#harnessed.md
"The primary job is no longer to write code, but to design environments, specify intent, and build feedback loops that allow agents to do reliable work."
— OpenAI, Harness Engineering
A directory of companies who have gone all-in on harness engineering — building the environment, constraints, and feedback loops that let AI build the product.
##What is a harnessed company?
Traditionally engineers spent 80% of their time on features, 20% on the system. Harnessed companies flip that on its head: 80% goes to the harness — the machine that builds the machine. 20% guiding where it goes.
The harness has two parts:
- Guides (feedforward) — steer the agent before it acts: documentation, architectural rules, constraints, linters
- Sensors (feedback) — verify after it acts and self-correct: tests, CI, type checks, structural analysis
╭·····································╮
· failures become new guides ·
· ·
▼ ·
Guides (feedforward) ·
│ ·
│ constrain + direct ·
▼ ·
Agent builds ◄───────┐ ·
│ │ ·
▼ │ no ·
Sensors (feedback) ··╁··················╯
│ │
▼ │
Pass? ───────────────┘
│
yes
│
▼
Ship
The system gets better over time. Every sensor failure is a candidate for a new guide — you don't fix the code, you fix the harness so it never breaks that way again. That's what makes it engineering, not configuration.
##Key reading
- My AI Adoption Journey — Mitchell Hashimoto The origin of harness engineering
- Harness Engineering — Ryan Lopopolo / OpenAI 1M lines of code, zero written by humans
- Harness Engineering for Coding Agent Users — Birgitta Böckeler / ThoughtWorks The guides and sensors framework
- Compound Engineering — Dan Shipper, Kieran Klaassen / Every How Every codes with agents