Tag
The article argues that AI harnesses serve two distinct purposes—providing context about what the user wants (intent) and instructions on how to achieve it (execution)—and that these age differently: execution instructions become less valuable as models improve, while intent context becomes more valuable.
This tweet argues that Spec-Driven Development is ineffective for AI agents, drawing parallels to the failure of waterfall methodology in software development. It advocates for 'intent engineering'—communicating context, strategy, and constraints to agents to handle unknown unknowns.