bell.ca
Gemini · gemini-2.5-flash · HTTP · Target bell.caA measurement at one moment, not a verdict · MethodologyAI agents can access bell.ca, but missing structural files and poor internal linking force them to rely on external search engines, resulting in a low 20% task success rate.
Publish llms.txt+775 → 82
All of them together: 90 (C)
Projected from the audit record. After fixing, re-run the task or re-measure to confirm.
Agents experienced perfect reliability when accessing the domain, encountering no bot blocks and finding a healthy number of links on the homepage. However, the lack of machine-readable maps like llms.txt and sitemap.xml severely hindered native navigation. Agents were forced to use external search engines to find information for 7 out of 10 tasks, leading to partial or complete failures in 8 areas. Notably, for recent news, agents failed to cite the site entirely, relying instead on third-party sources to answer user queries.
What works
- 100% site reliability with no bot blocking detected.
- High own-source citation rate (90%) across most intents.
- Native navigation succeeded for locations, pricing, and compare intents.
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
- Cookie consent banner: OneTrust
- First byte after 715ms
Evidence
- /llms.txt — absent (HTTP 404)
- /llms-full.txt — absent (HTTP 404)
- /sitemap.xml — absent (HTTP 404)
- /sitemap-index.xml — absent (HTTP 404)
- /sitemap_index.xml — absent (HTTP 404)
- /robots.txt — present
Evidence
- 119 links in the raw HTML
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 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 100%
- 2xx rate 100%
- done_unaided
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 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 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 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 full
- the final answer cited this site
- site-guided navigation 0%
- 2xx rate 100%
- 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 | |
|---|---|---|---|---|---|---|
| contact a human | Partial | 100% | 100% | 0% | Yes | |
| open roles | Full | 100% | 100% | 0% | Yes | |
| find a branch | Partial | 100% | 100% | 100% | Yes | |
| get support | Partial | 100% | 100% | 0% | Yes | |
| find pricing | Partial | 100% | 100% | 100% | Yes | |
| latest notice | Failed | 0% | 100% | 0% | No | |
| refund policy | Partial | 100% | 100% | 0% | Yes | |
| find a document | Failed | 100% | 100% | 0% | Yes | |
| compare two options | Partial | 100% | 100% | 100% | Yes | |
| create an account | Full | 100% | 100% | 0% | Yes |
About this report
- Measured
- 9/25/2026, 11:56:35 PM 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.