Run the check on your own action
Bring one consequential action and see its verdict and receipt.
Sample path
One consequential action agent infrastructure and tool-use platforms can take, governed end to end. Read the sample verdict path below, then open the same flow in the live compiler.
The scenario
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 invokes an unregistered MCP tool
HELM checks policy
Quarantines the unknown tool and checks the action
Verdict
DENY
Proof
Quarantine receipt + integration EvidencePack
What you get
Each governed action produces records you can keep and verify later.
Verify it yourself
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.
Bring one consequential action and see its verdict and receipt.
Questions
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.
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.
No. The receipt and EvidencePack verify offline, outside any dashboard or account.
Keep reading
Terms
A small bundle of records used to verify one event or review path.
Use for replayable evidence slices.A record chain that helps replay and check what happened.
Use for HELM proof records and replay paths.HELM lets the action run.
Use as a canonical verdict.HELM blocks the action.
Use as a canonical verdict.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.The demo shows one path. The risk test shows yours.