Get KordnOSDiscuss a deployment

Verifiable delegatedauthority for AI agents

The Kordn Delegation Protocol lets organizations delegate bounded authority to AI agents. When an agent acts, its counterparty can verify who authorized it, what it may do, and whether that action is within scope.

Discuss a deployment

An agent's internal permissions stop at the company boundary.

Organizations already use access controls, policies, API credentials, and approval systems to govern software internally. But an external counterparty cannot inspect those controls. When an agent acts across a company boundary, the counterparty needs answers to a different set of questions:

  • Who authorized this agent?
  • What was it authorized to do?
  • What constraints apply?
  • Is the authority still valid?
  • Does this particular action fall within its scope?

Identity tells you which agent is acting. Delegation tells you what it may do.

Identity

Who is acting?

What a counterparty can see today
Delegated authority
  • Who authorized the agent?
  • What may it do?
  • Under what constraints?
  • Is this action within scope?
What Kordn Delegation Protocol makes verifiable

How a counterparty verifies an agent’s authority

01

Define the authority

An organization issues a delegation credential describing what an agent may do and under which constraints.

02

Bind the action

When the agent uses that authority, it signs the exact consequential action and links it to the credential.

03

Verify before accepting

The counterparty checks the issuer, credential status, signature, and scope before deciding whether to accept the action.

Inside the organization Across the boundary
People + systems
KordnOS
Delegates authority
AI agent
Signed action
Counterpartyverifies the authority

Using KordnOS, people and systems delegate bounded authority to an AI agent. When the agent acts across the organizational boundary, it signs the exact action and links it to its delegation credential. The counterparty verifies both before deciding whether to accept the action

Inside the organization
01Define the authority

An organization issues a delegation credential describing what an agent may do and under which constraints.

People + systemsIssues credentialKordnOS
02Bind the action

When the agent uses that authority, it signs the exact consequential action and links it to the credential.

KordnOSDelegates authorityAI agent
Across the organizational boundary
03Verify before accepting

The counterparty checks the issuer, credential status, signature, and scope before deciding whether to accept the action.

AI agentSigned actionCounterparty

Using KordnOS, people and systems delegate bounded authority to an AI agent. When the agent acts across the organizational boundary, it signs the exact action and links it to its delegation credential. The counterparty verifies both before deciding whether to accept the action.

Designed for real organizational boundaries

  1. 01

    Authority must be explicit and bounded.

  2. 02

    Authority must be verifiable, not merely asserted by the agent.

  3. 03

    Every consequential action must be bound to the authority under which it was taken.

  4. 04

    Delegation must support constraints, expiry, and revocation.

  5. 05

    Each organization must retain control over its own acceptance policy..

  6. 06

    The protocol must work across vendors, agents, and organizational systems.

Will your AI agents act across company boundaries?

We are working with organizations, agent developers, and infrastructure providers preparing for agents to place orders, approve work, or make commitments across company boundaries.

Discuss a deployment

Technical materials are available to selected deployment partners.