Notes from the forge
Design tenets, milestone debriefs, and the occasional rant about why agents forget. New posts ship roughly when a milestone does.
- · m2 · mcp · architecture
The architect loop — and why foundry-ai never pays for an LLM call
M2 shipped the MCP server, the sentinel, and spec audits. The trick — and the design tenet that keeps foundry-ai self-hosted and free at the runtime — is that the "architect" lives inside your existing agent, not inside foundry-ai.
- · specs · m1 · architecture
Specs as a first-class unit of agent work
A spec is bounded, reviewable, and auditable. A vibe-coded change is none of those. The unlock of M1 was treating every agent intervention as a spec with a lifecycle the agent can drive but cannot bypass.
- · intro · memory · governance
Why foundry-ai exists
AI coding agents forget. They forget the master context. They forget the constraints you spent an hour explaining yesterday. foundry-ai is the layer that makes them remember — and that audits what they propose before it touches your repo.