AI at work

The vocabulary behind the AI products your company is buying. · ~18 minutes

  1. Embedding: Turning words or documents into a list of numbers so that similar meanings end up close together.
  2. Vector Database: A database that finds things by similar meaning instead of exact words.
  3. Retrieval-Augmented Generation (RAG): Letting the AI look things up in your documents before it answers.
  4. Fine-Tuning: Giving an already-trained AI extra training on specific examples to specialise it.
  5. Tool Use: Letting an AI use other software, such as a calculator, search engine or calendar.
  6. AI Agent: An AI that doesn't just answer, but takes actions step by step to complete a goal.
  7. Responsible AI: Building and using AI in ways that are fair, safe, transparent and respectful of people.
🔎esc