Intent Weaving for AI Coding Agents (autohand.ai)

Hey HN community, I’m Igor, co-founder of Autohand.ai in New Zealand.

We’re building an open stack that lets AI coding agents deliver work with the discipline senior engineers expect. Our latest write-up, “Intent Weaving for AI Coding Agents,” breaks down how we encode strategy, policy, and telemetry into machine-executable intent, plus an honest inventory of where current agents fail (reasoning, repo awareness, testing, etc.).

Highlights: - Mission compiler that turns business objectives into guardrail-rich plans for agents. - Knowledge graph + policy DSL so automation stays inside governance envelopes. - Pain-points matrix from real deployments; new benchmarks that punish regressions, not just pass unit tests. - Open-source pieces as we release them; Commander is already MIT-licensed.

We’d love feedback from folks shipping agentic workflows or wrestling with AI codegen drift. Where should we push harder? What failure modes have we missed?

Link to our manifesto: https://autohand.ai/manifesto

Thanks for reading, and be kind. Creating a new category means stretching before the skills are perfect.

Nice idea, I came up with a similar system. The idea is to map the "state space" of the agent, and describe a number of discrete states. Then assign a policy to each one. Both state space mapping and policy are generated by the agent after a discussion with the human. A chat driven, LLM based expert system, a problem specific bunch of "when in situation X, do Y".

Feel like we're revisiting heuristic planning and General Problem Solving by Simon, Shaw, and Newell.

My main worry about all these tools is that the model providers can just sit back and let you do your thing and fight it out with your competitors. Then, once a clear victor rises up, they can just copy your implementation and sell it at a fraction of your price because unlike you, they don't need to pay someone for access to a model.