Sign InOpen Brain
AI EngineerVideoSource Linked

Your Agent Just Authorized What?! — Jay Mok & Ben Coumes, Paypal

Agent authorization should scale with stakes and reversibility: logs may cover coding changes, while open-ended payments need scoped, time-bound, independently verifiable mandates.

AI Engineer · Sep 1, 2026
Open Source Open MarkdownOpen JSON
Source Summary

PayPal frames authorization around **three questions**: did the human approve, is the action currently within scope, and can that approval be proven later. Its approval token can be issued before product selection and carries constraints including **amount, expiry, and merchant**.

Practical Implication

Match controls to consequences. Reversible coding work may rely on permissions and logs; payments inside a vetted network can use scoped credentials; irreversible actions across unknown parties need signed intent that merchants and processors can verify independently.

Agent-Ready Context
PayPal frames authorization around **three questions**: did the human approve, is the action currently within scope, and can that approval be proven later. Its approval token can be issued before product selection and carries constraints including **amount, expiry, and merchant**.

Match controls to consequences. Reversible coding work may rely on permissions and logs; payments inside a vetted network can use scoped credentials; irreversible actions across unknown parties need signed intent that merchants and processors can verify independently.

The highest-stakes open-ecosystem model was **not yet observed in production**. PayPal's near-term token is an opaque value only PayPal can validate, while interoperable FIDO verifiable intents and AP2 mandates remain the proposed direction.
Connected Context · Feed7 Judgment

This refines least privilege into an evidence-bearing authorization contract: approval must come from a human, remain within current amount, merchant, and time constraints, and be provable after execution. It makes control strength depend on consequence and reversibility, while narrowing the strongest open-ecosystem design to a proposal rather than demonstrated production practice.

Teaching agents to pay — Anna Spysz, StripeStripe’s external limits, cancellation, disclosure, and logs complement PayPal’s approval token by covering execution and recovery around the scoped authorization.AI Agents Are Just Distributed Systems Now — Salman Munaf, TikTokSigned intent answers who authorized what, while idempotency, reconciliation, and compensation address the separate unknown-outcome problem after a payment tool call begins.In Code They Act, In Proof We Trust — Erik Meijer, Leibniz LabsThe proof-gated harness applies the same pre-side-effect principle more generally, but PayPal grounds it in human attribution and constraints that merchants and processors can verify.Tribal Dungeons of Global Shipping: AI Agents at Global Scale — Dmitry Buykin, MaerskMaersk’s bounded tools and replayable traces reinforce that scoped authority and provable history must be maintained as operational infrastructure, not treated as a one-time approval prompt.
Context Map
agentcodingsecurity#tool-use#harness-engineering#agent-reliability
Uncertainty
The highest-stakes open-ecosystem model was **not yet observed in production**. PayPal's near-term token is an opaque value only PayPal can validate, while interoperable FIDO verifiable intents and AP2 mandates remain the proposed direction.