johnlewis.com

scanned 9/26/2026, 12:10:24 AM · took 121s · HouseholdGemini · gemini-2.5-flash · HTTP · Target johnlewis.comA measurement at one moment, not a verdict · Methodology
75/ 100
CFair

AI agents can access the site, but struggle to complete core e-commerce tasks natively due to missing structural files and heavy reliance on external search.

The one fix worth most right nowGet the fix files →

Publish llms.txt+775 → 82

All of them together: 94 (A)

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

AI agents successfully accessed johnlewis.com without encountering bot blocks, but achieved only a 30% task success rate. The absence of foundational routing files like `/llms.txt` and `/sitemap.xml` left agents without a clear map of the site's structure. Consequently, agents were forced to rely heavily on external search engines to find information for six out of ten tasks. While tasks like shipping, contact, and signup were fully successful, critical e-commerce intents like checking stock and finding the latest products failed entirely. Providing machine-readable pathways and ensuring key pages are discoverable via direct HTML links will significantly improve agent performance.

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
8/20
Access
24/30
Navigation
30/30
Completion
13/20
HTTPREDIRECT

Evidence

  • homepage HTTP 200
  • redirect hops: 1
ROBOTSBOT

Evidence

  • robots.txt contains Disallow rules
  • First byte after 572ms
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

  • 134 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 20%
  • 2xx rate 60%
  • done_small_detour
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
SUPPORTPARTIAL

Evidence

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

Evidence

  • outcome success · verdict full
  • the final answer cited 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 100%
  • 2xx rate 100%
  • done_unaided
COMPAREPARTIAL

Evidence

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

Evidence

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

Evidence

  • outcome success · verdict full
  • the final answer cited this site
  • site-guided navigation 83%
  • 2xx rate 100%
  • done_unaided

WebMCP — what the site declares about itself

Not checked

Check failed: page.goto: net::ERR_HTTP2_PROTOCOL_ERROR at https://johnlewis.com/ Call log: - navigating to "https://johnlewis.com/", waiting until "domcontentloaded"

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 & returnsFull100%60%20%Yes
is it availableFailed0%0%0%No
get supportPartial100%100%0%Yes
contact a humanFull100%100%0%Yes
refund policyPartial100%100%100%Yes
compare two optionsPartial100%100%100%Yes
latest noticeFailed0%100%0%No
find a branchPartial100%100%100%Yes
create an accountFull100%100%83%Yes

About this report

Measured
9/26/2026, 12:10:24 AM 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.

Diagnosingjohnlewis.com

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