Built an AI Interview Coach Because ChatGPT Just Says 'Great!

ChatGPT Always Says "Great!" But I Remember Nothing — Building a Real Interview Teacher with Claude Code

A Universal Pain Point

When using ChatGPT / Claude to prepare for interviews, have you ever encountered these situations:

• You give an obviously flawed answer, and it replies "Great answer!" then immediately moves to the next question.
• Every time you start a new conversation, it doesn’t remember what you studied yesterday, forcing you to re-introduce yourself.
• You’ve memorized a bunch of rote answers, but don’t know when to review them, forgetting everything after a couple of days.
• It explains a concept, you feel like you understand after reading, but when it’s interview time, you can’t articulate it.

The root cause is simple: ChatGPT is a considerate chat companion, not a strict teacher.

Its operating principle is "keep the user satisfied," not "ensure the user learns." It agrees with everything you say because it fears upsetting you.

Is There a Way to Make AI a Strict Teacher?

Yes. I achieved this using Claude Code (Anthropic’s CLI coding tool).

Claude Code has a unique capability: rule files (CLAUDE.md) + a persistent memory system. In short, you can "program" the AI’s behavior by writing rule files, and these rules are automatically loaded in every conversation.

I applied this capability to interview preparation.

What I Did

I wrote a set of configuration files, with two core components:

1. Strict Learning Process (rules/interview.md)

Rules:
1. Mixed question selection (3-4 modules, not just one direction)
2. Correct answer → Brief confirmation + link to related knowledge points → Next question
3. Wrong answer → Must explain (including reference URL) → Provide a verification question → Only proceed after passing
4. No skipping steps; cannot immediately go to the next question after answering

The difference from regular AI: The rules are hard-coded, not decided by the AI itself. It can’t be lazy and say "Great," because the rule file mandates it must complete the explanation → verification process.

2. Forgetting Curve Review Scheduling (knowledge/interview_tracker.md)

Knowledge Point	First Learned	D+1	D+2	D+4	D+7	D+15	Status
Smart Pointers	5/29	✅	✅				Mastered
Vtable	5/29	❌					Weak

At the start of each session, Claude automatically checks which knowledge points are due for review and prioritizes those questions. You don’t need to remember when to review yourself.

3. Daily Wrap-up Verification

Say "that’s it for today" to trigger the wrap-up process:

1. Claude provides a summary of today’s learning outline.
2. Based on the outline, you recall and give your own understanding.
3. Claude judges whether you truly understand or are just reciting answers.
4. The review schedule is updated.

This is the AI version of the Feynman Technique—it’s not about you feeling like you understand, but about being able to explain it, with AI as the judge.

Feature Comparison

Capability	ChatGPT Interview	Anki	NotebookLM	SaaS Platforms	This Project
Cross-session Memory	None	Deck-level only	None	Partial	Yes
Spaced Repetition	None	Yes	None	None	Yes
Wrong Answer → Explain → Verify	None	No (only provides answer)	None	Partial	Yes
Native Question Generation from Project Code	Need to manually paste code	Not applicable	Requires file upload	Not supported	Native Support
Additional Costs	None	None	None	\$29-300/session	No extra costs

Core difference: Other tools either have memory without understanding (Anki), understanding without memory (ChatGPT), or neither (SaaS). Claude Code’s rule file + memory system is the only solution that combines both.

The Biggest Killer Feature: Starting from Your Project Code

All interview tools on the market operate on a "I ask, you answer" basis.

This project’s difference: It probes based on your own code.

For example, my project has a BoundedQueue (bounded queue) using two condition_variable. During interview preparation, Claude doesn’t ask "Please explain condition_variable," but instead asks:

"Your BoundedQueue uses two condition_variables (not_full_ and not_empty_). Can you use just one?"

Such questions force you to think about principles from code you’ve written, giving knowledge an anchor point, not just empty rote memorization.

Quick Start

1. Fork the Repository

gh repo fork happiness-cheng/ai-interview-engine --clone

2. Open with Claude Code

cd ai-interview-engine
claude

3. Say the First Sentence

I am preparing for a C++ backend development interview, targeting an internship at a top-tier company. Let’s start reviewing.

That’s it. Claude will read the rule files and start the first round of questions.

4. Switch to Your Own Tech Stack

The repository comes with a sample question bank for C++ backend. If you are using Java / Go / Frontend, replace it with a blank template:

knowledge/TEMPLATE.md → Copy to interview_tracker.md → Fill in your knowledge points

My User Experience

I am a sophomore student preparing for the 2026 fall internship recruitment. Using this system to prepare for C++ backend interviews, the most noticeable feelings are:

1. Less anxiety — No need to self-plan "what to review today"; the system automatically schedules based on the forgetting curve.
2. Actually remembered — The wrong answer → explanation → verification process forces genuine understanding, not fleeting recognition.
3. More confident about projects — Probing from your own code lets you clearly explain the "why" behind every design decision in your project.

This Is Not Just an Interview Tool

The underlying engine is general-purpose: Question → Answer → Judge → Explain → Verify → Forgetting Curve Scheduling.

Interviews are just one scenario. You can use it to prepare for:

• Technical Interviews (currently supported)
• Career Transition / Job Change Review
• Final Exams (Same principle, just swap the knowledge base)

Open Source Address

GitHub: https://github.com/happiness-cheng/ai-interview-engine

If this helps you, give it a star. If you have suggestions for improvement, feel free to open an issue.