Legal/CivicEnglish

How Company Register Intel is built

Visit Company Register Intel Company Register Intel in the collection

Measured numbers

Counted by the collection, not written by hand. A figure we cannot support is left out rather than shown as zero.

Pages: 400,023; 1st of 24 measured in Legal/Civic, by sitemap URLs
Page count over time: 160,000 → 400,023 pages measured, 30 Sep to 25 Oct
Languages: English
Deploys: 13 in the last 30 days; Last deploy 21 Oct 2026. From the public status feed
llms.txt: Published; llms.txt 6.9 KB · llms-full.txt 20.6 KB
Sitemap: Listed in robots.txt
Content last updated: 24 Oct 2026; As reported by the site itself

Tech and AI search

Read from the live site on 2026-10-23: its homepage, robots.txt and llms.txt. A line we could not read is left out.

Built with: Next.js; Read from the homepage markup
Structured data: WebSite; schema.org types on the homepage
AI crawler access: Allows all 11 major AI crawlers; From the site’s robots.txt
llms.txt link depth: 28 page links; Markdown links in the site’s llms.txt
Search: Search box on the homepage

How it is built, by role

The same roles apply across the whole collection. Nothing in this block is specific to this site; what the site says about itself is quoted word for word below it.

1
Edge network
Visitors reach a site through an edge layer: a content delivery network with a web application firewall in front of it.
2
Application host
The edge talks to an application host that serves the site and renders its pages.
3
Data
What the pages show comes from a relational database or, for a site pre-rendered at build time, from data files built into its release.
4
Scheduled measurement
The collection measures its sites on a schedule: content dates and site health nightly, page counts read from each site’s sitemap weekly. Every reading is kept with its date. A site too large to re-walk is not re-measured, and shows no trend.
5
Public status feed
A monitoring panel sends a signed report on uptime, deploys and backups once a day, and the Operations page publishes it. A figure on this page that comes from that report says so.

In the site's own words

Each passage is copied unaltered from a page the site publishes, with the address it was taken from and the date we took it. We add nothing between them.

“Plain-English financial-health intelligence read from the TEXT of UK Companies House accounts filings — going-concern doubt, audit opinions, auditor changes, director loans, covenant breaches — every flag backed by a verbatim quote from the filing.”

Source: companyregisterintel.com/llms-full.txt · retrieved 2026-10-24

“This site reads the TEXT: the independent auditor’s report, going-concern notes, related-party and director-loan disclosures, post-balance-sheet events.”

Source: companyregisterintel.com/llms-full.txt · retrieved 2026-10-24

“A language model extracts structured signals from each filing under a strict rule: every non-default finding must carry a quote copied verbatim from the filing, and that quote is verified character-for-character against the document (after unicode normalisation, on word boundaries, with negated boilerplate rejected).”

Source: companyregisterintel.com/llms-full.txt · retrieved 2026-10-24

“Numbers shown come directly from the iXBRL tags in the filing (current period, dimension-free contexts), never from the language model.”

Source: companyregisterintel.com/llms-full.txt · retrieved 2026-10-24

“Signals carry the period they relate to and are retracted when a newer filing clears the condition.”

Source: companyregisterintel.com/llms-full.txt · retrieved 2026-10-24

“The page gives a distress score (0–100), a plain-English narrative, and each signal with the verbatim quote from the filing and a link to the source document at Companies House.”

Source: companyregisterintel.com/llms-full.txt · retrieved 2026-10-24