Free Consultation
Free to view · no account needed

How the Agent Control Plane actually works

Most AI governance platforms describe policy. This is the mechanism underneath it — authority, runtime control, intervention, evidence, and decision provenance — each stage backed by a real endpoint you can call yourself, not a diagram of something that only exists in a sales deck. Every "see it live" link below goes to the actual, working thing.

The flow

Five stages, one action

What happens, in order, every time an agent asks the Control Plane whether it may act.

01 · AUTHORITY

A key, not a claim

Every agent authenticates with its own registered key. Whatever identity the request claims is ignored — the key alone decides who's really acting, and it can't be spoofed from the request body.

Try it with a real key →
02 · RUNTIME CONTROL

Checked before it happens

The agent calls the Control Plane before the action executes and waits for allow / review / deny. It's a live policy engine consulted on every call, not a log line written after the fact.

Run a live evaluation →
03 · INTERVENTION

Held, not guessed

A review decision pauses the action until a person resolves it — approved, denied, or edited. A workspace-wide kill switch can halt everything instantly if you need a blunter stop.

Resolve a held action →
04 · EVIDENCE

Sealed, tamper-evident

Every decision — allow, review, or deny — is appended to a hash-chained ledger. Raw payloads are never stored, only a redacted copy. Edit one sealed record afterward and the chain breaks.

Verify the chain →
05 · DECISION PROVENANCE

Reconstructable, later

Every entry records which controls matched and why, and links to the entry before it. Months later, you can reconstruct exactly what happened and prove the record hasn't changed since.

See the recorded reasons →
Not a mockup

Live from the public demo ledger

This is real data from the same free, anonymous Workbench tool anyone can use — no account, no sales call. Run an action above and these numbers move.

Allowed
Review
Denied
Allowed
Review
Denied
Loading live ledger… Chain head
One request, start to finish

What actually happens on the wire

Agent calls POST /control-plane/evaluate

With Authorization: Bearer <its key> and what it wants to do — a tool, an action type, a target, an optional payload.

Server resolves identity from the key

Looks up which registered asset that key's hash belongs to. If the key is unrecognized, suspended, or revoked, the call is denied right here — before any policy runs.

Policy engine decides

Checks the workspace kill switch and every active compiled policy. Sensitive payload values are redacted before anything is stored.

Decision returned and sealed

The agent gets allow, review, or deny, plus the matched controls and reasons. The same response is appended to the hash chain, linked to the entry before it.

If held, a human resolves it

A review decision waits. Approving or denying it writes a new ledger entry referencing the original — the original held decision is never edited or deleted.

Anyone can verify the chain, any time

Re-walking every hash from the beginning proves nothing in it has been altered — the same check this page's live numbers above are drawn from.

What this page won't do: stage a fake attack for effect. The "try it" links above go to the real free product — the same one you'd actually integrate. If something described here stops being true, this page is wrong and should be fixed, not the other way around.

Go deeper

This page is the picture. The API reference, request/response shapes, and SDK snippets are one click away.