Conversational Search
Searching by asking a full question, often as a follow-up to a previous one, the way you would ask a person. It favours pages that answer plainly over pages stuffed with keywords.
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 full question, often as a follow-up to a previous one, the way you would ask a person. It favours pages that answer plainly over pages stuffed with keywords.
The text, images or code a model learned from. It shapes everything the model knows and every bias it carries, and it is why what your website said two years ago may still be what an assistant repeats.
Markup for an item you sell: name, price, currency, availability, condition. Without it an assistant reading your shop has to guess the price from the page, and sometimes guesses wrong.
The unit an AI reads and writes in — roughly three quarters of a word. Models are priced and limited by tokens, which is why very long documents cost more and sometimes get truncated.
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.
What somebody actually wants when they type a query: to learn, to compare, to buy, or to find a specific site. Matching it matters more than matching the words.
When a system produces unfair results because its training data reflected an unfair world. It matters commercially as well as ethically: a biased model makes confidently wrong decisions about real people.