B5 · Generative AI and Conversational Assistants

Module Review and Assessment

This review brings together the key ideas of Generative AI and Conversational Assistants: the types of generative AI, how it creates content, what a large language model is, how to prompt and follow up, how to use it for learning, hallucinations and fact-checking, spotting generated content, and questions of ownership and credit, followed by a scored quiz.

10 min Beginner Jump to the activity

What you need: Nothing. This page starts from the beginning, with no programming and no formulas.

Definition

Could you now explain to a friend how a chatbot writes, why it can be wrong, and how to use it well?

This review brings together the key ideas of Generative AI and Conversational Assistants: the types of generative AI, how it creates content, what a large language model is, how to prompt and follow up, how to use it for learning, hallucinations and fact-checking, spotting generated content, and questions of ownership and credit, followed by a scored quiz.

In simple words

Read the recap table, try the matching activity, then take the quiz. Each answer comes with an explanation. If you miss one, go back to that topic and read it again.

Why it matters

Generative AI is the kind of AI you are most likely to use directly, every day. The habits from this module, clear prompts, careful checking and honest credit, are what separate a skilled user from a careless one.

How it works

IdeaIn one line
TypesText, images, audio, video and programs; multimodal tools combine them
How it createsLearns patterns in training, then builds new content step by step
Language modelsPredict the next piece of text; fluent, and not a fact-checker
PromptsRole, context, task, format and limits
Follow-upImprove answers through specific requests; ask for evidence, not agreement
Learning with AITry first; use it for hints, quizzes and feedback
HallucinationsConfident, fluent and false; commonest with exact details and sources
Fact-checkingSIFT: stop, investigate, find better coverage, trace
Generated contentClues are fading; check the origin
Thinking partnerThink with it, not through it
Ownership and creditThe law is unsettled; honesty is always required

Try it yourself

Match each problem to its remedy

What should you do in each situation?

  • The answer is too general
  • The chatbot cites a book you cannot find
  • A shocking photo arrives with no source
  • You must write an essay to learn a topic
  • You used AI to help with a project

Common mistakes

  • Treating a chatbot as a search engine that returns checked facts.
  • Believing content because it is fluent, detailed or realistic.
  • Letting the tool do the thinking that you needed to do yourself.

Check yourself

Question 1

1. Which of these is NOT a type of generative AI output?

Question 2

2. How does a text generator produce a sentence?

Question 3

3. An image generator starts from…

Question 4

4. What is a knowledge cut-off?

Question 5

5. Which part of a prompt tells the tool about your situation?

Question 6

6. You say "I think you're wrong" and the chatbot changes a correct answer. What is this tendency called?

Question 7

7. Which use of AI best supports learning?

Question 8

8. What is a hallucination?

Question 9

9. What does the S in SIFT stand for?

Question 10

10. What is the most reliable way to judge a suspicious image?

Question 11

11. Handing in an AI-written essay as your own is…

Summary

  • Generative AI builds new content from learned patterns and does not check for truth.
  • Clear prompts and specific follow-ups get better results; verification stays your job.
  • Use it to think better, give honest credit, and check before you believe or share.

Finished reading?

Sources: UNESCO: Guidance for generative AI in education and research · AI4K12: Five Big Ideas in AI