Agentic Rails Atlasby merces.ai

Persona

Delegating consumer

Wants an agent to buy for them without losing control, refunds or privacy.

Verified (verified under 30 days ago)

Role

Goals

  • Hand a shopping task to an agent and set a budget, a merchant list and an expiry before anything is charged.
  • See exactly what was bought, from whom, for how much, and which agent did it, in one place.
  • Keep the same refund and dispute rights as for a purchase made by hand.
  • Approve high-value or unusual purchases with a passkey, and let small routine ones run without a prompt.
  • Share as little personal data with merchants as a purchase needs.
  • Revoke an agent's payment access in one step when it misbehaves or when the task is done.

Pains

  • Under Regulation E, a payment made by an agent the consumer gave credentials to may not count as unauthorized, so it is unclear who pays when the agent buys the wrong thing.
  • Bank and card statements show the merchant, not the agent, so a bad purchase is hard to trace back to the delegation that caused it.
  • Consent screens differ in every wallet and surface. Some ask once for broad permission, others ask at each checkout, and the consumer cannot tell which rule applied.
  • The TAP consumer object and similar payloads carry IP address, device data and location to the merchant without a clear opt-out.
  • Open mandates in AP2 and Verifiable Intent can last 24 hours to 30 days, and there is no standard way to revoke one early.
  • Prompt injection on a merchant page can steer the agent toward a different product or seller, and the consumer only finds out after the charge.

Decisions they own

  • How much spending authority to delegate: a one-time closed amount, or an open budget with constraints.
  • Which wallet or credential provider holds the card and captures consent.
  • Which agent or surface to trust with a payment credential at all.
  • Whether to require a step-up approval for every purchase or only above a threshold.

Vocabulary

  • budget
  • spending limit
  • mandate
  • passkey
  • consent
  • refund
  • chargeback
  • dispute
  • Regulation E
  • revoke
  • receipt
  • step-up
  • allowed merchants
  • human-not-present

Each protocol from this seat

Relevance levels: High, a main persona on the protocol page; Medium, owns, implements or verifies a step; Low, relies on or observes a step; None, no role found in the protocol page.

ERC-8004: Trustless Agents

Relevance: None

Not one of the main personas on the ERC-8004: Trustless Agents page. The responsibility table gives this persona no step.

x402

Relevance: None

Not one of the main personas on the x402 page. The responsibility table gives this persona no step.

Visa Trusted Agent Protocol

Relevance: None

Not one of the main personas on the Visa Trusted Agent Protocol page. The responsibility table gives this persona no step.

Agentic Commerce Protocol (ACP)

Relevance: High

Buys through an AI assistant and sees the merchant, not the assistant, as the seller. Source [1, 2, 3]

Goals

  • Buy quickly without typing a card number again
  • Know who to contact if something goes wrong
  • Not be charged more than approved

Pains

  • The checkout path changed in 2026 and differs by merchant
  • No signed record of what was approved
  • Unclear fees and ranking

Implements

  • Confirming the purchase in the assistant interface

Must trust

  • The assistant to show the merchant's real totals
  • The merchant to fulfill and refund
  • The token to be limited to the approved amount

Questions they ask

  • Who is the seller here?
  • Can the assistant charge me again?
  • Where do I ask for a refund?

First three steps

  1. Check the merchant name and total before you confirm
  2. Keep the order link the assistant shows
  3. Use the merchant's own support for returns

Metrics they care about

  • Total charged versus total approved
  • Time to refund

A day in the life. Sam asks an assistant for running shoes in size ten. The assistant shows three options from different stores, each with a price from the store itself. Sam picks one and confirms the total, including tax and shipping. The assistant says the purchase is with the store, and the card statement later shows the store's name, not the assistant's. When the shoes are too small, Sam opens the order link and starts a return on the store's site. The refund appears as an adjustment in the order updates the assistant receives. Nothing in the protocol records Sam's confirmation except the assistant's own interface.

Steps in the responsibility table

  • ObservesCreate and update the checkout session
  • ObservesReturn authoritative totals and messages
  • OwnsConfirm the purchase
  • Relies onSet the allowance (max_amount, merchant, session, expiry)
  • Relies onCreate the order (merchant of record)
  • Relies onHandle refunds and chargebacks

UCP

Relevance: High

The buyer: asks an agent to shop, reviews and places the order, and deals with the merchant afterward. Source [4, 5, 6, 7]

Goals

  • Buy without filling in forms on every site
  • See the real seller, price and terms before paying
  • Get refunds and support from the store as usual

Pains

  • Not always clear who the seller is on an agent surface
  • Privacy and upselling concerns raised about agent checkout
  • Handoffs to a store web page in the middle of a purchase

Implements

  • Nothing; uses the platform's trusted checkout screen

Must trust

  • The platform to show the business's own checkout and links
  • The business as merchant of record
  • The wallet that issues the token

Questions they ask

  • Who is the seller?
  • Can the agent buy without me pressing buy?
  • Where do I go for a refund?

First three steps

  1. Check the seller name and the terms link on the review screen
  2. Use a wallet you already trust
  3. Keep the order link from the confirmation email

Metrics they care about

  • Time to purchase
  • Number of handoffs
  • Refund and return experience

A day in the life. Maria asks Gemini to find a ceramic vase under $80 and buy it. The agent finds one at a store that supports UCP checkout, fills in her address and shows her a review screen with the store's name, the total and the store's terms. She presses buy and Google Pay supplies the payment. A confirmation email from the store arrives a minute later with an order link. When the vase arrives chipped, she returns it through the store's site, because the store, not Google, sold it to her. She never typed a card number, and the agent never placed the order without her tap.

