aircanada.com
Gemini · gemini-2.5-flash · HTTP · Target aircanada.comA measurement at one moment, not a verdict · MethodologyA critical redirect loop on the homepage blocks AI agents from entering directly, forcing them to rely on external search engines to find your content.
Put the main links in the raw HTML+3035 → 65 · grade D → C
All of them together: 93 (A)
Projected from the audit record. After fixing, re-run the task or re-measure to confirm.
AI agents attempting to access the site encountered an infinite redirect loop on the homepage, preventing direct navigation. Because they could not enter through the front door, agents had to rely heavily on external search engines to find deep links for 9 out of 10 tasks. While they successfully found information for basic tasks like booking and support, they failed or only partially succeeded on 6 tasks, including comparisons, pricing, and policies. Furthermore, the absence of standard agent-facing files like llms.txt and sitemap.xml leaves agents without a clear map of the site's structure. Consequently, the site surrenders control of its narrative to third-party search results.
What works
- Agents successfully completed tasks for booking, fees, support, and contact by discovering deep links.
- A sitemap_index.xml file is available and returns a 200 status.
- The site does not actively block bots, achieving a 90% own-source citation rate overall.
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 301
- redirect hops: 2
- https://aircanada.com/home/kr/ko/aco/flights
- https://www.aircanada.com/home/kr/ko/aco/flights
Evidence
- no bot blocking observed
- /robots.txt absent
- First byte after 1396ms
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 — present
- /robots.txt — absent (HTTP 404)
Evidence
- homepage HTML could not be parsed
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 full
- 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 full
- the final answer cited this site
- site-guided navigation 0%
- 2xx rate 75%
- 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 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
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 | |
|---|---|---|---|---|---|---|
| book an appointment | Full | 100% | 100% | 0% | Yes | |
| find pricing | Partial | 100% | 100% | 0% | Yes | |
| fees & rates | Full | 100% | 100% | 0% | Yes | |
| get support | Full | 100% | 100% | 0% | Yes | |
| contact a human | Full | 100% | 75% | 0% | Yes | |
| refund policy | Partial | 100% | 100% | 0% | Yes | |
| compare two options | Failed | 0% | 100% | 0% | No | |
| find a branch | Partial | 100% | 100% | 0% | Yes | |
| latest notice | Partial | 100% | 100% | 50% | Yes | |
| find a document | Partial | 100% | 100% | 0% | Yes |
About this report
- Measured
- 9/25/2026, 11:50:14 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.