— governance & trust

Autonomy,
under control.

An AI that acts on its own must stay controllable. Governance isn't an add-on — it's native, at every tool call.

— lock manager

Locking sensitive actions

Governance comes down to a switch. In supervised mode, every tool you flagged "require my approval" — typically an email send, a publication, a financial action — is intercepted before it runs and waits for your go-ahead. In autonomous mode, the assistant acts on its own and everything stays logged. Nothing is hard-coded: you decide, tool by tool.

mode behavior for whom
Supervised Only the tools you flagged "require my approval" are intercepted → proposal. All others pass. Cautious rollout — sensitive actions under control.
Autonomous The assistant acts on its own — everything is allowed, and everything is logged in the audit. Trust established — maximum speed.
Per-tool switch Each tool carries its own "require my approval" switch: you pick exactly what needs your go-ahead. Fine-grained control, tool by tool.

extensible system — each tool, native or added, can declare its own locked actions. The Lock Manager is an open protocol, not a fixed list: the control surface adapts as the ecosystem grows.

— human in the loop

Proposals: actions requiring approval await your decision

A locked action isn't executed: it becomes a proposal you approve, reject, or defer from a console. Once approved, the action is replayed exactly as captured.

locked action proposal approved → executed · rejected · deferred
pending proposals are surfaced back to the assistant, so it accounts for them
Tool call by an agent
Autonomous mode, or unflagged toolimmediate execution, logged
Supervised mode · tool flagged "approval"interception
↓ a locked action isn't executed — it becomes a proposal
Proposal — human decision (console)
approved → executedreplayed verbatim, with explicit override
rejected
deferred
↓ every outcome is recorded
Audit log — append-onlyallowed · refused · validated · executed — who, what, when
Lock Manager — arbitrating a sensitive action · proposal states: pending → approved → executed / failed · rejected · deferred
— traceability & cost
append-only audit

Who did what, when

Every decision — allowed, refused, validated — is written append-only. The audit trail enterprises need.

token quota

Capped costs

A ceiling per instance. Top-ups require an explicit approval — no billing runaway.

emergency switch

Freeze it all, instantly

A single control pauses every autonomous task on the instance. Everything can be disabled instantly.

tunable modes

Supervised or autonomous

Switch between supervised and autonomous, globally or per profile. Supervised: only the tools you tick go through approval; autonomous: everything is allowed but logged.

— profile isolation

Partitioned where it matters, shared where it helps

A single instance can host several "personalities" — a main assistant, a monitoring agent — each with its own private memory, contacts, tools and channels.

A profile's private memory is never read by another without an explicitly configured share. Two spaces, however, are common by design: the document cabinet (reference sheets) and the company directory — so the assistant and the autonomous agents draw on the same files and contacts. The strongest isolation is between instances: each client has its own — separate containers, database and volumes.

— access

A use case in mind?

Tell us your use case — individual reply within 48h.