Payments

AI agent payments, explained

How wallets, spending policies, payment challenges, stablecoins, fiat settlement, and receipts work when software agents become buyers.

10 min readReviewed July 23, 2026
AgentRequests $0.017company search + enrichment
PolicyApprovedcap $0.25 · category allowed
Weft record2 providersintent · policy · settlement · outcome

TL;DR

AI agent payments are transactions initiated by software within authority delegated by a person or organization. A safe system separates the agent’s ability to request a purchase from the policy engine’s authority to approve and sign it.

What to remember

  • The agent proposes a purchase; a policy-bound account authorizes it.
  • A wallet is only one payment method. The control model matters more than the rail.
  • Protocol payment evidence should be enriched with intent, provider, policy, and outcome context.

Delegated authority, not unlimited autonomy

Giving an agent purchasing power should not mean handing a model an unrestricted private key. The safer pattern separates decision-making from authorization. The agent identifies a service and requests a purchase. A control plane evaluates that request against rules established by the owner of the funds.

Those rules can include a total task budget, per-call ceiling, allowed currencies, approved provider categories, blocked jurisdictions, rate limits, and manual approval above a threshold. The payment credential can then be scoped to the authorized action.

What happens in a paid request

  1. 01

    The service states its terms

    A payment challenge identifies the amount, currency or method, recipient, and the resource being purchased.

  2. 02

    The account checks policy

    The requested spend is evaluated before a signature, token, or other credential is issued.

  3. 03

    The payment is authorized

    The system creates proof through the selected protocol and payment method.

  4. 04

    The service verifies and responds

    The provider follows the selected method’s verification and settlement procedure, then returns the resource when payment requirements are satisfied.

  5. 05

    The system records evidence

    The protocol returns settlement evidence or an optional receipt; Weft can attach the task, provider, endpoint, policy decision, and measured result.

Stablecoins, cards, and processor balances

The current x402 reference ecosystem is strongly oriented toward stablecoin payments, while MPP’s core payment-authentication design is method and currency agnostic. Stripe’s specific MPP integration supports stablecoins settled onchain, plus fiat methods such as cards and buy-now-pay-later through Shared Payment Tokens.

Protocol, payment method, settlement network, and merchant payout are separate choices. Stripe says its MPP transactions can settle to a merchant’s existing Stripe balance in its default currency; that is a property of Stripe’s integration, not of MPP universally.

Controls teams need in production

  • Pre-transaction policy checks with explicit allow and deny reasons.
  • Idempotency so retries cannot accidentally create duplicate charges.
  • Short-lived, least-privilege payment credentials.
  • Provider, endpoint, currency, and protocol observability.
  • Receipts that finance and engineering can reconcile independently.
  • A kill switch and budget controls outside the agent’s prompt context.

Sources and further reading

Protocols change quickly. We reviewed the primary sources below on July 23, 2026.

  1. x402 security and wallet FAQx402 Foundation
  2. Machine paymentsStripe Documentation
  3. Introducing the Machine Payments ProtocolStripe