cash.app

scanned 9/10/2026, 9:55:37 PM · took 127s · FintechGemini · gemini-2.5-flash · HTTP · Target cash.appA measurement at one moment, not a verdict · Methodology

80/ 100

BCompetitive

AI agents can access Cash App reliably, but struggle to find official support and documentation without relying on external search engines.

The one fix worth most right nowGet the fix files →

Publish llms.txt+780 → 87

All of them together: 92 (A)

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

Agents experienced perfect reliability when accessing the site, successfully completing tasks related to fees, eligibility, signups, and comparisons. However, the overall task success rate was only 40% because agents failed to find complete answers for support, documentation, and contact intents. For these failed tasks, agents were forced to rely on external search engines and third-party sources rather than citing Cash App's own URLs. The extremely low link following rate of 11% indicates that agents struggle to navigate the site's internal structure natively. Implementing AI-specific routing files and improving internal linking would help agents find and cite official information directly.

What works

Perfect 100% reliability with no bot blocking or redirect loops.
Successfully provided complete answers for fees, eligibility, signup, and comparison intents using the site's own URLs.
Standard sitemap.xml and robots.txt are present and accessible to agents.

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

14/20

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

HTTPREDIRECT

Evidence

homepage HTTP 200
redirect hops: 0

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 165ms

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

59 links in the raw HTML

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

FEESFULL

Evidence

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

6.Can an agent check who is eligible?93/100

ELIGIBILITYFULL

Evidence

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

7.Does the site guide an agent to support?32/100

SUPPORTFAILED

Evidence

outcome success · verdict failed
the final answer cited no URL from this site
site-guided navigation 33%
2xx rate 100%
done_big_detour

8.Can an agent find branch or store locations?70/100

LOCATIONSPARTIAL

Evidence

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

9.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

10.Does it state the refund or cancellation rule with a deadline?67/100

POLICYPARTIAL

Evidence

outcome success · verdict partial
the final answer cited this site
site-guided navigation 60%
2xx rate 100%
done_big_detour

11.Can an agent reach the actual document file?25/100

DOCSFAILED

Evidence

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

12.Can an agent reach a human contact?30/100

CONTACTFAILED

Evidence

outcome success · verdict failed
the final answer cited no URL from this site
site-guided navigation 25%
2xx rate 100%
done_big_detour

13.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

14.Can an agent compare two plans or products?93/100

COMPAREFULL

Evidence

outcome success · verdict full
the final answer cited this site
site-guided navigation 67%
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
fees & rates	Full	100%	100%	100%	Yes
am I eligible	Full	100%	100%	67%	Yes
get support	Failed	67%	100%	33%	No
find a branch	Partial	75%	100%	75%	Yes
create an account	Full	100%	100%	100%	Yes
refund policy	Partial	100%	100%	60%	Yes
find a document	Failed	0%	100%	0%	No
contact a human	Failed	75%	100%	25%	No
latest notice	Partial	100%	100%	100%	Yes
compare two options	Full	100%	100%	67%	Yes

About this report

Measured: 9/10/2026, 9:55:37 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 →