AI interview hacks · Lesson 5 of 6 · 10 min
Turn every miss into a card
Part 1Basics
Most people practise until they feel tired, without tracking what went wrong. So tomorrow's session is the same as today's, and the same mistakes come back.
A ledger fixes that. Each miss gets one row: the topic, the cause, a question, and an answer. The cause matters most. 'Failed two sum' tells you nothing, while 'didn't test empty input' describes a habit you can change.
AI helps twice here. It can read your mock and name the cause, and it can turn a miss into a clean flashcard. Spaced review then brings the card back just as you're about to forget.
Words you need
- Cause
- The habit behind the miss, in a few words: off by one, skipped clarifying, no test before moving on.
- Spaced repetition
- Reviewing at growing gaps, such as 1, 3 and 7 days. The revise page on this site does it for you.
- Half-life
- How long a miss takes to lose half its weight. Here, 7 days: old misses matter less unless they come back.
A worked example
After a week, Meera's ledger has 19 rows. The topics are all over the place, but one cause shows up six times: 'accepted AI output without running it'. That's the most useful thing she's learned all week, and no list of topics would have shown it.
Part 2The question
How do you stop making the same mistake in every mock?
By the end of this lesson, you should be able to:
- Log a miss with a real cause
- Find your weakest topic and your most repeated habit
- Export misses as flashcards
Part 3In detail
Step by step
- Log straight after each session. Two minutes, while you still remember.
- Name the cause, not the problem. Ask AI if you can't tell: 'What habit caused this?'
- Write one question per miss. One fact per card. Long cards don't get remembered.
- Start each day from the ledger. Practise your weakest topic first.
- Review the causes weekly. A repeated cause gets a rule, such as 'run it before I accept it'.
Spreadsheet first
A spreadsheet with four columns is enough. The code below shows what's worth calculating once you have rows: recent misses count more, and repeated causes stand out.
Prompts to copy
Turn a miss into a card
Check the answer yourself before you save it.
I got this wrong in practice: [problem and what I did] Reply with: 1) the habit that caused it, in under 6 words, 2) one flashcard question that tests the idea, not this exact problem, 3) an answer of at most 2 sentences. If you're unsure of a fact, say so.
The code, explained
This is real code, and our tests run it, including the buggy versions, to prove the bugs are real.
What the ledger tells you
Two views of the same rows: which topic is weak now, and which habit keeps coming back.
1/** Recent misses count more: a miss loses half its weight every 7 days. */2export function weakestTopics(misses: Miss[], now: number, halfLifeDays = 7): [string, number][] {3 const weight = new Map<string, number>();4 for (const m of misses) {5 const ageDays = Math.max(0, now - m.at) / DAY;6 weight.set(m.topic, (weight.get(m.topic) ?? 0) + 0.5 ** (ageDays / halfLifeDays));7 }8 return [...weight].map(([t, w]): [string, number] => [t, Math.round(w * 100) / 100]).sort((a, b) => b[1] - a[1] || a[0].localeCompare(b[0]));9}10 11/** If the same cause keeps coming back, that habit is worth more than any single topic. */12export function repeatedCauses(misses: Miss[], atLeast = 2): [string, number][] {13 const counts = new Map<string, number>();14 for (const m of misses) counts.set(m.cause, (counts.get(m.cause) ?? 0) + 1);15 return [...counts].filter(([, n]) => n >= atLeast).sort((a, b) => b[1] - a[1] || a[0].localeCompare(b[0]));16}0.5 ** (ageDays / halfLifeDays)- A miss loses half its weight every 7 days. A miss from today counts 1, and one from two weeks ago counts 0.25.
repeatedCauses- Counts causes without any decay, since a habit that keeps showing up matters however old the first case is.
Tested by npm run test:modules.
Exporting to flashcards
Anki imports tab-separated text, one card per line.
1/** Tab-separated lines that Anki can import. Tabs and line breaks inside a field would break a row. */2export function toAnki(misses: Miss[]): string {3 const clean = (s: string) => s.replace(/[\t\r\n]+/g, " ").trim();4 return misses.map((m) => `${clean(m.question)}\t${clean(m.answer)}\t${clean(m.topic)}`).join("\n");5}replace(/[\t\r\n]+/g, " ")- A stray tab or line break inside a field would split the row and scramble the card.
Tested by npm run test:modules.
What can go wrong
- Saving cards you never checked
- Models make confident errors. Check each card before it goes in your deck.
- Too many cards
- A 300-card backlog gets abandoned. Add only what you actually missed.
Part 4Questions and answers
Answer out loud first, then open each one.
Why log the cause separately from the topic?
Why make old misses count less?
Part 5Going further
Drill: Start your ledger (10 min)
- Open a spreadsheet with topic, cause, question, answer.
- Add your last three misses.
- Add your first card to the revise deck, or to Anki.
- Write the one rule your most common cause suggests.
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: where the line sits, and why the most viral hack of all is the one to avoid.