A shopping agent can recommend the wrong item while quoting every word on your homepage correctly. The failure often lives deeper: a variant is out of stock, a delivery promise applies only to one region, or a return exception is hidden in an image. Agent-friendly commerce begins with dependable product facts.
A shopping agent can recommend the wrong item while quoting every word on your homepage correctly. The failure often lives deeper: a variant is out of stock, a delivery promise applies only to one region, or a return exception is hidden in an image. Agent-friendly commerce begins with dependable product facts.
Audit the smallest purchasable unit. A product family is not the same as its blue, medium, in-stock variant. Give each variant a stable identifier, a clear relationship to the parent product, a current price with currency, availability and the conditions that affect delivery or returns. A feed and a product page should tell the same story.
What to build—and what each layer does
| Layer | Useful job | What it does not establish |
|---|---|---|
| Readable, accessible pages | Explain the offer and make the next action understandable. | That an agent will interpret every detail correctly. |
| A short llms.txt | Provide a concise map for clients that use it. | Permission, universal adoption or a search ranking boost. |
| Documented read-only data | Return structured facts for a defined task. | That those facts are fresh or safe without maintenance. |
| Optional MCP integration | Expose capabilities to compatible clients. | Automatic discovery, authorization or reliable outcomes. |
Choose the layer that solves the observed problem. llms.txt proposal and format describes the file convention; OpenAPI specification describes HTTP API contracts; Model Context Protocol architecture explains MCP’s client/server architecture. These are different responsibilities.
Worked example: a bag for a specific trip
Illustrative Coastline Carry sells a small bag in two materials. A shopper needs the washable version and delivery to a specified destination. The agent must identify the material, the correct variant and the delivery information the store can actually support. “Usually dispatches in two business days” is not a guarantee of arrival by Friday. If the postcode or live shipping quote is required, the answer must explain that uncertainty.
Use the store’s supported customer-facing interface
Shopify’s Storefront API supports customer-facing product and cart workflows. WooCommerce’s Store API exposes customer-facing product, cart and checkout data, with additional protections for writes. Read the platform documentation before choosing an integration. Do not publish an Admin API token, expose customer records or turn authenticated administrative endpoints into public endpoints. A catalog lookup is a sensible first test; placing orders is a separate implementation with stronger controls.
Test the awkward cases before the attractive demo
Include an unavailable variant, a sale that has ended, a missing size, an unsupported destination and conflicting policy text. Re-fetch price and stock near the decision point. In a test environment, check how cart and checkout failures are reported; never run an unapproved real purchase to prove a scanner score. Keep a human review point for quantity, total, delivery and payment before commitment.
The six-step implementation
- Pick one product family. Include its real variants.
- Align the facts. Page, feed and catalog agree.
- Explain the conditions. Shipping, returns and limits.
- Use a supported API. Start with public product reads.
- Test edge cases. Stock, regions and stale prices.
- Review before checkout. Confirm the final commitment.
A short llms.txt you can adapt
This is an illustrative template. Replace every example.com URL with an existing public page on your own domain. Check the content, not just the link. If your site has no public API, leave API instructions out. Do not publish placeholder endpoints, private URLs, access tokens or customer information.
# Coastline Carry
> Find a suitable product variant, explain the current price and return conditions, and stop before adding it to a cart.
## Useful pages
- [Main information](https://example.com/collections/): The current offering and relevant details.
- [Conditions and process](https://example.com/shipping/): Eligibility, limitations and how the process works.
- [Next step](https://example.com/returns/): The official route for a person to continue.
## Boundaries
This example does not support automated purchases or bookings.
Use the linked pages for current facts; ask when information is missing.
Serve the file at your site root when your hosting setup supports it. In a typical static build, that means placing it in the directory copied to the public root. Verify the deployed URL: a local file alone is not a published file. If your platform already generates one, inspect and maintain that version instead of creating conflicting instructions.
If you need an API, start with a read
The following is a hypothetical catalog-adapter contract, not an endpoint installed on this site or a native Shopify or WooCommerce request. The price and stock state are fictional. A null delivery estimate means unknown; the agent must not turn it into an arrival promise. Choose fields that answer the task, document their types and meaning, and return only information you intend to make public. Include a source URL and an update signal where useful. A checked date records a review; it does not guarantee the underlying data is current.
GET https://example.com/api/v1/products/weekender-washable
Accept: application/json
{
"example": true,
"checked_at": "2026-11-11",
"product_id": "weekender",
"variant_id": "weekender-washable",
"name": "Coastline Weekender \u2014 washable fabric",
"material": "Washable fabric",
"price": {
"amount": "49.00",
"currency": "USD"
},
"availability": "in_stock_at_last_check",
"delivery_estimate": null,
"delivery_note": "Destination and current shipping quote required.",
"returns_url": "https://example.com/returns/",
"source_url": "https://example.com/products/weekender/",
"available_actions": [
"read_details"
]
}Define no-result and error behavior as carefully as success. Keep private data behind proper access controls. For future actions that change records or spend money, design authentication, authorization, explicit confirmation and duplicate-action protection separately. OWASP API Security Project provides a useful security review starting point.
