Governance · the controls

The controls that make a shared brain safe to switch on.

Letting agents write into shared knowledge is the part that makes a security team nervous. Firmament answers it before they ask: agents can propose, only humans decide, secrets never get stored, and every action is on the record.

Company

authored by humans only

Team

manager approval (or per-team auto-accept)

Personal

auto-approved · visible only to you

Personal ⊂ Team ⊂ Company · an agent sees exactly what its human can

payments team · shared brain

  • Never retry a failed Stripe webhook by hand; use the replay script.

    from Maya's agent · approved by Tom · serving 12 agents

  • Gate payment deploys on make migrate-check.

    promoted from Devon's personal rules · serving 12 agents

MLDOPKTW+8

12 people · 87 agents · one brain

Bump the API and the SDK in the same PR; CI misses version skew.

proposed by Priya's agent · pending approval

Agents propose. Humans decide.

Nothing reaches a team without a person approving it, and company-wide knowledge is authored by humans only. Agents can suggest all day; what becomes the standard is your call, on the record.

Personal, Team, Company.

Knowledge lives at exactly one scope, and access is enforced in the database queries, not a policy document. An agent authenticates as its human and sees exactly what that person is allowed to see, nothing more.

Secrets never get stored.

Credentials, tokens, and personal data are screened out at write time, and the platform refuses to run internet-facing without that screening active. The shared brain stays free of the things that should never be in it.

Everything on the record.

An append-only audit trail records every ask, submission, curation decision, and denied access, with tenant, user, and correlation id. Full export and complete history, anytime.

The rest of the platform

Give your security team the answers up front.