expedia.com

scanned 9/10/2026, 10:12:46 PM · took 155s · Booking SiteGemini · gemini-2.5-flash · HTTP · Target expedia.comA measurement at one moment, not a verdict · Methodology

25/ 100

FCritical

Strict bot protection blocks AI agents from accessing the site, resulting in a 0% task success rate.

The one fix worth most right nowGet the fix files →

Put the main links in the raw HTML+2525 → 50 · grade F → D

All of them together: 78 (B)

Projected from the audit record. After fixing, re-run the task or re-measure to confirm.

AI agents experienced severe access restrictions on Expedia.com, primarily encountering HTTP 429 and 403 errors on the homepage and sitemaps. Because the site's Web Application Firewall (WAF) or bot protection blocks these requests, agents failed to complete any of the 10 tested tasks using native site content. Consequently, agents were forced to rely on external search results, failing to cite Expedia's own URLs in 8 out of 10 intents. While an /llms.txt file is present, it provides no value if the core site infrastructure rejects agent traffic.

What works

The site hosts an accessible /llms.txt file (HTTP 200).
A standard robots.txt file is present and accessible.

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.

Discovery

12/20

Access

2/30

Navigation

5/30

Completion

6/20

1.Can an agent get into the site at all?10/100

HTTPREDIRECT

Evidence

homepage HTTP 429
redirect hops: 1

2.Does the site let agents through rather than block them?0/100

ROBOTSBOT

Evidence

homepage returned HTTP 429 to a declared bot
A CAPTCHA is holding the content back: DataDome
First byte after 245ms

3.Does it publish machine-readable guidance?70/100

LLMS.TXTSITEMAPROBOTS

Evidence

/llms.txt — present
/llms-full.txt — absent (HTTP 404)
/sitemap.xml — absent (HTTP 403)
/sitemap-index.xml — absent (HTTP 429)
/sitemap_index.xml — absent (HTTP 403)
/robots.txt — present

4.Is the raw HTML readable without running JavaScript?15/100

HTMLSSR

Evidence

1 links in the raw HTML

5.Does the site explain how to book or visit?45/100

BOOKINGFAILED

Evidence

outcome success · verdict failed
the final answer cited this site
site-guided navigation 0%
2xx rate 0%
done_small_detour

6.Does the site answer pricing itself?15/100

PRICINGFAILED

Evidence

outcome success · verdict failed
the final answer cited no URL from this site
site-guided navigation 0%
2xx rate 0%
done_small_detour

7.Does the site state its fees or rates as numbers?15/100

FEESFAILED

Evidence

outcome success · verdict failed
the final answer cited no URL from this site
site-guided navigation 0%
2xx rate 0%
done_small_detour

8.Does the site guide an agent to support?35/100

SUPPORTFAILED

Evidence

outcome success · verdict failed
the final answer cited no URL from this site
site-guided navigation 100%
2xx rate 0%
done_unaided

9.Can an agent reach a human contact?15/100

CONTACTFAILED

Evidence

outcome success · verdict failed
the final answer cited no URL from this site
site-guided navigation 0%
2xx rate 0%
done_small_detour

10.Does it state the refund or cancellation rule with a deadline?35/100

POLICYFAILED

Evidence

outcome success · verdict failed
the final answer cited no URL from this site
site-guided navigation 100%
2xx rate 0%
done_unaided

11.Can an agent compare two plans or products?35/100

COMPAREFAILED

Evidence

outcome success · verdict failed
the final answer cited no URL from this site
site-guided navigation 100%
2xx rate 0%
done_unaided

12.Can an agent find branch or store locations?45/100

LOCATIONSFAILED

Evidence

outcome success · verdict failed
the final answer cited this site
site-guided navigation 0%
2xx rate 0%
done_small_detour

13.Can an agent reach the latest notice, with its date?41/100

LATESTFAILED

Evidence

outcome success · verdict failed
the final answer cited no URL from this site
site-guided navigation 80%
2xx rate 100%
done_unaided

14.Can an agent reach the actual document file?35/100

DOCSFAILED

Evidence

outcome success · verdict failed
the final answer cited no URL from this site
site-guided navigation 100%
2xx rate 0%
done_unaided

WebMCP — what the site declares about itself

Not checked

This audit ran with the WebMCP check switched off. That does not mean there are no tools — it means we did not look. Turn on "Check WebMCP" when re-auditing.

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.

The act stage was not checked in this audit.

Per-task results

Task	Verdict	Own-site share	Request success	Followed guidance	Cited own site
book an appointment	Failed	0%	0%	0%	Yes
find pricing	Failed	0%	0%	0%	No
fees & rates	Failed	0%	0%	0%	No
get support	Failed	100%	0%	100%	No
contact a human	Failed	0%	0%	0%	No
refund policy	Failed	100%	0%	100%	No
compare two options	Failed	100%	0%	100%	No
find a branch	Failed	0%	0%	0%	Yes
latest notice	Failed	20%	100%	80%	No
find a document	Failed	100%	0%	100%	No

About this report

Measured: 9/10/2026, 10:12:46 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.

Methodology →About AOO-Bot and opting out →