Open Protocol · v0.6

Give AI autonomy
without giving it authority.

A human sets what the automation may do — scope, limits, duration. Every consequential action is checked against that mandate before it runs, and produces a signed receipt proving the authorization existed first. Not a log written afterwards. A precondition.

Read the Protocol
See how it works

The core invariant

No receipt. No execution.

The receipt is not a post-execution log. It is the precondition for execution — and, afterwards, the verifiable proof that authorization existed before it ran. Agents request execution; they do not hold the keys.

Execution receipt signed · pre-execution
profileId
charge@0.4
actionType
refund
boundsHash
sha256:7a91… — the mandate this ran under
executionContext
order #4821 · €48.00
cumulativeState
€391 / €500 today — enforced by the Authority Server
subjects
did:key:z6Mk… — authorizing human, disclosed opt-in
timestamp
2026-05-23T14:22Z
signature
ed25519:8f3b…1b4c
  1. A human authorizes bounded execution — scope, limits, time, and commitment mode.
  2. The Gatekeeper verifies the attestation, checks per-action bounds, and enforces local context constraints.
  3. The Authority Server checks cumulative limits, expiry, and revocation, then signs the receipt.
  4. The Executor runs the action — only after the receipt exists.

Open infrastructure. Any compliant Authority Server can issue receipts — Suveren is one implementation. The protocol is open; no single vendor owns the trust layer.

One signed act

One receipt. Three jobs.

Most systems make you choose: a gate that blocks, or a log that explains. The same signed artifact does both, and a third thing neither can.

NowIt runs, or it doesn't.

Every consequential action is checked against the mandate before it happens. Not caught in a log afterwards. Prevented.

OutwardA stranger can check it.

Hand someone the receipt and they verify the signature and the content themselves — no account, no relationship with you. Cryptography, not testimony.

BackYou can answer for it.

Evidence created before the act, not reconstructed after: which mandate, which bounds, which content. What an auditor, an insurer, or a court asks for.

What holds today, and what comes next

Today the Authority Server signs that the human authorized it — the chain holds as far as you trust one operator's key. Next, the human's own key co-signs the mandate. Then it holds without trusting any operator, including us.

The same receipt does all three. That is what a signed artifact can do and a permission cannot.

Where it fits

HAP composes. It doesn't compete.

HAP isn't another login, API gateway, agent framework, sandbox, or policy engine. It's the layer that decides whether an already-reachable capability may be used for a consequential action — with proof.

LayerWhat it does
OAuth / OpenID ConnectGrants API access
Identity (EUDI, passkeys, WebAuthn)Proves who you are
MCPExposes tools to agents
Agent identity and lifecycle (e.g. Entra Agent ID)Governs which agents exist and what they may reach
Agent platforms and policy engines (e.g. Bedrock AgentCore)Run agents and evaluate configured rules per call
HAPAuthorizes the consequential execution — against a mandate a named human committed to, before it runs, with a signed receipt

Every other layer here answers can this system reach that? — an access question, and each answers it well. None of them holds a bounded mandate a named human committed to, and none produces an artifact a third party can verify for themselves. HAP adds that layer and replaces none of them: keep your identity provider, your agent platform, your policy engine, your sandbox and secrets manager. Point them at the agent path, and put the mandate above.

OAuth grants reachable capability. HAP governs authorized use of that capability.

Agent platforms decide what an agent may reach. HAP records what a human actually mandated — and proves this act was inside it.

Commitment modes

You decide how much runs on its own.

The level of autonomy is a signed choice on every authorization — the protocol's commitment mode, not a default the agent can change.

AutomaticAgent runs within bounds

The agent acts within the bounds you set. No per-action approval — the Authority Server enforces the limits and issues a signed receipt for each action before execution.

ReviewYou approve each action

The agent proposes; you approve each action before it runs. No approval, no receipt — no execution.

Review above a capApprovers sign above a limit

The agent runs on its own under a limit you set. Above it, the action routes to a named set of approvers before any receipt is issued.

The distinction

Agents aren't employees. They're executors.

Most systems give agents accounts, credentials, and standing permissions — turning them into authority-bearing actors. HAP does the opposite.

An agent never carries authority or raw credentials of its own. A human authorizes a bounded action; the receipt is cryptographic proof that this specific action was authorized — and issued before it ran. An agent may have technical identifiers for logging and routing, but it holds no independent authority.

As AI systems become more capable, HAP keeps authority from quietly moving from humans into machines.

The model choice

Two models for authorizing agents.

How a system treats agent authority is an architectural decision with long-term governance consequences.

Agent-identity approach HAP approach
Treat agents as authority-bearing actors Treat agents as executors
Manage standing agent permissions Issue bounded action receipts
Hand agents standing credentials Keep credentials behind the execution boundary
Audit after execution Verify the receipt before execution
Agent acts under standing authority Agent acts only inside receipt-approved bounds
Post-incident, the answer is “the agent was permitted” Post-incident, the answer is “this named person mandated this scope — here is the proof”

EU AI Act — Article 14

Article 14 requires effective human oversight of high-risk AI. HAP turns that oversight into an enforceable control at the action layer: consequential actions cannot run unless a human-linked authorization receipt exists before execution.

Wherever an organization must show a human stood behind an automated act — regulation, audit, insurance, or litigation — the receipt is the artifact.

HAP is Article-14-enabling infrastructure — not compliance on its own. Compliance still requires governance, training, documentation, and human competence.

For whom

Three readers, one artifact.

Engineering

Deploy agents on the infrastructure you already have. One enforcement point, no new stack, whichever model you run.

Compliance and audit

The same gate produces the evidence: who mandated it, what it covered, proven before it ran.

Legal and counterparties

Proof that survives leaving your organization — verifiable without trusting the operator.

Use cases

Where consequential actions need proof.

Paymentsrefunds, charges, payouts
Emailhigh-stakes sends
CRMrecord changes & deletes
Infrastructuredeploys & config
Multi-owner approvalstwo people must sign
Compliance auditverifiable receipts

Open infrastructure

No single vendor owns the trust layer.

HAP is an open standard — MIT-licensed, developed in the open, and maintained by stewards, not owners. Any compliant Authority Server can issue receipts.