Governance

Keep control without keeping AI out.

Full autonomy where you allow it. None where you don’t. Decided per command, at the moment the command acts — on the exact application, process and window it is about to touch.

What we govern

Everyone governs the data the AI reads. We govern the actions it takes.

Identity tells you who the agent is. A sandbox tells you where it runs. Approval tells you when it may. None of them tells you what it is about to touch. InvokeFlow checks that — every command, at the target, as it resolves right then.

Five controls, on every command

Control at the moment it matters.

Control you already trust

Your cloud already works this way. Your desktop didn’t.

A cloud key that opens one bucket, not the account. A sandboxed app that gets the file the user picked, not the filesystem. Data-loss controls that govern the channel. Authority bound to the action is how enterprises already stay in control — everywhere except the desktop, where the work actually happens.

Now it does.

The execution of record

Every company has a system of record. Almost none has an execution of record.

Tamper-evident, hash-chained, and ready to hand to an auditor. Every command, every refusal and every policy change, from humans, automations, and AI agents alike, in one chain.

#ActorApplicationCommandAuthorityResult may go toEvidenceOutcome
4181automationCRM (desktop)Record.Opentaught run · per-commandsame applicationread-back checkran · verified
4182automationDialerNumber.Loadtaught run · per-commandsame applicationnative responseran
4183agentSheetRange.Readgrant-2f9a · per-commandsame application—ran · text, 14 chars
4184agentEmailMessage.Draftgrant-2f9a · per-commandsame application—ran
4185agentEmailMessage.Sendgrant-2f9a · destructiveexternal—refused · not named for this run
4186humanEmailMessage.Sendseat · human in seatexternalnative responseran
4187admin—Policy.Changeconsole——recorded

No titles. No text. No URLs. A read’s result never enters the chain — a type-and-size descriptor stands in for it. Destructive steps are skipped unless a human names each one, every run: the agent’s send was refused, and the human’s ran. There is no “approve all.”

Local-first, cloud-optional

Your machines. Your record.

Your machines

The runtime and the broker run in your environment. Nothing leaves the endpoint unless you send it.

Your record

The chain lives with you. It is evidence you own, not a report you request.

Designed for the failure modes

Built for the ways AI agents go wrong.

Overreaching. Taking access they weren’t given. Acting on a window that changed underneath them. The runtime treats each one as a refusal on the record, not an incident to investigate — and the way it checks authority is patent-pending.

Start here

Start with the application you’ve never let an agent touch.

It runs governed from the first command, with every refusal on the record — and the record is yours to hand to whoever asks.