constraints.
  • The paper warns against treating the model as the whole system; agent behaviour is heavily shaped by the harness around the model, not only by model capability [src-094].
  • In the AI-assisted SDLC, the harness is configured during requirements, planning, and architecture; run during implementation; improved through testing and QA; and observed during review, deployment, and maintenance [src-094].
  • GitHub's worktree guide gives the low-level filesystem pattern for safe parallel coding work: separate working directories let humans and agents work on different branches without stashing or disturbing editor state [src-098].
  • Google's ADK guide gives the long-running workflow pattern for production agents: persistent sessions, state machines, event-driven dormancy, and multi-agent delegation are part of the harness, not optional polish [src-101].
  • [src-191] adds fresh World's Fair evidence for harness-over-model thinking: liveness models, save buttons, multi-machine fleets, physical-data harnesses, process discipline, and adaptive engineering all become part of what makes an agent reliable.
  • The playlist also connects harness engineering to UX and review: a good harness should produce receipts, make "done" inspectable, and reduce the hidden review debt created by coding agents [src-191].

Related entities

Related concepts

Source references

  • [src-084] OpenAI Codex, Workspace Agents, Prompt Caching, and Superintelligence Policy cluster (2026-02-09 to 2026-05-08)
  • [src-094] Addy Osmani, Shubham Saboo, Sokratis Kartakis – "The New SDLC With Vibe Coding" (2026-05)
  • [src-098] Cassidy Williams – "What are git worktrees, and why should I use them?" (2026-06-16)
  • [src-101] Shubham Saboo and Eric Dong – "Build Long-running AI agents that pause, resume, and never lose context with ADK" (2026-05-12)
  • [src-191] AI Engineer World's Fair Online Track 2026 playlist update (47 new transcript captures, 2026-06-22 to 2026-07-02)

Robin Cartier perspective

This page is part of Robin Cartier's working AI knowledge graph: a practical research layer for production AI, recommendation systems, experimentation, GEO, and agentic web readiness.

The useful next step is to connect this concept back to applied product leadership and operating models.

Recommended next

Keep reading from this thread

From 491 indexed pages and articles.

  1. Wiki concept GPT-5.4 An OpenAI reasoning model presented in the API & Codex Build Hour as a token-efficient coding and agent model with native computer-use capabilities Related by 084
  2. Wiki concept Software Factory Model The software factory model is the idea that, in mature AI-assisted development, the developer's main output becomes the system that produces code: specifications Related by harness
  3. Insight AI Beyond POCs How enterprise AI moves beyond proofs of concept through ownership, governance, measurement, adoption, and production operating models Readers have engaged with this next