Sample path

See AI SDR and outbound agent vendors governed

One consequential action ai sdr and outbound agent vendors can take, governed end to end. Read the sample verdict path below, then open the same flow in the live compiler.

Open the live compiler

The scenario

One action, from proposal to receipt.

The agent proposes a consequential action. HELM checks it against policy before the effect runs, returns a verdict, and binds a signed receipt.

Agent proposes

Agent drafts an outbound email making a pricing commitment

HELM checks policy

Checks the message against commitment and contact policy

Verdict

ESCALATE

Proof

Message receipt + outbound-policy EvidencePack

What you get

The evidence the run leaves behind.

Each governed action produces records you can keep and verify later.

  • Message receipt
  • Outbound-policy EvidencePack
  • Security-review sample

Verify it yourself

Proof that does not depend on us.

The receipt and EvidencePack from this run are content-addressed and signed. Anyone can verify them offline, without a dashboard or an account. The same check works on the action you bring to the risk test.

Questions

About this demo.

Is this a real verdict?

It is the same decision shape HELM returns in the action path: ALLOW, DENY, or ESCALATE, with a receipt bound to the verdict. The demo walks one scenario so you can read the flow end to end.

Can I run it on my own action?

Yes. The risk test takes one of your own actions and shows you the verdict and the receipt for it, instead of the sample below.

Do I need a dashboard to check the result?

No. The receipt and EvidencePack verify offline, outside any dashboard or account.

Keep reading

Follow the proof path.

Security review The boundary and the proof a reviewer asks for. Receipts vs logs Why a log is not proof an action was authorized. EvidencePacks Signed, offline-verifiable proof of what happened.

Terms

Plain-language terms

EvidencePack

A small bundle of records used to verify one event or review path.

Use for replayable evidence slices.
ProofGraph

A record chain that helps replay and check what happened.

Use for HELM proof records and replay paths.
ALLOW

HELM lets the action run.

Use as a canonical verdict.
DENY

HELM blocks the action.

Use as a canonical verdict.
ESCALATE

HELM stops and asks for more facts, policy, or human approval.

Use as the canonical non-dispatch path for missing facts, policy hold, or approval.

See the verdict on your own action.

The demo shows one path. The risk test shows yours.

Run the execution risk test Request a proof pack