bankofamerica.com

scanned 9/10/2026, 9:44:43 PM · took 153s · BankingGemini · gemini-2.5-flash · HTTP · Target bankofamerica.comA measurement at one moment, not a verdict · Methodology

79/ 100

CFair

While AI agents can access Bank of America's website, poor internal navigation forces them to rely on third-party search engines to answer customer queries.

The one fix worth most right nowGet the fix files →

Publish llms.txt+779 → 86

All of them together: 89 (C)

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

AI agents successfully accessed the site without being blocked, achieving a 95% on-site discovery rate. However, the overall task success rate was only 20%, with 8 out of 10 tasks resulting in partial failures. Agents struggled to navigate the site directly, as evidenced by a very low 11% link following rate. Consequently, agents had to rely heavily on external search bridges for almost all tasks, meaning third-party search results are dictating the answers provided about your services. The absence of an llms.txt file further prevents agents from understanding the site's structure directly.

What works

The site does not block AI agents, allowing basic access (HTTP 200).
Agents successfully cited the site's own URLs for 9 out of 10 intents.
A sitemap_index.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

12/20

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 32ms

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

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

HTMLSSR

Evidence

37 links in the raw HTML

5.Does the site state its fees or rates as numbers?53/100

FEESPARTIAL

Evidence

outcome success · verdict partial
the final answer cited this site
site-guided navigation 0%
2xx rate 80%
done_big_detour

6.Can an agent check who is eligible?87/100

ELIGIBILITYFULL

Evidence

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

7.Does the site guide an agent to support?55/100

SUPPORTPARTIAL

Evidence

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

8.Can an agent find branch or store locations?65/100

LOCATIONSPARTIAL

Evidence

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

9.Does the site guide an agent through signing up?85/100

SIGNUPFULL

Evidence

outcome success · verdict full
the final answer cited this site
site-guided navigation 25%
2xx rate 100%
done_big_detour

10.Does it state the refund or cancellation rule with a deadline?55/100

POLICYPARTIAL

Evidence

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

11.Can an agent reach the actual document file?55/100

DOCSPARTIAL

Evidence

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

12.Can an agent reach a human contact?55/100

CONTACTPARTIAL

Evidence

outcome success · verdict partial
the final answer cited this site
site-guided navigation 0%
2xx rate 100%
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?23/100

COMPAREPARTIAL

Evidence

outcome success · verdict partial
the final answer cited no URL from this site
site-guided navigation 0%
2xx rate 83%
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	Partial	80%	80%	0%	Yes
am I eligible	Full	100%	100%	33%	Yes
get support	Partial	100%	100%	0%	Yes
find a branch	Partial	100%	100%	50%	Yes
create an account	Full	100%	100%	25%	Yes
refund policy	Partial	100%	100%	0%	Yes
find a document	Partial	100%	100%	0%	Yes
contact a human	Partial	100%	100%	0%	Yes
latest notice	Partial	100%	100%	0%	Yes
compare two options	Partial	67%	83%	0%	No

About this report

Measured: 9/10/2026, 9:44:43 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 →