The governance doctrine
Promotion, not deployment.
Agents are not pushed to production. They are promoted through a governed gate a human owns — so every capability in the mesh is one someone chose to stand behind. That is the difference between a demo and a system you can run a business on.
The gate is human.
Every agent release passes a human approval gate. Not a policy file, not a threshold — a named person who reviews the release and chooses to stand behind it. Accountability that can say no.
The trail is complete.
A full audit trail across every action. Builds, approvals, promotions, calls — recorded and attributable. When an auditor asks what happened, the answer is a query, not a reconstruction.
The boundary is the database.
Tenant isolation is enforced in the database, not the UI. A boundary that lives in the interface is a suggestion; a boundary the data layer refuses to cross is a guarantee.
Production is one-way.
A one-way promotion from build to production — immutable and attributable. What was approved is exactly what runs; nothing edits production in place. Rolling back means promoting the previous approved release, never editing the live one.
Capabilities are promoted too.
The same gate governs models. In Cognition Factory, a cognition earns its place in the mesh by passing the Model Breach — checksum, license, provenance, a real load probe. Cognitions are promoted, not shipped.
one cognition → a live node
Credit is governance.
We credit our tools by name — human, AI, and open source alike — because a company that hides how it works is a company asking you to trust it blind. How this was built →
For domain experts who are accountable for what their software does — build an agent your auditors would approve.