If you're running coding agents at any scale, deterministic lint rules are a far more reliable steering mechanism than prompt-level instructions or CLAUDE.md conventions the agent may ignore; this post gives you the framing for turning tribal architectural knowledge into constraints an agent can't silently violate.
This Factory.ai blog post argues that as AI coding agents take over more of the actual code writing, linters should be used to encode architectural rules, boundaries, and style conventions as machine-verifiable constraints rather than relying on human code review or tribal knowledge.
It frames lint rules as a more reliable control mechanism for steering agent-generated code than traditional guardrails.
Transcript
Agents write the code; linters write the law. We’re moving from “developers writing code with AI” to “developers orchestrating agents that build software.” The old guardrails (code review, conventions, tribal memory) aren’t enough. Agents need clear rules they can concretely verify. They need lint rules, not suggestions.
