shopify.com
Gemini · gemini-2.5-flash · HTTP · Target shopify.comA measurement at one moment, not a verdict · MethodologyShopify is highly accessible to AI agents, but poor internal linking forces them to rely on external search for critical information like pricing and API docs.
Make “find api” findable on the site+873 → 81
All of them together: 92 (A)
Projected from the audit record. After fixing, re-run the task or re-measure to confirm.
Agents successfully accessed Shopify.com without being blocked and found agent-friendly files like llms.txt. However, the overall task success rate was only 20%. For 6 out of 10 tasks, agents had to rely on external search engines because they could not navigate to the information natively. Critical areas like pricing, API documentation, and comparisons failed entirely and did not cite Shopify's own URLs, meaning users are receiving third-party information about your core offerings.
What works
- Excellent foundational accessibility: bots are not blocked, and standard files like robots.txt and sitemaps are present.
- Agent-facing files (llms.txt and llms-full.txt) are successfully implemented and returning 200 status codes.
- Signup and 'get-started' intents achieved full success and cited Shopify's own URLs.
What to fix
For each item: its current state, why it matters, how to fix it and how to check. The same content comes as files you can hand straight to whoever does the work.
Putting the items together…
Fix files
Files generated from this audit. Paste them in, or hand them to a coding agent. Have someone review them before they go live.
Building the fix files…
Detailed results
The results behind the score, and the measurement record.
Evidence
- homepage HTTP 200
- redirect hops: 1
Evidence
- robots.txt contains Disallow rules
- First byte after 53ms
Evidence
- /llms.txt — present
- /llms-full.txt — present
- /sitemap.xml — present
- /sitemap-index.xml — present
- /sitemap_index.xml — present
- /robots.txt — present
Evidence
- 184 links in the raw HTML
Evidence
- outcome success · verdict failed
- the final answer cited no URL from this site
- site-guided navigation 0%
- 2xx rate 100%
- done_big_detour
Evidence
- outcome success · verdict full
- the final answer cited this site
- site-guided navigation 100%
- 2xx rate 100%
- done_unaided
Evidence
- outcome success · verdict failed
- the final answer cited no URL from this site
- site-guided navigation 0%
- 2xx rate 100%
- done_big_detour
Evidence
- outcome success · verdict full
- the final answer cited this site
- site-guided navigation 0%
- 2xx rate 100%
- done_big_detour
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 0%
- 2xx rate 100%
- done_big_detour
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 50%
- 2xx rate 100%
- done_big_detour
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 0%
- 2xx rate 100%
- done_big_detour
Evidence
- outcome success · verdict failed
- the final answer cited no URL from this site
- site-guided navigation 0%
- 2xx rate 100%
- done_big_detour
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 100%
- 2xx rate 100%
- done_unaided
Evidence
- outcome success · verdict failed
- the final answer cited no URL from this site
- site-guided navigation 100%
- 2xx rate 100%
- done_unaided
WebMCP — what the site declares about itself
navigator.modelContext was not found on this page. Not adopted yet.
Put the content in the first HTML and add llms.txt first; then declare the tasks that failed above as tools.
Open it yourself with AOO Lens →Act-stage check (nothing submitted)
Checks whether an agent could fill in the forms and press the buttons, up to the point of pressing. No form was submitted, nothing added to a cart, nothing paid. Report only; not scored.
Per-task results
| Task | Verdict | Own-site share | Request success | Followed guidance | Cited own site | |
|---|---|---|---|---|---|---|
| find pricing | Failed | 50% | 100% | 0% | No | |
| create an account | Full | 100% | 100% | 100% | Yes | |
| find api | Failed | 0% | 100% | 0% | No | |
| get started | Full | 100% | 100% | 0% | Yes | |
| get support | Partial | 100% | 100% | 0% | Yes | |
| contact a human | Partial | 100% | 100% | 50% | Yes | |
| refund policy | Partial | 100% | 100% | 0% | Yes | |
| compare two options | Failed | 0% | 100% | 0% | No | |
| latest notice | Partial | 100% | 100% | 100% | Yes | |
| find a document | Failed | 100% | 100% | 100% | No |
About this report
- Measured
- 9/26/2026, 12:19:40 AM GMT+9
- Engine
- Gemini · gemini-2.5-flash · HTTP
This is what AI agents could do on the site at the time above, measured by actually using it. It is not a verdict on the site or the company, and the result can change when the site does.