Cla64.ai

Practice AI-Coding Interviews

Work on real code in a cloud-hosted VS Code with an AI interviewer that challenges your decisions and helps when you need it.

Start a free interview
Explore interviews

No installation · Real code execution · AI assistance · Detailed feedback · No card needed

Watch a session
A replay of a practice session on a rate limiter bug, on the session's Exercise tab, next to its Instructions tab. The interviewer relays a support complaint, the candidate spots that denied requests are still being recorded, fixes the code in VS Code, asks the AI how to make pytest stop at the first failure, gets a one-line answer, and runs the tests, which pass. The interviewer then asks whether two limiters could share state, and the candidate points at a shared mutable default argument.
Not a coding puzzle

Real engineering. Not coding puzzles.

Unfamiliar code, bug reports, tradeoffs and follow-ups. And AI, the way you use it at work.

Instead of an algorithm puzzle like Two Sum, you get a support ticket about a production bug.

How it works

One interview. Four steps.

  1. 1

    Choose an interview

    Pick a scenario and a language: Python, TypeScript, JavaScript, Java or C++.

  2. 2

    Open your workspace

    Watch a short video brief while your VS Code workspace gets ready. Nothing to install.

  3. 3

    Work with the AI

    Ask it for syntax, APIs or a hint. It follows your code, asks why, and adds requirements as you go.

  4. 4

    Get your feedback

    Hidden tests run against your code, and you get a written review of how you worked.

The scenarios

Practice real engineering scenarios

Each interview drops you into a small codebase with a task from a real job.

  • Debug

    Rate Limiter

    Users are blocked under quota in production. Find the cause and prove the fix with a test.

  • Build

    Bus Control Center

    Track a fleet from streaming position reports, with follow-ups arriving as you code.

  • Design

    Push Notification Router

    Route alerts across email, SMS and push from a blank project, then demo it live.

  • Incident

    Load Balancer

    Start from an incident report, restore correct routing, and explain what broke.

How the AI works with you

AI that helps and challenges you

Helps when you ask
Syntax, APIs, a library call, a hint when you're stuck. Ask it the way you'd ask AI at work.
Challenges your decisions
It reads your code as you write it and asks why.
Leaves the engineering to you
The design calls are yours to make and defend. Your report shows how you used AI along the way.

Example exchange: the candidate asks the AI how to drop items off the front of a Python deque and gets a direct answer, followed by a question about why they are replacing the list at all. The candidate explains the per-request scan, and the interviewer follows up about memory at 10,000 requests a minute.

Your interview report

Your interview. Your feedback.

No score and no ranking. What the tests found, how you reasoned and used AI, and what to do differently next time.

Session review

Rate limiter in production

Language
Python
Time used
68 of 75 min

Test results

4 of 5 passed, including hidden tests

  • ✓test_traffic_pattern
  • ✓test_denied_not_countedhidden
  • ✓test_history_pruninghidden
  • ✓test_instance_isolationhidden
  • ✕test_boundaryhidden

What went well

  • Went from the support ticket to the exact line in under ten minutes, and said out loud why raising window_seconds wouldn't help.

What to improve

  • A request exactly window_seconds old still counts against the user. Ask which side of the boundary is inclusive before choosing <=.

How a strong solution would approach it

Reproduce each ticket as a failing test first, then fix the three causes separately: stop recording denied requests, prune history outside the window, and give each limiter its own dictionary.

Rate limiter in production

Python, 68 of 75 min

Test results

test_boundary failed

What went well

Went from the support ticket to the exact line in under ten minutes, and said out loud why raising window_seconds wouldn't help.

What to improve

A request exactly window_seconds old still counts against the user. Ask which side of the boundary is inclusive before choosing <=.

Pricing
Beta

Free while we're in beta

Every account gets 3 practice interviews. No card, no subscription. Paid plans will come later, and we'll tell you before anything changes.

Start a free interview

  • Need more interviews?

    Preparing for a specific role or a round of interviews? Tell us what you need and we'll extend your account.

    Ask for more

  • Hiring?

    Run real interviews with your own candidates, with the full exercise catalog and higher limits for your team.

    Talk to us about team access
Q&A

Q&A

What is an AI coding interview?

An AI coding interview is a technical interview where you solve a realistic engineering problem with an AI assistant at your side, and you're assessed on how well you direct it, verify what it gives you and make the decisions yourself. On Cla64.ai you practice exactly that: a real project in VS Code in your browser, an AI you can work with, and an interviewer that asks about your reasoning.

How is Cla64.ai different from LeetCode?

LeetCode is for algorithm puzzles: a short function, a known trick, an accepted or rejected verdict. Cla64.ai tests different skills, with AI in the room: understanding a codebase, debugging, designing and building something new, testing, and explaining your decisions - and you get a written review of how you worked.

Does the AI write the code for me?

Not on Cla64.ai. Some companies now let candidates use AI to generate code in their interviews - Meta's AI-enabled round, for example - but you still have to understand and explain every line. Cla64.ai practices that part: the AI answers language, library and tooling questions directly and gives one hint at a time when you're stuck, while the logic and design stay yours. Your review describes how you used the AI.

How long does one practice interview take?

75 or 90 minutes, depending on the exercise. The clock starts when you start reading the task, and you can finish earlier.

How is my work assessed?

Exercises that come with starting code are checked with hidden tests. Blank-project exercises have no fixed tests: you demo your solution in the terminal, and an AI reviews your code, the demo and the conversation. Either way you get a written review - what went well, what to improve and how a strong solution would approach it - with no score and no ranking.

Is Cla64.ai free?

Yes, during the beta every account gets 3 free practice interviews with no card required. If you need more, ask through the contact page.

Get started

Be ready when the real interview starts.

Practice the interview. Use the tools. Get challenged. Learn where you need to improve. Your first 3 interviews are free.

Start a free interview