Skip to content

Week 4 of 6 · 2.5-3 hours

Text AI, Chatbots, and Recommendations

See how AI handles language and suggestions — from keyword chatbots to text prediction to the feeds that shape what you see.

Big question: How does AI work with language and suggestions — and when should we question what it tells or shows us?

By the end of this week

  • Build a rule-based chatbot using keywords, intents, a decision tree, and a fallback.
  • Explain how a language model predicts the likely next piece of text from a prompt.
  • Explain why fluent AI output is not the same as true or correct output.
  • Audit how recommendations use similarity and feedback, and how they form filter bubbles.

Loading your progress…

  1. Build a Rule-Based ChatbotDesign a chatbot the old-fashioned way — with keywords, intents, and a decision tree — and discover why it needs a fallback for everything it wasn't built to handle.
  2. How Language Models Predict TextLook inside the AI behind autocomplete and chat assistants: it breaks text into pieces and predicts the likely next piece — which sounds fluent but is not the same as being true.
  3. Build and Question RecommendationsSee how recommendation systems use similarity and your feedback to suggest what's next — and question how the same system can trap you in a filter bubble.