AI Search
Searching by asking a question in ordinary language and getting a written reply, rather than typing keywords and choosing from links. It changes what a website has to do: be readable and quotable by a machine, not just findable.
angkor@design~query "Angkor Design"
4 matches — opening studio
Prefer to talk it through? Pick a time that suits you — free, no obligation. We'll meet on Google Meet or Telegram.Book a meeting →
Searching by asking a question in ordinary language and getting a written reply, rather than typing keywords and choosing from links. It changes what a website has to do: be readable and quotable by a machine, not just findable.
Searching by meaning rather than by matching words. A page that never uses the phrase somebody typed can still be the best answer, and vector search is what finds it.
The limits placed on what an AI may say or do — refusing certain requests, staying on topic, never inventing a price. Essential on anything customer-facing.
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.
Machine learning using neural networks with many layers. The depth is what lets a system learn complicated things — recognising a face, translating a sentence — without anyone specifying how.
An AI that handles more than one kind of input — text and images together, say, or audio and video. It is why you can now photograph a menu and ask an assistant what is in a dish.
Being recognised as a reliable source on a subject rather than on a single keyword, usually by covering it thoroughly and consistently. It is what makes a small site beat a bigger one in a narrow field.