MCP (Model Context Protocol)
An open standard for connecting AI assistants to outside tools and data in a consistent way. It matters to businesses because it is how an assistant might one day query your booking system directly.
angkor@design~query "Angkor Design"
4 matches — opening studio
An open standard for connecting AI assistants to outside tools and data in a consistent way. It matters to businesses because it is how an assistant might one day query your booking system directly.
Training a model on unlabelled data and letting it find structure by itself — grouping similar customers, say, without being told what the groups are.
Visitors who arrive from an AI assistant rather than a search engine. Usually small in number and unusually well-qualified, because they clicked after reading a recommendation.
How well a system can show why it reached a decision. It matters most where the decision affects somebody — a loan, a diagnosis, a job application — and “the model said so” is not an answer.
A standard location, always under /.well-known/, where machines look for information about a site — security contacts, API catalogues, agent details. Putting files there means they can be found without being linked.
An answer engine replies to a question with a written answer instead of a list of links. ChatGPT, Perplexity and Google’s AI Overviews are all answer engines. The old question was “do we rank?”; the new one is “are we the answer?”
An AI that does things rather than only answering — browsing a site, filling a form, completing a booking. It is why websites are starting to be judged on whether a machine can use them, not only read them.