Learn · 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. 01

    Spot AI in daily life

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

    beginner
    Review lesson
  2. 02

    Define AI without jargon

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

    beginner
    Review lesson
  3. 03

    Can vs can't checklist

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

    beginner
    Review lesson
  4. 04

    ML in plain English

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

    beginner
    Review lesson
  5. 05

    Redact before you paste

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

    beginner
    Review lesson
  6. 06

    Verify a chatbot claim

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

    beginner
    Review lesson
  7. 07

    Spot dataset bias

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

    intermediate
    Review lesson
  8. 08

    Synthetic media clues

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

    intermediate
    Review lesson
  9. 09

    Your first conversation

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

    beginner
    Review lesson
  10. 10

    Role + task + context + format

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

    beginner
    Review lesson
  11. 11

    Bare vs rich context

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

    beginner
    Review lesson
  12. 12

    Apply a prompt pattern

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

    intermediate
    Review lesson
  13. 13

    Step-by-step reasoning

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

    intermediate
    Review lesson
  14. 14

    Trusted / check / reject

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

    beginner
    Review lesson
  15. 15

    Rewrite with constraints

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

    beginner
    Review lesson
  16. 16

    Professional email draft

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

    beginner
    Review lesson
  17. 17

    Summarize messy notes

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

    intermediate
    Review lesson
  18. 18

    Describe an image for analysis

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

    intermediate
    Review lesson
  19. 19

    Voice assistant script

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

    intermediate
    Review lesson
  20. 20

    Plan weekly AI practice

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

    beginner
    Review lesson
  21. 21

    Guess the next token

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

    beginner
    Review lesson
  22. 22

    Explain embeddings

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

    intermediate
    Review lesson
  23. 23

    RAG in one sentence

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

    beginner
    Review lesson
  24. 24

    Order the RAG pipeline

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

    intermediate
    Review lesson
  25. 25

    Chunk size tradeoff

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

    intermediate
    Review lesson
  26. 26

    Fine-tune or RAG?

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

    intermediate
    Review lesson
  27. 27

    Design a tool schema

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

    intermediate
    Review lesson
  28. 28

    Prompt injection probe

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

    advanced
    Review lesson
  29. 29

    Pick a model

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

    intermediate
    Review lesson
  30. 30

    Chat memory strategy

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

    advanced
    Review lesson
  31. 31

    When to use reasoning models

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

    intermediate
    Review lesson
  32. 32

    Multimodal inputs and outputs

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

    intermediate
    Review lesson
  33. 33

    Structured output schema

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

    advanced
    Review lesson
  34. 34

    Call chat from server

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

    intermediate
    Review lesson
  35. 35

    Sketch SSE streaming

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

    advanced
    Review lesson
  36. 36

    Embed and search

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

    intermediate
    Review lesson
  37. 37

    Mini RAG end-to-end

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

    advanced
    Review lesson
  38. 38

    Wire a tool handler

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

    advanced
    Review lesson
  39. 39

    Plan a batch embed job

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

    advanced
    Review lesson
  40. 40

    Outline a fine-tune dataset

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

    advanced
    Review lesson
  41. 41

    Sketch an agent loop

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

    advanced
    Review lesson
  42. 42

    Golden task eval

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

    advanced
    Review lesson
  43. 43

    Add an input filter

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

    advanced
    Review lesson
  44. 44

    RAG deploy checklist

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

    advanced
    Review lesson
  45. 45

    Run a local model

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

    intermediate
    Review lesson
  46. 46

    Add trace spans

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

    advanced
    Review lesson