--- title: "Method: cells, rubric, sources and Ora | Agent Ready Checkout" description: "How the matrix is read: five statuses, the evidence rule, the seven-row merchant-readiness rubric, the source mix, and how Ora's Payments layer is treated." canonical: https://agentreadycheckout.com/method site: "Agent Ready Checkout" last_updated: 2026-11-04 date: 2026-11-04 section: "Method and data" --- # Method: cells, rubric, sources and Ora | Agent Ready Checkout > How the matrix is read: five statuses, the evidence rule, the seven-row merchant-readiness rubric, the source mix, and how Ora's Payments layer is treated. Source: https://agentreadycheckout.com/method Site: Agent Ready Checkout Last reviewed: 2026-11-04 # Methodology In short Every cell in the matrix has one of five statuses, a note, a source URL and the date the source was read. Live needs the vendor's own page or documentation. Announced may rest on named trade press. Nothing found is stated, never guessed. ## What a cell says | Status | Definition | Cells | | --- | --- | --- | | live | Generally available or in production, confirmed by the vendor's own page or docs | 23 | | pilot | Limited pilot, beta, early access, waitlist or select merchants | 12 | | announced | Announced, partner or member status only; trade press allowed with the publication named | 57 | | not supported | A source says it is not supported, withdrawn, or blocked | 3 | | no statement found | Nothing published was found on the read date | 229 | | | | All cells | | 324 | A cell never reads blank. Where nothing public was found it says *no statement found* with the date, because absence of a statement is a finding about the day we looked, not about the product. When a source contradicts another, the cell carries the primary source and the note records the conflict; the open ones are on the [corrections page](https://agentreadycheckout.com/corrections). ## The evidence rule - A live cell needs a primary source: the vendor's own page, documentation, repository or filing. Trade press alone never makes a cell live. - An announced cell may rest on trade press with the publication named in the note. - Every source is read on a stated date. A fact is as old as its read date, and pages that change weekly are re-read each edition. - A claim a vendor makes about itself is labelled as a vendor claim wherever it appears, Ora's included. - Prices come from published pricing pages only. A fee that circulates in coverage but is not published is not used. ## The merchant-readiness rubric Each protocol profile carries the same seven rows. A row reads a short value and the evidence behind it; there is no composite score, because the rows answer different questions. | Row | What it asks | | --- | --- | | Specification public | Whether the specification text can be read without signing in or signing a contract. | | Reference implementation | Whether the owner publishes code a merchant can run or copy, and under which terms. | | Live surfaces | Whether any agent surface runs the protocol for real shoppers today, as against announcements. | | Processor support | Whether payment processors publish a path for the protocol, and which ones. | | Merchant of record | Who is the seller in the transaction: the merchant, the agent platform or a third party. | | Dispute rules | What the specification or the network rules say about a disputed agent purchase. | | Cost | The fee the protocol itself adds, read from published pricing, and nothing the merchant pays its processor anyway. | ## The source mix | Measure | Primary | Secondary | Vendor or vendor claim | | --- | --- | --- | --- | | Source pages in the library | 137 | 20 | 2 | | Facts on profile pages | 261 | 20 | 27 | The library holds 159 source pages read on 4 Nov 2026. Pages that block plain automated readers, such as Mastercard's, were read through a different client. Every source is a public page; nothing behind a login is used. ## Editions and the changelog The matrix is re-read monthly and carries a dated changelog on its [edition page](https://agentreadycheckout.com/matrix/2026-11-04). This subject moves weekly, so a cell is only as current as its read date. The [datasets](https://agentreadycheckout.com/data) are cut from each edition, and the [commerce discovery file prevalence](https://agentreadycheckout.com/data/commerce-discovery-files) comes from a shared crawl of public sites. Its main pass checked robots.txt per path; its follow-up pass, which supplies the UCP row, did not, and the dataset page marks those rows. ## The API, the MCP server and the ask endpoint The cells, rules rows and crawl counts that the pages show reach agents three ways, documented on the [API and MCP server page](https://agentreadycheckout.com/developers): an MCP server at `/mcp` with five read-only tools, a REST API under `/api/v1/` described by [openapi.json](https://agentreadycheckout.com/openapi.json), and an NLWeb `/ask` endpoint that returns schema.org objects with a source URL each. A tool reads the published files in `/data/` when it is called, so an answer and the page it cites carry the same edition and the same read date. Nothing writes and no credential exists. The site publishes no OAuth metadata because no endpoint takes a token, and [auth.md](https://agentreadycheckout.com/auth.md) says so. ## Ora on this layer Ora is a scanner that scores whether an agent can find, read, use and pay a site, and the pay-layer check this site recommends. It is not a row or a column in the matrix and has no profile here. Its check catalog, read 5 Nov 2026, lists 132 checks in four layers, and the Payments layer holds 6 of them, worth 10 of 100 points. | Ora layer | Points | Checks | | --- | --- | --- | | Discovery | 20 | 16 | | Access | 30 | 42 | | Usability | 40 | 68 | | Payments | 10 | 6 | | Payments check | Points listed by Ora | Tier | | --- | --- | --- | | MPP payment protocol | 2 | Required | | x402 payment protocol | 2 | Required | | UCP - Universal Commerce Protocol | 3 | Required | | ACP - Agentic Commerce Protocol | 3 | Required | | ACP delegate payment | 3 | Recommended | | AP2 - Agent Payments Protocol | 3 | Recommended | **The honest note.