Vercel and Ora launched a free public scanner on August 20, 2026 β€” is-agentic.com β€” that grades any URL 0–100 on how well AI agents can discover, read and use it. If you’ve seen it score a site and want to know whether it actually checks whether an agent can buy something there, the short answer: barely, and the tool says so itself.

Two scores, one engine

Ora’s own methodology page describes the full Ora ranker as four layers a real agent moves through: Discovery (16 checks, 20 points), Access (41 checks, 30 points), Usability (56 checks, 40 points), and Payments (6 checks, 10 points) β€” “can it pay you?” out of a possible 100. Vercel’s blog post puts the total check count at 127 across those four layers.

is-agentic.com is not that ranker directly. Per Ora’s own post, it’s “a verticalized endpoint… tuned for what most websites need” β€” a lighter score built from the same underlying scan, where “essentials carry the score, and capability checks like MCP servers or payments sit in a recommended tier and in bonus signals that only add credit.” is-agentic.com’s own methodology page confirms the split: Essential checks share an 80-point pool, Recommended checks share 20, and “emerging signals can add a small bonus, capped at five points, without becoming requirements.” Checks for an API, OAuth, MCP server, GraphQL endpoint or commerce surface only activate once evidence shows the site actually has one β€” a marketing page isn’t marked down for lacking a checkout.

Why that matters for a store

Two things follow from those numbers. First, on the full Ora ranker β€” the one 16,000+ domains have reportedly been scanned against β€” payments is capped at 10% of the total score, the smallest of the four layers by a wide margin (Usability alone is four times the weight). Second, on is-agentic.com specifically, a commerce check isn’t part of the 80-point Essential pool at all; it lives in the 20-point Recommended tier or the 5-point bonus, and only if the scan detects a commerce surface in the first place.

Neither number is wrong for what the tool is trying to do β€” is-agentic.com is explicit that it’s built for the median website, most of which have no checkout to test. But it means a store can post a high is-agentic.com or Ora score while its actual purchase flow β€” cart state, login walls, payment timeouts β€” has never been exercised by the scan. is-agentic.com’s own page states this directly: “Use the report as a prioritized technical review, not as a guarantee that every model or browser automation system will complete every task.” That’s the same gap Cloudflare’s Agent Readiness Score has: it checks that a ucp.json or acp.json file exists, not that an agent can complete a purchase against it.

What to do with a score like this

If your domain scores well on is-agentic.com or ora.ai, treat it as confirmation of the discovery-and-access layer β€” worth having, and no small thing given how few sites pass it. It isn’t evidence that an agent can add your product to a cart, authenticate, and pay. That’s a separate test, and it’s the one AgentReady runs, or you can compare scanners side by side to see what each one actually exercises.

FAQ

Does Vercel’s Is Agentic score check if AI agents can complete a purchase?

Not directly. Commerce checks only activate when the scan detects a commerce surface, and even then they sit in is-agentic.com’s Recommended tier (20 of 100 points) or its 5-point bonus tier, not the 80-point Essential pool that most of the score comes from. The scan reads for the presence of surfaces like a checkout endpoint; it does not drive an agent through adding an item, authenticating and paying.

How much does payments count on the full Ora ranker?

Ora’s methodology page states the full ranker splits 100 points across four layers: Discovery (20), Access (30), Usability (40) and Payments (10). Payments is the smallest layer, worth a quarter of Usability alone, and its 6 checks only run “for products agents can buy or meter.”

What’s the difference between is-agentic.com and ora.ai’s own scanner?

They run the same underlying scan, per Ora’s own blog post, but weight it differently. is-agentic.com evenly weights a smaller set of essentials suited to ordinary websites β€” content sites without an API or checkout to test. The full Ora ranker at ora.ai scores all four layers, including payments, and is aimed at products that agents transact with directly.

Sources

A score that reads a checkout file is not the same as a scan that completes a checkout β€” that gap is what AgentReady tests.