Skip to content

Does your business work for AI agents?

AZPay Agentic ReadinessAI agent readiness diagnostic for agentic commerce

Agentic readiness means running a store where an AI agent can find the product, build the order, complete the purchase and track the delivery using the data and paths the store publishes. It is the foundation for selling through agentic commerce.

Free diagnostic

Run a diagnostic on your store

We only read what the store already publishes, and the report opens on its own page.

The store’s public address, with https.

The diagnostic doesn’t sign in to accounts, build a cart, create an order or pay. The report doesn’t show your email. The email is checked by a validation service.

Why it matters

A store built only for on-screen clicks leaves the agent’s path incomplete.

AI agents can already search for offers and start a purchase on someone’s behalf. A store built only for on-screen clicks leaves that path incomplete: the agent can’t read the catalog, can’t build the cart or stops before payment. This diagnostic shows, in plain language, what the store needs to adjust to take part in this kind of sale.

The six diagnostic criteria

The diagnostic runs 38 checks across the six criteria. Each criterion gets a score from 0 to 100, and the overall score is a weighted average: catalog 25%, cart 20%, checkout 15%, bot policies 15%, payment 15% and order traceability 10%. From 85 points the store is ready for agents; from 70, ready with some gaps; from 40, partly ready; below that, not ready yet. If the store blocks the reading, the report says so instead of showing a low score. The report shows what was found and the five fixes with the greatest impact.

Cart endpoints

Choosing the product is only the start: the agent needs to build a cart. That can be a cart API or predictable URLs that always lead to the same set of items. Without a stable path, the visit stops at the storefront and the order never exists.

4 checks: identifiable platform, public product JSON, cart read (such as /cart.js) and price with variant or availability.

Agent-compatible checkout

Checkout needs to be a flow an agent can complete, not just a sequence of clicks designed for a person. That includes compatibility with agentic commerce protocols and a clear path to order confirmation. If a step only works with human interaction on screen, the purchase stops halfway.

5 checks: captcha or challenge, guest checkout, UCP profile at /.well-known/ucp, ACP document at /.well-known/acp.json and other machine-to-machine channels.

Bot policies

The store needs to declare which automations it accepts. This shows up in robots.txt, llms.txt and firewall or bot management rules: they shouldn’t block legitimate agents and should be able to identify verified bots. Treating all automated access as abuse also shuts the door on those who would come to buy.

9 checks: robots.txt rules per agent, home page response for ChatGPT-User, OAI-SearchBot, Claude-User and PerplexityBot, probe access, HTTP redirects, content without login, Markdown response, useful 404, training-crawler policy and signed bots.

Order traceability

After payment, order status and tracking need to be queryable by machines. The agent, or the person who authorized it, must be able to follow the order without copying codes from an email into another site. A status lookup via API or structured data closes the sales loop.

3 checks: tracking page without an account, Order or ParcelDelivery JSON-LD and a named carrier.

Payment capability

The purchase only ends when there is a payment method the agent can use and authorize. That includes programmatic payments, where the charge follows a rule agreed in advance, without someone typing in details for every order. If the only path is a button made for a person, this step remains incomplete.

4 checks: payment methods written in the HTML (Pix, card, boleto), Pix, identifiable gateway and programmatic payment: UCP with payment handlers, ACP or /.well-known/x402.

  1. Enter the store URL.
  2. AZPay checks the six points.
  3. The report gives a score for each criterion and what to fix.

How the diagnostic works

Enter the store URL. AZPay checks the six points and delivers a report with a score for each criterion and what to fix.

AZPay Agentic Readiness is free. The diagnostic only reads what the store already publishes: it doesn’t sign in to accounts, build a cart, place an order or pay. Points that can’t be seen from the outside are marked as undetermined.

Frequently asked questions

What is AZPay Agentic Readiness?

AZPay Agentic Readiness is a diagnostic that checks whether an online store is ready to sell to AI agents. It assesses six criteria, from catalog to payment, and delivers a report with a score for each criterion and what to fix. The diagnostic is free.

What is agentic commerce?

Agentic commerce is selling where an AI agent searches, compares, builds the order and pays on behalf of a person or company, within the limits they authorized. To take part, a store has to publish data and paths a machine can read and use, from the catalog to order tracking.

What does being ready for AI agents mean?

Being ready for AI agents means running a store where an agent can find the product, build the order, complete the purchase and track the delivery using the data and paths the store publishes. If any of these steps only works for a person clicking on screen, the store isn’t ready yet.

Can I run the diagnostic myself?

Yes. At the top of this page you enter the store URL and an email address, and the report opens on its own page, usually within a few minutes. The diagnostic only reads what the store already publishes, without signing in to accounts, building a cart or placing an order.

How much does it cost?

The diagnostic is free. You enter the store URL and an email address and get the report on its own page. To prevent abuse, there is a daily limit of diagnostics per store and per email address.

What are the six criteria?

Agent-accessible catalog, cart endpoints, agent-compatible checkout, bot policies, order traceability and payment capability. Each criterion gets a score and a pointer to what to fix.

Which protocols do you check?

We check the UCP (Universal Commerce Protocol) profile at /.well-known/ucp, the ACP (Agentic Commerce Protocol) discovery document at /.well-known/acp.json and x402 at /.well-known/x402. We also read robots.txt, the XML sitemap, llms.txt and schema.org JSON-LD (Product, Offer, Organization and Order), and test whether the home page answers ChatGPT-User, OAI-SearchBot, Claude-User and PerplexityBot. In total, 38 checks across six criteria.

Do I need to change my store platform?

The diagnostic starts from the URL of the store you already run. It describes what an agent can or can’t do today. It doesn’t replace the platform, nor does it promise that every adjustment comes implemented in the report.

What does the bot policies criterion check?

It looks at whether robots.txt, llms.txt and firewall or bot management rules let legitimate agents through and identify verified bots. Blocking all automated traffic also blocks those who would come to buy.

What counts as payment capability?

A method the agent can use and authorize counts, including programmatic payments, where the charge follows agreed rules. A payment that only works with someone typing in details for every order doesn’t complete this step.

Get your store ready to sell to agents

The report points out what to fix. At the payment step, AZPay Agents is AZPay’s programmatic path.