A reference for evaluating whether a spec document is comprehensive enough for AI agents to implement from in a loop, without requiring human clarification.
Agent-readable specs describe behavior in prose. An agent can understand them but will fill gaps with assumptions, producing divergent implementations.
| { | |
| "basics": { | |
| "name": "Mitchell Jones", | |
| "label": "Software Arhitect / Technical Lead", | |
| "summary": "I’m a full stack web developer who can build apps from the ground up. I've worked mostly at startups so I am use to wearing many hats. I am a very product focussed developer who priotizes user feedback first and foremost. I'm generally very flexible when investigating new roles. ", | |
| "email": "mitchellcjones@protonmail.com", | |
| "location": { | |
| "city": "San Francisco", | |
| "countryCode": "CA" | |
| }, |
I hereby claim:
To claim this, I am signing this object: