starbucks.com

scanned 9/10/2026, 9:17:21 PM · took 132s · Food & BeverageGemini · gemini-2.5-flash · HTTP · Target starbucks.comA measurement at one moment, not a verdict · Methodology

82/ 100

BCompetitive

AI agents can access Starbucks.com and handle basic inquiries, but fail to retrieve first-party data for stock and latest products due to poor internal routing.

The one fix worth most right nowGet the fix files →

Publish llms.txt+782 → 89

All of them together: 98 (A)

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

Agents successfully accessed the site without encountering bot blocks, achieving an 82% on-site discovery rate. They easily navigated to standard pages like support, contact, and signup using native links. However, the overall task success rate is only 40% because agents struggled with dynamic or specific queries like stock, latest products, and policies. For these tasks, agents were forced to rely on external search bridges, and in the case of stock and latest items, they failed to cite Starbucks' own URLs entirely. The lack of an llms.txt file leaves agents guessing at URLs, which leads to dead ends and reliance on third-party information.

What works

The site is fully accessible to AI agents with a 200 HTTP status and no bot blocking.
Support, contact, and signup intents succeed natively with 100% reliability and on-site discovery.
Standard crawler files like sitemap.xml and robots.txt are present and properly configured.

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

27/30

Navigation

30/30

Completion

13/20

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?90/100

ROBOTSBOT

Evidence

no bot blocking observed
Cookie consent banner: TrustArc
First byte after 215ms

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

92 links in the raw HTML

5.Does the site answer pricing itself?75/100

PRICINGPARTIAL

Evidence

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

6.Does the site answer shipping and returns itself?65/100

SHIPPINGPARTIAL

Evidence

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

7.Can an agent tell whether an item is available?15/100

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

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

SUPPORTFULL

Evidence

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

9.Can an agent reach a human contact?100/100

CONTACTFULL

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?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 compare two plans or products?80/100

COMPAREFULL

Evidence

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

12.Can an agent reach the latest notice, with its date?25/100

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

13.Can an agent find branch or store locations?55/100

LOCATIONSPARTIAL

Evidence

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

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

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
find pricing	Partial	100%	100%	100%	Yes
shipping & returns	Partial	100%	100%	50%	Yes
is it available	Failed	0%	0%	0%	No
get support	Full	100%	100%	100%	Yes
contact a human	Full	100%	100%	100%	Yes
refund policy	Partial	100%	100%	0%	Yes
compare two options	Full	67%	100%	0%	Yes
latest notice	Failed	50%	100%	0%	No
find a branch	Partial	100%	100%	0%	Yes
create an account	Full	100%	100%	100%	Yes

About this report

Measured: 9/10/2026, 9:17:21 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 →