Steps in the responsibility table

  • OwnsReview and place the order in a trusted UI
  • Relies onEscalate with continue_url
  • Relies onIssue the opaque token
  • Relies onSign the checkout and verify the AP2 mandate
  • ObservesSend signed order webhooks
  • Relies onHandle refunds and disputes

AP2

Relevance: High

Approves mandates on a Trusted Surface: exact purchases when present, limits for the agent when not. Source [8, 9, 10]

Goals

  • Let an agent buy within limits I set
  • See exactly what I approve
  • Have evidence if a purchase goes wrong

Pains

  • No way to cancel an open mandate before it expires
  • Limits written in constraint terms are hard to read
  • Unclear who pays if the agent misreads me

Implements

  • Nothing technical: approves on a wallet, issuer app, browser or agent app that acts as Trusted Surface

Must trust

  • The Trusted Surface to show the real checkout
  • The agent to stay inside its constraints
  • The network rules for disputes

Questions they ask

  • What exactly did I approve, and for how long?
  • Can the agent spend twice from one approval?
  • What happens when the agent finds something outside my limits?

First three steps

  1. Read the merchant, items, amount range and expiry before approving an open mandate
  2. Prefer short expiry times for autonomous tasks
  3. Keep the receipts the agent stores

Metrics they care about

  • Time from task to approved purchase
  • Number of fallbacks to manual approval
  • Disputes resolved with mandate evidence

A day in the life. Priya asks her assistant to buy a two-person tent before Friday, under 300 dollars, from one of two outdoor stores. Her banking app opens and shows the limits in plain words, the stores, the price ceiling and an expiry on Friday night. She confirms with her fingerprint and goes to work. On Wednesday the agent finds the green tent for 249 dollars and buys it without asking. On Thursday it tries a matching groundsheet, but the store answers that the item is outside the approved line items, so her phone asks her to approve that one directly. She declines. Both receipts sit in the app.

Steps in the responsibility table

  • OwnsApprove Mandate Content on the Trusted Surface
  • Relies onSign closed mandates in human-not-present mode
  • Relies onVerify mandates and receipts in a dispute

Mastercard Agent Pay

Relevance: High

Holds the Mastercard card, authorizes an agent with a passkey and sets its limits. Source [11, 12, 13]

Goals

  • Delegate routine purchases safely
  • Keep the real card number private
  • Get money back if the agent gets it wrong

Pains

  • Unclear rules when an agent buys the wrong item within its limits
  • Little visibility into which agents are trusted
  • Limits that vary by platform

Implements

  • Passkey authentication
  • Merchant, amount and time limits for the agent

Must trust

  • The agent platform to follow instructions
  • The issuer to honor dispute rights
  • Mastercard certification

Questions they ask

  • Can the agent see my card number?
  • How do I stop the agent?
  • Who refunds a wrong purchase?

First three steps

  1. Check that your bank supports Agent Pay
  2. Set tight merchant and amount limits
  3. Review your statement for agent purchases

Metrics they care about

  • Purchases completed as intended
  • Disputes raised
  • Time to cancel an agent

A day in the life. Tom asks his assistant app to book a ski weekend under a set budget. The app asks him to confirm with a passkey and to choose limits: this merchant, this amount, this weekend. It never sees his card number; it gets an agentic token that works only within those limits. If the booking is wrong he can dispute it with his bank like any card purchase, because standard chargeback rights apply. What he cannot find is a simple button to stop one agent everywhere, so he plans to keep limits tight and short.

Steps in the responsibility table

  • OwnsAuthenticate consumer and set limits
  • Relies onProvision agentic token
  • Relies onVerify Verifiable Intent chain
  • Relies onHandle dispute

Sources

  1. Agentic Commerce (OpenAI developer documentation; full Markdown export at /commerce/llms-full.txt) (external link)OpenAI. Documentation, primary source. Accessed .
  2. Buy it in ChatGPT: Instant Checkout and the Agentic Commerce Protocol (external link)OpenAI. Announcement, primary source. Published . Accessed . Archived copy (external link).
  3. ACP JSON Schema, Agentic Checkout, 2026-04-17 (external link)Agentic Commerce Protocol project. Specification, primary source. Accessed .
  4. Checkout Capability (v2026-08-25) (external link)UCP Authors. Specification, primary source. Published . Accessed .
  5. Frequently Asked Questions, Google UCP Guide (external link)Google. Documentation, primary source. Accessed .
  6. UCP glossary (v2026-08-25) (external link)UCP Authors. Specification, primary source. Published . Accessed .
  7. What to expect in digital advertising and commerce in 2026 (external link)Google (Vidhya Srinivasan). Announcement, primary source. Published . Accessed .
  8. AP2 Flow Examples (external link)Google (google-agentic-commerce). Specification, primary source. Published . Accessed .
  9. Agentic Payment Protocol (v0.2) specification (external link)Google (google-agentic-commerce). Specification, primary source. Published . Accessed .
  10. AP2 Implementation Considerations (external link)Google (google-agentic-commerce). Specification, primary source. Published . Accessed .
  11. Level 1 Agentic Commerce: Enable Agent Support with Minimal Changes (external link)Mastercard Developers (Merchant Cloud tutorials). Documentation, primary source. Accessed .
  12. Mastercard advances agentic payments in Latin America and the Caribbean with live transactions completed across the region (external link)Mastercard Newsroom. Announcement, primary source. Published . Accessed .
  13. Mastercard accelerates AI-powered commerce with Australia’s first authenticated agentic transactions using Agent Pay (external link)Mastercard Newsroom. Announcement, primary source. Published . Accessed .

Source details

    Loading the index.

    Enter open Esc close ? shortcuts