{
  "schema_version": "1.1",
  "id": "s8:https://www.youtube.com/watch?v=A-zeQiYkmXk",
  "slug": "teaching-agents-to-pay-anna-spysz-stripe-04jxy0s",
  "url": "https://feed7.dev/p/teaching-agents-to-pay-anna-spysz-stripe-04jxy0s",
  "title": "Teaching agents to pay — Anna Spysz, Stripe",
  "why_included": "Agent checkout needs more than payment tools: enforce user-set limits outside the agent, expose structured merchant data, honor cancellation, and log every decision.",
  "summary": "The demo uses **UCP** as a shared interface for agents and merchants. Stores expose a capabilities manifest and structured catalog; checkout uses a **shared payment token**, so the agent receives a token rather than the raw card number.",
  "practical_implication": "Put spending and token validity checks at the payment provider, not inside a prompt. Also disclose the agent, show fees, honor stop or cancel, reject totals above the user's maximum, avoid pressure tactics, and keep auditable decision logs.",
  "agent_context": "The demo uses **UCP** as a shared interface for agents and merchants. Stores expose a capabilities manifest and structured catalog; checkout uses a **shared payment token**, so the agent receives a token rather than the raw card number.\n\nPut spending and token validity checks at the payment provider, not inside a prompt. Also disclose the agent, show fees, honor stop or cancel, reject totals above the user's maximum, avoid pressure tactics, and keep auditable decision logs.\n\nThe hostile-salesperson example shows that a **system prompt can materially alter behavior**, even when the transaction plumbing is unchanged. These safeguards are presented as a practical checklist, not evidence that every manipulation or commerce failure is covered.",
  "source": {
    "name": "AI Engineer",
    "url": "https://www.youtube.com/watch?v=A-zeQiYkmXk",
    "published_at": "2026-09-01T16:30:06.000Z"
  },
  "source_class": "video",
  "content_type": "Video",
  "layer": "agent",
  "domains": [
    "security"
  ],
  "topics": [
    "tool-use",
    "harness-engineering",
    "agent-reliability"
  ],
  "verification": {
    "status": "source_linked",
    "label": "Source Linked",
    "method": "source_feed",
    "verified_at": null
  },
  "uncertainty": [
    "The hostile-salesperson example shows that a **system prompt can materially alter behavior**, even when the transaction plumbing is unchanged. These safeguards are presented as a practical checklist, not evidence that every manipulation or commerce failure is covered."
  ],
  "connected_context": {
    "meaning": "This turns payment safety into both a protocol and behavior problem. UCP structures merchant capabilities and shields raw card data, while provider-side limits, cancellation, disclosure, and audit logs constrain execution. The hostile-salesperson demo confirms that unchanged payment plumbing cannot neutralize prompt-driven manipulation, so transaction controls and behavioral policy must be enforced separately.",
    "corpus_size": 669,
    "generated_at": "2026-09-03T10:00:54.676Z",
    "connections": [
      {
        "title": "Your Agent Just Authorized What?! — Jay Mok & Ben Coumes, Paypal",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=vGn6N4-bxBY",
        "feed7_url": "https://feed7.dev/p/your-agent-just-authorized-what-jay-mok-ben-coumes-paypal-024znqi",
        "reason": "PayPal’s scoped, time-bound mandates strengthen Stripe’s provider-side checks by requiring payment authority to be attributable and independently verifiable."
      },
      {
        "title": "AI Agents Are Just Distributed Systems Now — Salman Munaf, TikTok",
        "source_name": "AI Engineer",
        "source_url": "https://www.youtube.com/watch?v=hD9-V56FNRI",
        "feed7_url": "https://feed7.dev/p/ai-agents-are-just-distributed-systems-now-salman-munaf-tiktok-1v4yc47",
        "reason": "Stripe’s checklist governs authorization and conduct, while the distributed-systems candidate adds idempotency and reconciliation for ambiguous payment outcomes after timeouts."
      },
      {
        "title": "Stop AI Agent Hallucinations: 5 Techniques + Production Patterns - Elizabeth Fuentes, AWS",
        "source_name": "YouTube",
        "source_url": "https://www.youtube.com/watch?v=vJukHCIv7Ck",
        "feed7_url": "https://feed7.dev/p/stop-ai-agent-hallucinations-5-techniques-production-patterns-elizabeth-09g1w9s",
        "reason": "Its pre-call rule enforcement supports rejecting invalid totals outside free-form reasoning, but Stripe adds commerce-specific duties such as fee disclosure and honoring cancellation."
      },
      {
        "title": "In Code They Act, In Proof We Trust — Erik Meijer, Leibniz Labs",
        "source_name": "YouTube",
        "source_url": "https://www.youtube.com/watch?v=-CnA2lGfymY",
        "feed7_url": "https://feed7.dev/p/in-code-they-act-in-proof-we-trust-erik-meijer-leibniz-labs-1lyno2y",
        "reason": "The proposed proof-gated harness is a stronger version of Stripe’s separation between model intent and executable payment checks, though Stripe presents a practical checklist rather than formal verification."
      }
    ]
  },
  "lifecycle": "Current",
  "published_at": "2026-09-01T16:30:06.000Z",
  "modified_at": "2026-09-01T16:30:06.000Z",
  "supersedes": [],
  "expires_at": null,
  "formats": {
    "html": "https://feed7.dev/p/teaching-agents-to-pay-anna-spysz-stripe-04jxy0s",
    "json": "https://feed7.dev/p/teaching-agents-to-pay-anna-spysz-stripe-04jxy0s.json",
    "markdown": "https://feed7.dev/p/teaching-agents-to-pay-anna-spysz-stripe-04jxy0s.md"
  }
}