A better audit prompt
Use an assistant with browsing or request capabilities. If it cannot access the site, it should report the limitation; a fluent response is not proof of inspection.
Review this public website: [URL]. Task: Find a suitable product variant, explain the current price and return conditions, and stop before adding it to a cart.
Use browsing or request tools if available; if unavailable, say what you cannot verify. Inspect the relevant public pages and /llms.txt. Record the URLs you actually fetched and the facts you found. Do not infer success from a 200 response alone. Separate observed facts, missing information and suggested changes. Do not sign in, submit forms, change data, add to a cart or purchase.
Draft a concise llms.txt using only verified public URLs. Include an API example only if a documented public endpoint exists and its read operation is appropriate to test. Do not invent endpoints. Rank the three most useful fixes by customer impact and effort. Explain how to retest each one.Test what happened, not what the assistant says happened
| Test | Evidence to keep | A passing result |
|---|---|---|
| Retrieve the map | Final URL, status, content type and response body. | The actual text file appears; no login page or application shell. |
| Follow its links | The final destination and the relevant source facts. | Useful pages resolve and match the stated purpose. |
| Try the customer task | Exact prompt, tool capability, answer and cited URLs. | Required facts and next step are correct. |
| Ask an unsupported question | The answer and what the source actually says. | The assistant names the limit rather than inventing a capability. |
| Repeat after a change | Source version, date and all attempted runs. | Any improvement is reproducible within the tested setup. |
Measure for this site’s use case: Variant accuracy, stale-data errors, successful product handoffs and verified orders where attribution exists. A recommendation is not an order.
Run a baseline before editing. Use fresh sessions and keep the prompt and available tools comparable. Include failed attempts in your denominator. Record whether you explicitly told the agent about llms.txt; that is different from observing spontaneous discovery. A scanner is a diagnostic aid, not a certification.
Avoid the shortcuts that create new problems
- Do not replace readable pages with machine-only content. People still need to evaluate the offer.
- Do not treat robots.txt or llms.txt as authentication. Protect private routes with real access controls.
- Do not tell every crawler it may access everything merely to improve a score.
- Do not duplicate prices and policies into several files without an update process.
- Do not claim a successful booking, lead or sale from a generated answer. Verify the actual system result.
For interface implementation, consult Google web.dev: agent-friendly website UX and W3C: labeling form controls. Preserve descriptive controls, meaningful form labels and visible state changes. Agent testing complements human usability and accessibility testing.
Questions worth answering
Will llms.txt improve Google rankings?
No ranking benefit is established by adding this file. Google’s current guidance says it does not use llms.txt for Search visibility. Treat the file as an optional usability aid for clients that consume it; keep ordinary SEO work and task testing separate.
Do I need MCP or Markdown copies of every page?
Not for every project. Start with the smallest interface the task requires. Add Markdown resources or a compatible tool integration when there is a clear consumer and maintenance plan. Check platform support rather than assuming all assistants behave the same way.
Can I use this without coding?
Yes. You can clarify public pages, check links and run the task exercise with your existing website editor and assistant. Publishing a root file depends on the host. A public API requires additional implementation; ask for help if that is outside your skills.
How often should I review it?
Review whenever an offering, policy, route or API contract changes. Assign an owner. Frequently changing prices or stock need stronger freshness controls than a static guide.
Search guidance: Google Search: optimizing for generative AI. Documentation reviewed November 11, 2026. Provider behavior can change; recheck the linked sources when implementing.
Store implementation references
Use the official Shopify Storefront API and WooCommerce Store API documentation for platform-specific authentication, supported operations and write protections. Do not assume a generic example applies unchanged to your store.
Put one improvement to work
Start with this task: Find a suitable product variant, explain the current price and return conditions, and stop before adding it to a cart. Save the baseline, make one justified improvement and keep the retest evidence. Use the result to choose the next useful change.
Sources and editorial notes
- llms.txt proposal and format
- Google Search: optimizing for generative AI
- Google web.dev: agent-friendly website UX
- W3C: labeling form controls
- OpenAPI specification
- Model Context Protocol architecture
- OWASP API Security Project
- Shopify Storefront API
- WooCommerce Store API
This guide combines primary-source documentation with original implementation advice and a fictional worked example. It is not a report of measured client results, guaranteed traffic or earnings. The examples use reserved example.com URLs and must be adapted and verified before deployment.
Ecommerce Growth Coaching · $750 / month
Two working sessions per month on one growth priority, with written next steps and one agreed artifact review.
Start with a free fit conversation. A written scope and payment instructions come before paid work begins.