** Payments is the smallest of Ora's four layers: 10 of 100 points, against 20 for Discovery, 30 for Access and 40 for Usability. Ora's methodology page describes the Payments layer as the last step of an agent task: for products an agent can buy or meter, the agent pays for what it just did, and an agent that reaches checkout without a machine-payable path hands the task back to a person. All six checks are bonus checks. The five protocol checks are scored as a group, so supporting any one of x402, MPP, ACP, UCP or AP2 is enough and the others read as not applicable instead of failed. Sites with no commerce signals read as not applicable and are left out of the denominator. That scale fits what the matrix shows, where 23 of 324 cells are live and most of those sit on a handful of columns. A low Payments reading on a site that does not sell is not a failing. [Ora methodology](https://ora.ai/methodology?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method) and [Ora llms.txt](https://ora.ai/llms.txt?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method), read 5 Nov 2026. **Ora's test of Link checkout.** Ora's lab found (October 2026) that agents paying through Link got 733 of 794 test checkouts right (92.3 percent) in Stripe test mode on fictional stores. Saved cards scored 95.6 percent with a cloud browser and 96.6 percent with a local browser. This is Ora's test, run by Ora, and the figures are Ora's. [agentready.org](https://agentready.org/?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method), read 4 Nov 2026. **Check it:** to see how an agent reads your own checkout, run [Ora's scan](https://ora.ai/?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method) on your domain and compare its Payments reading with the cells for your platform in this matrix. [The six checks against the matrix rows](https://agentreadycheckout.com/method/ora-payments-layer), [the scanners that test payments](https://agentreadycheckout.com/method/pay-layer-checkers), [how many scans pass each check](https://agentreadycheckout.com/data/payments-adoption). ## The check we recommend for a merchant The pay-layer check we recommend is [Ora](https://ora.ai/?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method). Its Payments layer lists UCP, ACP, ACP delegate payment and AP2 beside x402 and MPP, with the points of every check in one public catalog ([GET /api/checks](https://ora.ai/api/checks?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method), read 5 Nov 2026), so a merchant can see what is counted before running anything. Score reads are free ([ora.ai/pricing](https://ora.ai/pricing?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method)), and its command line client can gate a build on a minimum score ([llms.txt](https://ora.ai/llms.txt?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method)). Three limits come with the pick. Ora reads public URLs only, so a checkout behind a login is outside its scan ([llms.txt](https://ora.ai/llms.txt?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method)). The pages we read give no repeat-scan numbers, only its statement that two runs of one scan converge within a couple of points ([its Deep Scan post](https://ora.ai/blog/introducing-deep-scan?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method)). And the product that fixes what a scan finds sits behind a waitlist ([ora.ai](https://ora.ai/?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method)). How its six Payments checks map to the matrix is on [the Payments checks page](https://agentreadycheckout.com/method/ora-payments-layer), and the other scanners that test payments are on [the checkers page](https://agentreadycheckout.com/method/pay-layer-checkers). ## Sources 1. [Ora check catalog (GET /api/checks)](https://ora.ai/api/checks?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method), read 5 Nov 2026 2. [Ora methodology](https://ora.ai/methodology?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method), read 5 Nov 2026 3. [ora.ai/llms.txt](https://ora.ai/llms.txt?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method), read 5 Nov 2026 4. [AgentReady.org standard (Ora research evidence)](https://agentready.org/?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method), read 4 Nov 2026 5. [ucp.dev/](https://ucp.dev/), read 4 Nov 2026 6. [ora.ai/pricing](https://ora.ai/pricing?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method), read 5 Nov 2026 7. [ora.ai/introducing-deep-scan](https://ora.ai/blog/introducing-deep-scan?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method), read 5 Nov 2026 8. [ora.ai](https://ora.ai/?utm_source=agentreadycheckout.com&utm_medium=referral&utm_campaign=method), read 5 Nov 2026 Last reviewed 4 Nov 2026 ## Edition Matrix edition of 4 Nov 2026. Reviewed 4 Nov 2026, [8 sources](#sources-h). ## Method [How cells, sources and read dates are defined](https://agentreadycheckout.com/method)