Question 1

What problem does ArchSteer solve?

Accepted Answer

AI agents write code faster than any architect can review, document, or govern. Docs rot instantly, the real architecture is invisible, decisions are made silently, and intended architecture drifts. ArchSteer makes architecture continuously observable and governable.

Question 2

How is ArchSteer different from a linter or a diagram tool?

Accepted Answer

Linters check single-language rules; diagram tools require manual upkeep. ArchSteer maintains one code-derived model that powers living docs, auto-drafted ADRs, conformance with a net-new ratchet, an evolution feed, and AI-agent steering — all from the same source of truth.

Question 3

Do I have to set up rules before I get value?

Accepted Answer

No. The read-only X-ray runs with zero config: point it at any repo and instantly see the current architecture and how it changed. Declaring intent for governance is an incremental, opt-in upgrade.

Question 4

How does ArchSteer steer AI coding agents?

Accepted Answer

It injects sharp, file-scoped guardrails into CLAUDE.md / AGENTS.md / .cursor/rules that point at the governing ADR, so agents build toward the target architecture instead of copying adjacent legacy code.

Field notes