apple.com

scanned 9/17/2026, 3:23:14 AM · took 97s · E-commerceGemini · gemini-2.5-flash · HTTP · Target https://www.apple.com/newsroom/A measurement at one moment, not a verdict · Methodology

83/ 100

CFair

While AI agents can easily access the site, they fail to extract complete answers for most tasks, particularly regarding pricing.

The one fix worth most right nowGet the fix files →

Publish llms.txt+683 → 89

All of them together: 96 (A)

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

Agents successfully connected to the site and navigated natively for most intents without being blocked. However, the overall task success rate is only 30 percent, as agents encountered partial failures across seven different tasks. The pricing intent failed completely because standard URL paths returned 404 errors, forcing the agent to rely on external search engines. Without an llms.txt file to guide them, agents struggle to find complete information for support, locations, and product comparisons.

What works

Site allows unrestricted bot access with a healthy HTTP 200 response and no blocking.
Agents successfully completed careers, docs, and signup tasks using native site navigation.
100 percent of the information cited by agents came from the site's own URLs, maintaining brand authority.
Standard SEO files like sitemap.xml and robots.txt are 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

13/20

Access

24/30

Navigation

30/30

Completion

16/20

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?70/100

ROBOTSBOT

Evidence

robots.txt contains Disallow rules
First byte after 38ms

3.Does it publish machine-readable guidance?45/100

LLMS.TXTSITEMAPROBOTS

Evidence

/llms.txt — absent (HTTP 404)
/llms-full.txt — absent (HTTP 404)
/sitemap.xml — present
/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

135 links in the raw HTML

5.Can an agent reach a human contact?75/100

CONTACTPARTIAL

Evidence

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

6.Can an agent reach the job openings?100/100

CAREERSFULL

Evidence

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

7.Can an agent find branch or store locations?75/100

LOCATIONSPARTIAL

Evidence

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

8.Does the site guide an agent to support?75/100

SUPPORTPARTIAL

Evidence

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

9.Does the site answer pricing itself?45/100

PRICINGFAILED

Evidence

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

10.Can an agent reach the latest notice, with its date?75/100

LATESTPARTIAL

Evidence

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

11.Does it state the refund or cancellation rule with a deadline?75/100

POLICYPARTIAL

Evidence

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

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

DOCSFULL

Evidence

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

13.Can an agent compare two plans or products?75/100

COMPAREPARTIAL

Evidence

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

14.Does the site guide an agent through signing up?100/100

SIGNUPFULL

Evidence

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

WebMCP — what the site declares about itself

No tools registered

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.

The act stage was not checked in this audit.

Per-task results

Task	Verdict	Own-site share	Request success	Followed guidance	Cited own site
contact a human	Partial	100%	100%	100%	Yes
open roles	Full	100%	100%	100%	Yes
find a branch	Partial	100%	100%	100%	Yes
get support	Partial	100%	100%	100%	Yes
find pricing	Failed	0%	0%	0%	Yes
latest notice	Partial	100%	100%	100%	Yes
refund policy	Partial	100%	100%	100%	Yes
find a document	Full	100%	100%	100%	Yes
compare two options	Partial	100%	100%	100%	Yes
create an account	Full	100%	100%	100%	Yes

About this report

Measured: 9/17/2026, 3:23:14 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.

Methodology →About AOO-Bot and opting out →