coca-cola.com

scanned 9/10/2026, 9:14:59 PM · took 150s · Food & BeverageGemini · gemini-2.5-flash · HTTP · Target coca-cola.comA measurement at one moment, not a verdict · Methodology
62/ 100
CFair

While AI agents can access the Coca-Cola website, the absence of structural files and poor internal linking causes a 70 percent failure or partial success rate across standard tasks.

The one fix worth most right nowGet the fix files →

Remove challenge and login walls+862 → 70

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 homepage without being blocked, but they struggle to navigate the site effectively. The absence of foundational routing files like /llms.txt and /sitemap.xml forces agents to guess URLs or rely heavily on external search engines. While tasks like shipping, support, and signup succeeded, agents failed completely on 5 out of 10 intents, including stock, contact, and product comparisons. Furthermore, for half of the tasks, agents did not cite Coca-Cola's own URLs, meaning users are receiving information from third-party sources rather than the brand itself.

What works

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
6/20
Access
16/30
Navigation
30/30
Completion
10/20
HTTPREDIRECT

Evidence

  • homepage HTTP 200
  • redirect hops: 2
ROBOTSBOT

Evidence

  • robots.txt contains Disallow rules
  • A CAPTCHA is holding the content back: reCAPTCHA
  • Cookie consent banner: OneTrust
  • First byte after 298ms
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
HTMLSSR

Evidence

  • 32 links in the raw HTML
PRICINGPARTIAL

Evidence

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

Evidence

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

Evidence

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

Evidence

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

Evidence

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

Evidence

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

Evidence

  • outcome success · verdict failed
  • the final answer cited no URL from this site
  • site-guided navigation 50%
  • 2xx rate 100%
  • done_big_detour
LATESTFAILED

Evidence

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

Evidence

  • outcome success · verdict failed
  • the final answer cited no URL from this site
  • site-guided navigation 75%
  • 2xx rate 100%
  • done_small_detour
SIGNUPFULL

Evidence

  • outcome success · verdict full
  • the final answer cited this site
  • site-guided navigation 40%
  • 2xx rate 80%
  • done_small_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

TaskVerdictOwn-site shareRequest successFollowed guidanceCited own site
find pricingPartial100%100%0%Yes
shipping & returnsFull60%100%80%Yes
is it availableFailed0%0%0%No
get supportFull100%100%0%Yes
contact a humanFailed33%100%0%No
refund policyPartial100%100%0%Yes
compare two optionsFailed0%100%50%No
latest noticeFailed0%100%0%No
find a branchFailed0%100%75%No
create an accountFull100%80%40%Yes

About this report

Measured
9/10/2026, 9:14:59 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 →

Open the full report

Free, no account. Leave your details and the evidence for each task, the findings, the recommendations and PDF export open right away.

Diagnosingcoca-cola.com

By opening the report you agree to the Terms of Service.