/Interview

AI interview hacks · Lesson 1 of 6 · 15 min

Never ask AI for the answer

Study with AI

Part 1Basics

Pasting a problem into a chatbot gives you a clean solution in ten seconds. Reading it feels like learning. Then the same problem comes back a week later and your mind goes blank.

The reason is simple. Interviews test recall under pressure, and you only build recall by struggling to produce the answer yourself. Reading skips that struggle.

So give the AI one job: hand over the smallest possible hint, and only after you've made a real attempt. Think of a ladder where each step gives away a little more, and you have to try again to reach the next one.

Words you need

Hint ladder
A fixed order of help: a question first, then a nudge, then the technique's name, then pseudocode for one step.
Attempt
What you tried and where it broke, written down. It's the price of the next hint.
System prompt
Instructions that set the rules for a whole conversation. Here, the rule is: don't give me the solution.

A worked example

Meera is our example candidate, and she's made up. She has an interview loop in 21 days: an AI-allowed coding round, an LLM screen, a RAG design round and an evals round. Every lesson in these paths follows her preparation.

On day two, Meera gets stuck on a sliding window problem. Her first instinct is to ask for the answer. Instead, she writes two sentences about what she tried, and asks for one question that shows where her reasoning breaks. The question is about what happens when the window shrinks, and she finds the bug herself.

Part 2The question

How do you get unstuck with AI and still learn the problem?

By the end of this lesson, you should be able to:

  • Set up a chat that won't give you the solution
  • Climb the ladder one step at a time
  • Say when to stop and read a real solution

Part 3In detail

Step by step

  1. Try for 15 minutes first. Paul Epps suggests about this long before asking. The number isn't magic, but it forces a real attempt.
  2. Write your attempt down. Two sentences: what you tried, and what went wrong. Often this alone unblocks you.
  3. Ask for level 1. A single question that exposes the flaw, with no hint.
  4. Try again before climbing. Change something first. A repeat of the same attempt earns nothing.
  5. Stop at level 4. If pseudocode for one step doesn't help, read a full solution. Then rebuild it tomorrow from memory.

Why the rule lives in code

Rules you hold in your head get dropped when you're tired. The small function below enforces them: no attempt, no hint. You can paste its prompt into any assistant, or wire it into the coach you build in the last path.

Prompts to copy

The ground rules

Paste this at the start of a practice chat.

You are coaching me through a coding interview problem.
Never write the solution, corrected code, or solution pseudocode.
Ask one question at a time.
Give more revealing help only when I ask for the next level, and only after I describe a new attempt.
Don't tell me I'm right unless I've explained why.

Attack my approach

Use this after you pick an approach, before you code.

Here is my approach to the problem: [approach].
Ask the one question most likely to expose a flaw in it. Don't give your own answer. Wait for my reply, then ask the next one.

The code, explained

This is real code, and our tests run it, including the buggy versions, to prove the bugs are real.

The rule that keeps you honest

This is the whole ladder as code. It answers one question: have you earned the next hint?

HintLadder.tsTypeScript
1/** No new attempt means no new hint. That rule stops the slide into reading answers. */2export function nextHint(state: LadderState | null, attempt: string): LadderState | { refused: string } {3  const tried = attempt.trim();4  if (tried.length < 40) return { refused: "Write what you tried and where it broke, in a sentence or two." };5  if (!state) return { level: 0, lastAttempt: tried };6  if (tried === state.lastAttempt) return { refused: "That's the same attempt. Change something, then ask again." };7  if (state.level >= HINT_LEVELS.length - 1) return { refused: "Out of hints. Read a solution, then rebuild it tomorrow from memory." };8  return { level: state.level + 1, lastAttempt: tried };9}
9 linesUTF-8TypeScript
tried.length < 40
A rough test that you wrote something real. 'help' doesn't pass.
tried === state.lastAttempt
Asking again without changing anything earns nothing.
state.level >= HINT_LEVELS.length - 1
The ladder ends. After this, you read a solution and rebuild it tomorrow.

Tested by npm run test:modules.

The prompt it builds

The same rules, as text you can send to any assistant.

HintLadder.tsTypeScript
1export function hintPrompt(problem: string, state: LadderState): string {2  return [3    "You are coaching me through a coding interview problem.",4    "Never write the solution, corrected code, or solution pseudocode.",5    `Problem:\n${problem}`,6    `What I tried:\n${state.lastAttempt}`,7    `Your task: ${HINT_LEVELS[state.level]}`,8  ].join("\n\n");9}
9 linesUTF-8TypeScript
Never write the solution
Goes in every request, because long chats drift away from earlier rules.
state.lastAttempt
Hints depend on context. Without your attempt, the model can only guess where you're stuck.
HINT_LEVELS[state.level]
Asks for one level of help and no more.

Tested by npm run test:modules.

What can go wrong

Asking for 'just a small hint' repeatedly
Five small hints add up to the solution. Each one must follow a new attempt.
The AI ignores your rules
Long chats drift. Start a fresh chat for each problem and paste the ground rules again.
Never reading a solution
Staying stuck for hours teaches nothing either. Level 4 has a clear exit.

Part 4Questions and answers

Answer out loud first, then open each one.

Why does reading an AI solution feel like learning when it isn't?
Understanding a solution you're reading is much easier than producing one from nothing. Interviews test producing it, and only struggling to recall builds that.
What earns the next hint?
A new attempt: you changed something and can say what broke. Asking again doesn't count.
When should you read the full solution?
After the last level still leaves you stuck. Then close it and rebuild the solution from memory the next day.

Part 5Going further

Drill: One problem, four rungs at most (30 min)

  1. Pick a medium problem you haven't seen.
  2. Try it for 15 minutes with no help.
  3. Use the ground rules prompt and climb only as far as you need.
  4. Write down which level you needed. Lower is better next time.

Keep the fundamentals fresh with the critical basics.

Who says so

Checked in November 2026. Vendors and individuals often report what candidates told them, so treat their details as reports.

Next: the hack that trains the skill AI rounds depend on most, which is reading code and spotting what's wrong.

Next: Bug planting →
AI Engineer · AI interview hacks