Crack it with AI, the best way · Lesson 2 of 3 · 15 min
The daily loop and your plan
Part 1Basics
A good day of preparation has four parts: recall what you learned before, learn one thing, practise it under time pressure, and log what went wrong.
AI fits differently in each part. It quizzes you during recall, explains during learning, stays out of the way while you practise except for hints, then grades you and helps write cards at the end.
The plan itself is simple arithmetic. Your time goes where a round counts most and you score lowest. Some weeks you'll be surprised by what it says.
Words you need
- Recall
- Producing an answer from memory, which is what strengthens it. Rereading doesn't do this.
- Spaced review
- Seeing a card again just as you're starting to forget it.
- Mock
- A full, timed round with no pauses, as close to the real thing as you can get.
A worked example
Meera enters her scores with 21 days to go. The plan gives RAG and evals the most days, with coding next, and only a little to behavioural, which she was tempted to polish because it's comfortable. Every fourth training day is a full mock. The final five days have AI off.
Part 2The question
What should each day look like, and how do you use AI across it?
By the end of this lesson, you should be able to:
- Generate a plan from your scores
- Run the four-part day
- Adjust the plan after each mock
Part 3In detail
Step by step
- Recall (15 minutes). Do your due cards from the revise page. No notes.
- Learn (30 minutes). One lesson, or one concept. Ask AI to explain it, then explain it back to the AI and have it find the holes.
- Practise (60 minutes). One timed task. Hint ladder only.
- Review (15 minutes). Have AI grade your work. Add your misses to the ledger and make cards.
- Update the plan weekly. New scores change the numbers.
Short on time?
Thirty minutes a day still works: 10 minutes of cards, 20 minutes on one drill. Doing that every day beats one huge weekend. If you have under 5 days, skip planning and drill your weakest round.
Explain it back
The strongest learning prompt is reversed. You explain a concept, and the AI asks about whatever you got wrong or left out. It shows you what you don't know far faster than reading does.
Prompts to copy
Explain it back
Use this during the learning block.
I'll explain [concept] to you as if you were a junior engineer. Don't correct me while I'm explaining. When I'm finished, ask me 3 questions about what I got wrong, left vague or skipped. Then tell me what a senior interviewer would still want to hear.
Mock interviewer
Answer as if it's real. Don't pause the clock.
You are interviewing me for [role] at a company like [type of company]. This round is [round]. It lasts [minutes] minutes. Ask one question at a time, and keep replies short. Probe weak answers rather than moving on. Don't teach me or give answers during the round. When I say 'end', score me 1 to 5 on problem solving, code quality, verification and communication, quoting my words as evidence.
The code, explained
This is real code, and our tests run it, including the buggy versions, to prove the bugs are real.
Sharing out your days
Time goes where a round counts most and you're weakest.
1/** More time goes where a round counts most and you score lowest. Largest remainder keeps the total exact. */2export function allocateDays(goals: RoundGoal[], days: number): Record<string, number> {3 const need = goals.map((g) => ({ round: g.round, need: g.weight * Math.max(6 - g.score, 1) }));4 const total = need.reduce((a, b) => a + b.need, 0);5 const shares = need.map((n) => ({ ...n, exact: (n.need / total) * days, whole: Math.floor((n.need / total) * days) }));6 let left = days - shares.reduce((a, b) => a + b.whole, 0);7 [...shares]8 .sort((a, b) => b.exact - b.whole - (a.exact - a.whole) || a.round.localeCompare(b.round))9 .forEach((s) => {10 if (left > 0) {11 s.whole++;12 left--;13 }14 });15 return Object.fromEntries(shares.map((s) => [s.round, s.whole]));16}g.weight * Math.max(6 - g.score, 1)- Even a strong round gets some time, so it never drops to zero need.
b.exact - b.whole- Largest remainder: leftover days go to the rounds that lost the most to rounding.
Tested by npm run test:modules.
Building the schedule
Baseline, training, a stretch with AI off, then rest.
1export function buildPlan(goals: RoundGoal[], days: number): PlanDay[] {2 if (days < 5) throw new Error("under 5 days, skip the plan and drill your weakest round");3 const aiOff = Math.max(2, Math.round(days * 0.25)); // the last quarter proves it stuck4 const trainDays = days - 2 - aiOff; // day 1 is the baseline and the last day is rest5 const counts = allocateDays(goals, trainDays);6 const queue = [...goals].sort((a, b) => a.score - b.score).map((g) => g.round);7 const plan: PlanDay[] = [{ day: 1, kind: "baseline", focus: "One timed mock per round, AI off. Write down your scores." }];8 for (let i = 0, d = 2; i < trainDays; i++, d++) {9 const round = queue.find((r) => counts[r] > 0) ?? queue[0];10 counts[round]--;11 queue.push(queue.splice(queue.indexOf(round), 1)[0]);12 plan.push({ day: d, kind: i % 4 === 3 ? "mock" : "train", focus: round });13 }14 for (let i = 0; i < aiOff; i++) plan.push({ day: plan.length + 1, kind: "ai-off", focus: queue[i % queue.length] });15 plan.push({ day: days, kind: "rest", focus: "Light card review only. Sleep." });16 return plan;17}Math.round(days * 0.25)- The last quarter runs with AI off, to prove that the skill stuck.
i % 4 === 3- Every fourth training day is a full mock.
queue.push(queue.splice- Rotates rounds, so you don't do five days of one thing.
Tested by npm run test:modules.
What can go wrong
- Practising only what's comfortable
- That's why the plan is arithmetic: it doesn't care what you enjoy.
- Endless reading
- If a day had no timed practice, it barely counts.
- Never updating the plan
- Your scores should change. If they don't, change the method.
Part 4Questions and answers
Answer out loud first, then open each one.
Why start with recall, not new material?
Why does a low score on a low-weight round get less time?
Part 5Going further
Drill: Make your plan (15 min)
- Write each round with its weight and your baseline score.
- Work out the days, by hand or with the code here.
- Put the mocks and AI-off days on a calendar.
- Do tomorrow's recall tonight, to set it up.
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.
- How I used AI to practice for my Meta interview Individual
- The best AI prompts for coding interview practice Individual, October 2026
Next: the step most people skip. Checking that it's you who improved, and not just the tool.