# Teaching agents to pay — Anna Spysz, Stripe

## Executive summary

This talk introduces 'agent-to-commerce,' detailing how AI agents can move beyond research assistance to execute complex transactions on behalf of users. The infrastructure relies heavily on structured data protocols like the Universal Commerce Protocol (UCP) and requires merchants to publish a `merchant capabilities manifest` and JSON catalogs, rather than relying on traditional website browsing. Security is maintained through shared payment tokens, ensuring that the payment provider—not the agent or merchant—enforces transaction limits and guardrails.

## Key takeaways

- Agent Discovery vs. Human Browsing: Agents do not browse websites; they read structured data (JSON) from a `merchant capabilities manifest` to understand supported payment methods, endpoints, and product catalogs. This makes merchants 'agent-ready.'
- The Role of UCP in Transactions: The Universal Commerce Protocol (UCP) acts as a shared language defining how agents initiate, update, complete, and cancel purchases across multiple merchants and agents.
- Security via Shared Payment Tokens: During checkout, the agent receives and passes a 'shared payment token' (representing a raw card number or wallet). The seller only unwraps what is necessary, and the payment provider enforces all limits, mitigating risk.

## Technical details

- Agent Architecture: An agent's decision-making process is structured: a Large Language Model (LLM) 'brain' makes decisions, which are executed by defined tools/actions. These actions are governed by instructions that run in a loop and shaped by the system prompt (persona and ethics policy).
- Merchant Integration Requirements: For agent access, merchants must provide a publicly accessible JSON file—the `merchant capabilities manifest`—located in the `.well-known` directory. This manifest declares supported payment methods and API endpoints.
- Data Structuring for Agents: Product catalogs, policies (e.g., shipping/return), and descriptions must be provided as structured JSON data to allow agents to filter and justify recommendations accurately.
- Agent Guardrails Checklist: Critical guardrail checklist items for building agentic commerce include: always disclosing that the user is speaking to an AI, upfront disclosure of fees, respecting 'stop' or 'cancel' commands, capping totals at a user-defined maximum amount, and logging all decisions for auditability.

## Practical implications

- For build engineers designing e-commerce platforms, adopting structured data standards (like JSON manifests) is crucial for enabling agent interaction.
- API design must account for 'agent consumption' by providing explicit endpoints and schemas rather than relying on general web scraping or parsing of HTML content.
- Implementing robust guardrails—especially around payment handling using shared tokens—is necessary to ensure security and user trust in automated transactions.

## Topics

Agentic Commerce, LLM Orchestration, API Design, Universal Commerce Protocol (UCP), Structured Data, Payment Security, Stripe Developers, Stripe Developers YouTube Channel

Source: https://www.youtube.com/watch?v=A-zeQiYkmXk