Operator pathway · foundation 01

Before an agent can spend.

A payment-capable agent crosses from information work into delegated economic action. The operator's job is to keep that authority explicit, bounded, testable, and reversible.

Learning boundary. This lesson teaches an operating model. It is not a certification, security assessment, legal delegation, financial recommendation, or approval to use production funds.
Learning objective

Separate five control dimensions.

By the end of this lesson, you should be able to inspect a proposed agent-payment workflow, assign evidence-based readiness scores, identify critical stop conditions, and explain why payment settlement is not proof of correct fulfillment.

01 · Mandate

Who delegated what?

Name the principal, objective, resources, counterparties, limits, expiry, escalation conditions, and revocation owner.

02 · Identity

Which agent is acting?

Keep signing material outside model context. Bind identity and authorization to the request, destination, time window, and rotation policy.

03 · Policy

What can it spend?

Enforce assets, networks, recipients, resources, amounts, velocity, and aggregate budgets deterministically—not through prompt language.

04 · Outcome

What settled and arrived?

Preserve distinct states for intent, authorization, execution, settlement, fulfillment, and reconciliation. A transaction reference proves too little by itself.

05 · Exceptions

How does it stop?

Exercise replay, timeout, compromised credentials, duplicate requests, partial fulfillment, refund, dispute, and infrastructure outage paths.

Practice lab · evidence before confidence

Score a bounded API purchase.

An analysis agent may purchase one market-data response for no more than 0.01 USDC on an approved test network. The recipient is allowlisted. Signing is isolated from the model. The team logs payment settlement, but has not tested duplicate requests, correlated delivery to payment, or assigned an incident owner.

  1. Score each dimension from 0: absent, 1: documented, or 2: tested.
  2. Name every claim that requires evidence before awarding a point.
  3. Identify the critical gaps that prevent a bounded pilot.
  4. Write the smallest safe next experiment.

Answer rationale

Mandate, identity, and policy may receive one point only if their documentation can be inspected; none deserves two without exercised tests. Outcome and exceptions cannot exceed one and may be zero: delivery correlation, idempotency, and incident ownership are missing. The appropriate next step is a testnet failure exercise—not higher limits or production funds.

STOP → TEST

Continue the system