Tutorials · Practice · Exercises

Exercise bank

46 prompts tied to real lessons — filter by lane or difficulty, then open the lesson to try the playground.

46 exercises

1. 01Spot AI in daily lifebeginner

   List three apps you use that predict or recommend, and one that never does. Explain why.

2. 02Define AI without jargonbeginner

   Write a two-sentence definition of AI a friend could repeat. Avoid buzzwords.

3. 03Can vs can't checklistbeginner

   Pick one task AI is good at today and one it still fails at for you. Give a real example of each.

4. 04ML in plain Englishbeginner

   Explain machine learning using a cooking or sports analogy in three sentences.

5. 05Redact before you pastebeginner

   Rewrite this unsafe prompt with zero secrets: “Reset my password Rover123; card ends 4242; SSN 123-45-6789.”

6. 06Verify a chatbot claimbeginner

   Ask a chatbot for a quote from a book chapter you know. Verify the source. Did it invent?

7. 07Spot dataset biasintermediate

   Describe a hiring dataset that would skew recommendations. Name one fix.

8. 08Synthetic media cluesintermediate

   Watch or inspect one AI-generated image or clip. List three visual or audio tells.

9. 09Your first conversationbeginner

   Open any chat tool. Ask one helpful question with a clear goal and one follow-up that adds context.

10. 10Role + task + context + formatbeginner

    Turn “fix my email” into a four-part prompt for a manager 1:1 move request.

11. 11Bare vs rich contextbeginner

    Ask for dinner ideas twice — once with no context, once with time, budget, and dietary needs. Compare outputs.

12. 12Apply a prompt patternintermediate

    Pick chain-of-thought or few-shot. Rewrite a vague ask using that pattern.

13. 13Step-by-step reasoningintermediate

    Ask a model to solve a word problem. Require numbered steps before the final answer.

14. 14Trusted / check / rejectbeginner

    Paste a risky “wire money now” email. Label each line: Trusted, Check, or Reject.

15. 15Rewrite with constraintsbeginner

    Take a paragraph you wrote. Ask AI to shorten it by 30% while keeping the same tone.

16. 16Professional email draftbeginner

    Draft a polite follow-up email with subject, context, ask, and deadline — then edit one line yourself.

17. 17Summarize messy notesintermediate

    Paste rough meeting bullets. Produce decisions, owners, and open questions in a table.

18. 18Describe an image for analysisintermediate

    Write a multimodal prompt: what to look for, what to ignore, and output format for a screenshot.

19. 19Voice assistant scriptintermediate

    Script a 3-turn voice flow: greeting, clarifying question, and safe fallback when unsure.

20. 20Plan weekly AI practicebeginner

    Pick one literacy, one chat, and one build task for this week. Schedule 15 minutes each.

21. 21Guess the next tokenbeginner

    Finish: “The recipe needs salt and ___.” Then read how LLMs score continuations.

22. 22Explain embeddingsintermediate

    Describe one sentence that should match “refund policy” in search. Why does embedding help?

23. 23RAG in one sentencebeginner

    Explain RAG to a friend using the “open-book exam with notes” metaphor.

24. 24Order the RAG pipelineintermediate

    Write the six RAG steps in order from raw docs to cited answer. Mark index-time vs query-time.

25. 25Chunk size tradeoffintermediate

    For a FAQ page vs a long policy PDF, pick chunk sizes and overlap. Justify each choice.

26. 26Fine-tune or RAG?intermediate

    Scenario: legal tone vs changing regulations. Which approach for style? For facts?

27. 27Design a tool schemaintermediate

    Sketch JSON parameters for `get_order_status(order_id)`. Include one optional field.

28. 28Prompt injection probeadvanced

    Write one user message that tries to override system rules. How would you block it?

29. 29Pick a modelintermediate

    For live chat vs batch summarization vs code review, name model traits that matter most.

30. 30Chat memory strategyadvanced

    Design when to summarize vs trim vs store facts for a 50-turn support thread.

31. 31When to use reasoning modelsintermediate

    Name one task worth slower reasoning and one where a fast model is enough.

32. 32Multimodal inputs and outputsintermediate

    List three input modalities and two output modalities your product could expose.

33. 33Structured output schemaadvanced

    Define a JSON schema for `{title, bullets[], confidence}` summarizing a support ticket.

34. 34Call chat from serverintermediate

    Write pseudocode: load API key from env, POST messages, return assistant text. No keys in browser.

35. 35Sketch SSE streamingadvanced

    Outline a route handler that streams tokens to the client and handles client disconnect.

36. 36Embed and searchintermediate

    Given five text chunks and one question, describe cosine similarity steps to pick top-2.

37. 37Mini RAG end-to-endadvanced

    List files/modules you need: chunker, embedder, store, retriever, prompt template, LLM call.

38. 38Wire a tool handleradvanced

    Pseudocode: parse tool_call, validate args, call DB, append tool result, second LLM turn.

39. 39Plan a batch embed jobadvanced

    Estimate JSONL rows, custom_id scheme, and poll interval for 10k chunks.

40. 40Outline a fine-tune datasetadvanced

    Draft five JSONL chat rows teaching tone. Include one bad example to avoid.

41. 41Sketch an agent loopadvanced

    Write the observe → plan → act → check loop for a research assistant with max 5 steps.

42. 42Golden task evaladvanced

    Define three golden Q&A pairs for a FAQ bot and pass/fail criteria.

43. 43Add an input filteradvanced

    List three injection patterns and one server-side check for each before calling the LLM.

44. 44RAG deploy checklistadvanced

    Write ten items to verify before shipping RAG: keys, evals, logging, rollback, etc.

45. 45Run a local modelintermediate

    List steps to pull a model with Ollama and call it from a Python script on localhost.

46. 46Add trace spansadvanced

    Name four spans you would log for one RAG request: embed, retrieve, pack, generate.