AIML Rounds

QUIZ

Prompting

8 questions on Prompting, from 8 lessons. Pick an answer in your head, then open it.

On the roadmap for: AI Engineering, ML Engineering.

  1. Question 1 of 8

    Where should stable instructions go in a long production prompt, and why?

    1. A. At the end, so the model reads them last and remembers them best
    2. B. At the start, before changing content, so caching works
    3. C. Anywhere: position makes no difference
    4. D. Repeated after every paragraph of the prompt
    View answer

    ✓ B. At the start, before changing content, so caching works

    A stable prefix makes caching work and keeps behaviour consistent; put the changing parts after it.

    Lesson: Prompt Engineering Patterns

  2. Question 2 of 8

    You switch to a reasoning model but keep a prompt full of step-by-step instructions. What should change?

    1. A. Add even more detailed step-by-step instructions for it to follow exactly
    2. B. Give the goal and constraints; let it plan its own reasoning
    3. C. Ask it to think as little as possible
    4. D. Remove the goal so the model isn't constrained
    View answer

    ✓ B. Give the goal and constraints; let it plan its own reasoning

    Reasoning models plan internally, and rigid step lists can get in the way.

    Lesson: Prompting Reasoning Models

  3. Question 3 of 8

    Why can 'please return JSON' still produce broken output, and what fixes it reliably?

    1. A. Asking isn't enforcing; constrained decoding blocks bad tokens
    2. B. JSON is too long for models; switch to XML instead
    3. C. Set the temperature to zero, and then the output will always parse correctly
    4. D. Models can't reliably write braces and quotation marks
    View answer

    ✓ A. Asking isn't enforcing; constrained decoding blocks bad tokens

    Grammar-constrained decoding masks any token that would break the schema, so the output always parses.

    Lesson: Structured Output and Constrained Decoding

  4. Question 4 of 8

    A system prompt has grown to 20 rules, and the assistant keeps breaking one or another. What helps most?

    1. A. Write every rule in capital letters, so the model knows each one matters
    2. B. Remove the system prompt and rely on the model
    3. C. Group and prioritise rules, fix conflicts, test each one
    4. D. Add a 21st rule: always follow all other rules
    View answer

    ✓ C. Group and prioritise rules, fix conflicts, test each one

    Rules interact and compete for attention; clear structure plus tests show which ones fail and why.

    Lesson: System Prompts with Many Rules

  5. Question 5 of 8

    What does an automatic prompt optimiser need to work well?

    1. A. A good eval set and metric, since it optimises what you measure
    2. B. Nothing: it can tell good prompts from bad ones itself
    3. C. No examples at all, so the optimiser isn't biased by the ones you picked
    4. D. Only a bigger model to rewrite the prompts
    View answer

    ✓ A. A good eval set and metric, since it optimises what you measure

    With a weak metric it overfits or games the score, just like any optimiser.

    Lesson: Automatic Prompt Optimisation

  6. Question 6 of 8

    Your model doesn't know your company's current policies. Which tool fits best?

    1. A. Fine-tuning on the policy documents
    2. B. RAG, which supplies the knowledge at question time
    3. C. A higher temperature so it guesses more freely
    4. D. A longer system prompt that contains every policy in full
    View answer

    ✓ B. RAG, which supplies the knowledge at question time

    Knowledge gaps call for retrieval; behaviour and style gaps are where fine-tuning helps.

    Lesson: Prompt vs RAG vs Fine-Tuning: How to Choose

  7. Question 7 of 8

    You need the model to always answer in a specific tone and format, across thousands of cases. When does fine-tuning beat prompting?

    1. A. Never: prompting can always fix tone and format alone
    2. B. When prompts aren't consistent enough and you have examples
    3. C. When you have no examples of the behaviour you want
    4. D. When you need the model to learn new facts that keep changing week to week
    View answer

    ✓ B. When prompts aren't consistent enough and you have examples

    Fine-tuning changes behaviour; it is a poor way to add facts that change.

    Lesson: Prompt vs RAG vs Fine-Tuning: How to Choose

  8. Question 8 of 8

    A one-line prompt fix passed five spot checks but broke other cases in production. What process prevents this?

    1. A. A regression eval on every change, plus staged rollout
    2. B. More spot checks by hand before each release
    3. C. Never changing prompts once they seem to work
    4. D. Testing only the exact case that was reported to you
    View answer

    ✓ A. A regression eval on every change, plus staged rollout

    Prompts are code: changes need tests over many cases, not a handful of examples.

    Lesson: A Prompt Fix That Broke Production