mi.com
Gemini · gemini-2.5-flash · HTTP · Target https://www.mi.com/de/store/A measurement at one moment, not a verdict · MethodologyStrict bot protection is blocking AI agents from accessing the site, resulting in a 0% task success rate and forcing reliance on third-party search results.
Put the main links in the raw HTML+3013 → 43 · grade F → D
All of them together: 85 (A)
Projected from the audit record. After fixing, re-run the task or re-measure to confirm.
AI agents attempting to navigate mi.com were immediately blocked by HTTP 403 Forbidden errors. This firewall or bot protection policy prevents agents from reading the homepage, robots.txt, or any standard discovery files. Because they could not access the site directly, agents were forced to rely on external search engines for all 10 tested tasks. Consequently, the site failed to provide authoritative, on-site answers, and 7 out of 10 tasks did not cite the brand's own URLs at all. Until access is granted, the site remains invisible to AI assistants.
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 403
- redirect hops: 1
Evidence
- homepage returned HTTP 403 to a declared bot
- /robots.txt absent
- First byte after 209ms
Evidence
- /llms.txt — absent (HTTP 403)
- /llms-full.txt — absent (HTTP 403)
- /sitemap.xml — absent (HTTP 403)
- /sitemap-index.xml — absent (HTTP 403)
- /sitemap_index.xml — absent (HTTP 403)
- /robots.txt — absent (HTTP 403)
Evidence
- 0 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 0%
- done_small_detour
Evidence
- outcome success · verdict failed
- the final answer cited no URL from this site
- site-guided navigation 0%
- 2xx rate 0%
- done_big_detour
Evidence
- outcome success · verdict failed
- the final answer cited this site
- site-guided navigation 0%
- 2xx rate 0%
- done_small_detour
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 0%
- 2xx rate 0%
- done_big_detour
Evidence
- outcome success · verdict partial
- the final answer cited this site
- site-guided navigation 0%
- 2xx rate 0%
- done_big_detour
Evidence
- outcome success · verdict failed
- the final answer cited no URL from this site
- site-guided navigation 0%
- 2xx rate 0%
- 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 failed
- the final answer cited no URL from this site
- site-guided navigation 0%
- 2xx rate 0%
- 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 failed
- the final answer cited no URL from this site
- site-guided navigation 0%
- 2xx rate 0%
- done_big_detour
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 | 100% | 0% | 0% | No | |
| shipping & returns | Failed | 100% | 0% | 0% | No | |
| is it available | Failed | 0% | 0% | 0% | Yes | |
| get support | Partial | 100% | 0% | 0% | Yes | |
| contact a human | Partial | 100% | 0% | 0% | Yes | |
| refund policy | Failed | 100% | 0% | 0% | No | |
| compare two options | Failed | 40% | 100% | 0% | No | |
| latest notice | Failed | 100% | 0% | 0% | No | |
| find a branch | Failed | 50% | 100% | 0% | No | |
| create an account | Failed | 100% | 0% | 0% | No |
About this report
- Measured
- 9/17/2026, 3:38:25 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.