statefarm.com

scanned 9/10/2026, 9:51:54 PM · took 123s · InsuranceGemini · gemini-2.5-flash · HTTP · Target statefarm.comA measurement at one moment, not a verdict · Methodology

75/ 100

CFair

State Farm's website is accessible to AI agents, but poor internal navigation and missing AI-specific files cause agents to fail 80% of tasks and rely heavily on external search.

The one fix worth most right nowGet the fix files →

Publish llms.txt+675 → 81

All of them together: 93 (A)

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

AI agents can successfully access the State Farm homepage and read standard discovery files like robots.txt and sitemap.xml. However, the overall task success rate is only 20%, with agents failing to complete 8 out of 10 tasks. Because the site lacks an llms.txt file and has a 0% link following score, agents are forced to guess URLs or rely on external search engines to find information. This results in agents frequently encountering errors on guessed paths and failing to cite State Farm's own URLs in 60% of the tested intents. Ultimately, users querying AI about State Farm are likely receiving information sourced from third parties rather than the official site.

What works

The homepage is fully accessible to bots with a standard HTTP 200 response and no bot-blocking mechanisms detected.
Standard discovery files like robots.txt and sitemap.xml are present and accessible (HTTP 200).
Agents successfully completed 'signup' and 'contact' tasks while citing the site's own URLs.

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

24/30

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?70/100

ROBOTSBOT

Evidence

robots.txt contains Disallow rules
First byte after 134ms

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

LLMS.TXTSITEMAPROBOTS

Evidence

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

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

HTMLSSR

Evidence

108 links in the raw HTML

5.Does the site state its fees or rates as numbers?35/100

FEESFAILED

Evidence

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

6.Can an agent check who is eligible?28/100

ELIGIBILITYFAILED

Evidence

outcome success · verdict failed
the final answer cited no URL from this site
site-guided navigation 67%
2xx rate 0%
done_big_detour

7.Does the site guide an agent to support?25/100

SUPPORTFAILED

Evidence

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

8.Can an agent find branch or store locations?25/100

LOCATIONSFAILED

Evidence

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

9.Does the site guide an agent through signing up?87/100

SIGNUPFULL

Evidence

outcome success · verdict full
the final answer cited this site
site-guided navigation 33%
2xx rate 100%
done_big_detour

10.Does it state the refund or cancellation rule with a deadline?25/100

POLICYFAILED

Evidence

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

11.Can an agent reach the actual document file?70/100

DOCSPARTIAL

Evidence

outcome success · verdict partial
the final answer cited this site
site-guided navigation 75%
2xx rate 100%
done_small_detour

12.Can an agent reach a human contact?82/100

CONTACTFULL

Evidence

outcome success · verdict full
the final answer cited this site
site-guided navigation 33%
2xx rate 50%
done_big_detour

13.Can an agent reach the latest notice, with its date?55/100

LATESTPARTIAL

Evidence

outcome success · verdict partial
the final answer cited this site
site-guided navigation 0%
2xx rate 100%
done_big_detour

14.Can an agent compare two plans or products?15/100

COMPAREFAILED

Evidence

outcome success · verdict failed
the final answer cited no URL from this site
site-guided navigation 0%
2xx rate 0%
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
fees & rates	Failed	100%	0%	100%	No
am I eligible	Failed	100%	0%	67%	No
get support	Failed	67%	100%	0%	No
find a branch	Failed	50%	100%	0%	No
create an account	Full	100%	100%	33%	Yes
refund policy	Failed	33%	100%	0%	No
find a document	Partial	100%	100%	75%	Yes
contact a human	Full	100%	50%	33%	Yes
latest notice	Partial	100%	100%	0%	Yes
compare two options	Failed	25%	0%	0%	No

About this report

Measured: 9/10/2026, 9:51:54 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 →