Supervised Learning
Training a model on examples that are already labelled with the right answer. It is the most common approach when you know exactly what you want the system to produce.
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 →
Training a model on examples that are already labelled with the right answer. It is the most common approach when you know exactly what you want the system to produce.
A saved set of prompts a team reuses so results stay consistent between people. The simplest way to stop everyone reinventing the same instructions badly.
An AI navigating a website on somebody’s behalf: finding the price, checking availability, sometimes buying. Sites that rely on hover menus and unlabelled buttons are hard for an agent to use.
Marking AI-generated content so it can be identified later, often invisibly. Part of the same effort as provenance, and equally early.
Turning written text into spoken audio. Modern voices are convincing enough to be used for real narration, which raises its own questions about disclosure.
When a model gets worse over time because the world moved on and it did not. A pricing or demand model trained two years ago quietly stops matching how customers behave now.
Markup for ratings and reviews, including who wrote them. It feeds the star ratings in search results, and gives an assistant something concrete to cite about your reputation.