airbnb.com

scanned 9/10/2026, 10:18:46 PM · took 194s · Booking SiteGemini · gemini-2.5-flash · HTTP · Target airbnb.comA measurement at one moment, not a verdict · Methodology

69/ 100

DNeeds work

AI agents cannot complete any tasks using only Airbnb's internal navigation, forcing them to rely on third-party search results for critical information like pricing and fees.

The one fix worth most right nowGet the fix files →

Publish llms.txt+669 → 75

All of them together: 93 (A)

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

Agents successfully accessed the homepage but failed to complete a single task using only the site's internal pathways. Because foundational machine-readable files like /llms.txt and /sitemap.xml are missing, agents were forced to guess URLs, resulting in frequent 404 errors. Consequently, for critical intents like pricing, fees, and comparisons, agents abandoned the site entirely and relied on external search engines. This means users querying AI about Airbnb's fees or latest updates are receiving answers based on third-party data rather than Airbnb's own content.

What works

The homepage is accessible to AI agents without bot-blocking (HTTP 200).
Agents successfully discovered and cited first-party URLs for booking, support, contact, policy, and documentation 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.

Discovery

7/20

Access

23/30

Navigation

30/30

Completion

9/20

1.Can an agent get into the site at all?90/100

HTTPREDIRECT

Evidence

homepage HTTP 200
redirect hops: 1

2.Does the site let agents through rather than block them?60/100

ROBOTSBOT

Evidence

robots.txt contains Disallow rules
Cookie consent banner: OneTrust
First byte after 443ms

3.Does it publish machine-readable guidance?15/100

LLMS.TXTSITEMAPROBOTS

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

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

HTMLSSR

Evidence

151 links in the raw HTML

5.Does the site explain how to book or visit?71/100

BOOKINGPARTIAL

Evidence

outcome success · verdict partial
the final answer cited this site
site-guided navigation 80%
2xx rate 100%
done_unaided

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?65/100

SUPPORTPARTIAL

Evidence

outcome success · verdict partial
the final answer cited this site
site-guided navigation 50%
2xx rate 100%
done_big_detour

9.Can an agent reach a human contact?68/100

CONTACTPARTIAL

Evidence

outcome success · verdict partial
the final answer cited this site
site-guided navigation 67%
2xx rate 100%
done_big_detour

10.Does it state the refund or cancellation rule with a deadline?68/100

POLICYPARTIAL

Evidence

outcome success · verdict partial
the final answer cited this site
site-guided navigation 67%
2xx rate 100%
done_big_detour

11.Can an agent compare two plans or products?0/100

COMPAREFAILED

Evidence

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

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?20/100

LATESTFAILED

Evidence

outcome success · verdict failed
the final answer cited no URL from this site
site-guided navigation 0%
2xx rate 50%
done_big_detour

14.Can an agent reach the actual document file?65/100

DOCSPARTIAL

Evidence

outcome success · verdict partial
the final answer cited this site
site-guided navigation 50%
2xx rate 100%
done_big_detour

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	Partial	100%	100%	80%	Yes
find pricing	Failed	0%	0%	0%	No
fees & rates	Failed	0%	0%	0%	No
get support	Partial	100%	100%	50%	Yes
contact a human	Partial	100%	100%	67%	Yes
refund policy	Partial	100%	100%	67%	Yes
compare two options	Failed	0%	0%	0%	No
find a branch	Failed	0%	0%	0%	Yes
latest notice	Failed	100%	50%	0%	No
find a document	Partial	100%	100%	50%	Yes

About this report

Measured: 9/10/2026, 10:18:46 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 →