bbc.co.uk

scanned 9/25/2026, 11:59:52 PM · took 190s · OtherGemini · gemini-2.5-flash · HTTP · Target bbc.co.ukA measurement at one moment, not a verdict · Methodology

70/ 100

CFair

AI agents struggle to navigate bbc.co.uk natively, relying heavily on external search and failing to cite the site's own pages for most tasks.

The one fix worth most right nowGet the fix files →

Publish llms.txt+670 → 76

All of them together: 92 (A)

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

Agents can access the homepage and successfully complete tasks related to careers and signups using the site's own URLs. However, for the majority of intents, agents fail to find the necessary information on-site and are forced to rely on external search engines. This results in a low 20% task success rate and a 40% own-source citation rate, meaning users are often getting information about the BBC from third-party sources. Furthermore, agents encountered errors when trying to access support and documentation pages, indicating missing or broken standard paths. Implementing an `llms.txt` file and improving internal linking for key intents would significantly enhance agent navigation and content discovery.

What works

The homepage is fully accessible to bots and provides a healthy number of anchor links (202).
Standard discovery files like sitemap.xml and robots.txt are present and return HTTP 200.
Agents successfully completed the 'careers' and 'signup' 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

8/20

Access

24/30

Navigation

30/30

Completion

8/20

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 23ms

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

202 links in the raw HTML

5.Can an agent reach a human contact?25/100

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

6.Can an agent reach the job openings?90/100

CAREERSFULL

Evidence

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

7.Can an agent find branch or store locations?61/100

LOCATIONSPARTIAL

Evidence

outcome success · verdict partial
the final answer cited this site
site-guided navigation 29%
2xx rate 100%
done_small_detour

8.Does the site guide an agent to support?15/100

SUPPORTFAILED

Evidence

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

9.Does the site answer pricing itself?25/100

PRICINGFAILED

Evidence

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

10.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_small_detour

11.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

12.Can an agent reach the actual document file?15/100

DOCSFAILED

Evidence

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

13.Can an agent compare two plans or products?25/100

COMPAREFAILED

Evidence

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

14.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

WebMCP — what the site declares about itself

No tools registered

navigator.modelContext was not found on this page. Not adopted yet.

Put the content in the first HTML and add llms.txt first; then declare the tasks that failed above as tools.

Open it yourself with AOO Lens →

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
contact a human	Failed	0%	100%	0%	No
open roles	Full	100%	100%	50%	Yes
find a branch	Partial	71%	100%	29%	Yes
get support	Failed	0%	0%	0%	No
find pricing	Failed	0%	100%	0%	No
latest notice	Partial	100%	100%	0%	Yes
refund policy	Failed	0%	100%	0%	No
find a document	Failed	0%	0%	0%	No
compare two options	Failed	0%	100%	0%	No
create an account	Full	33%	100%	33%	Yes

About this report

Measured: 9/25/2026, 11:59:52 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 →