Glossary
Plain-English definitions of the terms we use across ClassDigital's services and articles.
AI workflow
A repeatable sequence of steps in which an AI model handles part of a business task, such as drafting a reply, classifying an enquiry or summarising a document, with defined inputs, outputs and a human check where needed.
Automation
Software that performs a manual, rule-based task on its own, such as sending a lead follow-up, copying data between systems or generating a weekly report, so staff time goes to work that needs judgement.
Custom AI solution
An AI tool built around one specific business bottleneck, for example a customer support assistant, a lead qualifier or a content generator, rather than an off-the-shelf product configured for everyone.
Website rescue
A technical audit and repair of a broken, slow or poorly built website. It fixes the faults that cost enquiries (broken forms, slow loads, poor mobile layout, missing HTTPS) without rebuilding from scratch where that isn't needed.
Vibecoded website
A site produced mostly by prompting an AI coding tool. These often look finished but hide problems in structure, accessibility, security, performance and search visibility that need a human engineer to fix.
Technical audit
A structured review of a website or workflow that lists what is broken, what is slowing it down and what to fix first, ordered by business impact.
Lead follow-up
The process of responding to a new enquiry quickly and consistently. It is one of the most common things ClassDigital automates, because slow replies lose work.
Agent readability
How easily AI agents and crawlers can read and understand a website, through clean HTML, structured data, markdown versions of pages, a sitemap and an llms.txt file.
llms.txt
A plain-text file at the root of a website that summarises the site and links to its most important pages in a format that language models can read directly.
Structured data (JSON-LD)
Machine-readable markup embedded in a page that states what the page is about, such as the business, its services, FAQs and breadcrumb trail, so search engines and AI systems can interpret it accurately.
Handover
The final project stage: the finished build is deployed, and the client receives full documentation and access, so nothing depends on ClassDigital to keep running.