Engineering brief
Your AI Agent Just Authorized What? A Framework for Agent Payments
At a glance
- Relevance
- Practical value
- Warnings
- None
PayPal's Jay Mok and Ben Coumes propose a stakes-and-counterparty matrix for agent authorization: low-stakes code edits need only logs, high-stakes open payments need cryptographic proofs. The framework is worth adopting—before your next agent approves a transaction you can't…
Agent authorization is the next governance bottleneck—this framework makes it concrete.
Summary
PayPal presents a framework for agent authorization built on two axes: transaction stakes (low vs. high) and ecosystem openness (closed vs. open).
The model translates into three tiers: low-stakes actions in closed ecosystems (like Claude code editing) rely on simple logs and reversibility. Medium-stakes payments within a trusted network (e.g., Nevermind) use OAuth scopes and shared vaults, but still depend on centralized transaction logs rather than cryptographic proof.
For high-stakes, open-ecosystem payments where parties don't know each other, the authors argue for FIDO verifiable intents and AP2 mandates—multi-layered, selectively disclosable JWT-style proofs signed by the user and optionally the agent. PayPal's new 'approval token' is a concrete step in this direction, shipping soon for select wallet users.
The tradeoff is clear: stronger cryptographic guarantees increase complexity and user friction, but are mandatory for irreversible actions in untrusted environments. The model generalizes beyond payments to medical orders, e-signatures, and securities trading.
Watch the video
This video is blocked due to your privacy settings. To watch this video, please accept YouTube marketing cookies.
Related breakdowns
The Cheaper Model That Costs More: Why Custom Evals Matter
Cheaper AI models can be more expensive. Learn why custom evaluations are the only way to right-size model cost without sacrificing performance.
Cheap models beat frontier models at writing like a human
Tone-Bench tests whether AI models can write like one specific human. Its most practical lesson: cheaper models with long prompts may beat frontier models on…
Why a faster model can make your users wait 8x longer
MiniMax's M3.1 flash is faster per token, but doubling concurrency lifted p95 wait from 1.5s to 11.3s. Evaluate the whole job, not the model.
Get TL;DW
Too Long; Didn't Watch.
A concise breakdowns of the AI and devtools videos that actually matter for engineering leaders.
Free. Weekly. No hype.
Video and thumbnails remain the property of their respective creators. tldw.news provides editorial analysis, commentary, and discovery links to original content.