Company Brain

the problem

Your company’s knowledge lives in people’s heads, chat threads and old documents. Every new hire and every AI tool you try starts from zero.

A team knowledge base your agents can read and write, installed with boot, handoffs and guards.

We map how your team currently keeps and shares knowledge.
We install a shared knowledge base your agents can read and write to.
We install a boot protocol, so any agent starting work loads the right context automatically.
We install a handoff format, so context carries between agents and between sessions.
We install guards: a claim guard, so two agents can never edit the same file at once, and a red-first check, so a safety rule is proven against a real failure before it ships.

Fixed-scope install, priced and scheduled in writing before work starts.

Everything below is live and checkable. Our own company runs on it.

agent.leematulis.com — live, with a signed Web Bot Auth key directory and a transparency page documenting how our agents behave.
Every request is signed with HTTP Message Signatures (Web Bot Auth); the public keys are published at /.well-known/http-message-signatures-directory.
Our own agents made 1,518 web fetches between 25 August and 24 September 2026 — 11.7% were blocked.

Red-first: A safety check counts as installed only after we have seen it fail on the exact problem it exists to catch.
Claim guard: Two agents can never edit the same file at once; each claims its files before writing, and the system refuses a write against someone else’s claim.
Safety guard: Destructive commands are blocked by the system itself, not by an instruction the agent could forget.
Truth guard: Any live number on a page is computed from its source, never typed by hand.

from €10,000 — Floor for the smallest team; larger installs quoted after the Audit.