What does the code review test show?
Whether a developer can work fast with AI and still keep bugs, weak design and security holes out of the code. The candidate reviews a pull request an AI agent wrote against a short spec, comments on the lines that need changes and gives a verdict. You see what they caught, what they missed and whether they read the spec.
Do you test prompting?
No. The test looks at what a developer does with code an AI agent has already written: whether they check it against the requirements and find the bugs, design problems and security holes in it. How they use AI tools along the way is up to them.
What about candidates who use AI?
AI tools are allowed, as on a normal workday. We ran a plain AI review on every task many times: it finds most security and spec problems and almost none of the broken tests or duplicated logic. Those problems count four times as much, so pasting the pull request into a chat model gives a middling score. The report shows how many of them the candidate found. Each candidate gets a different mix of planted problems. If a review closely matches a plain AI review or another candidate's, the report says so and suggests a follow-up question.
How do you handle candidate data under GDPR?
The candidate sees who invited them, that the result goes only to you, and when it is deleted. We keep their review and result for 180 days after grading, then delete them. A candidate can ask us to delete their data sooner by writing to hello@majken.ai. A person on your side makes every hiring decision.
Which languages and stacks do the tests cover?
TypeScript and Node.js backend tasks today. Python and React frontend tasks are coming.
How long does the test take?
About 25 minutes. There is no hard timer, and the time they spend is recorded. The candidate can pause and come back while the link is valid, which is 7 days.
What does the candidate see?
An email from Majken with your company name and a link. They need no account and write no code. Before they start, they see that AI tools are allowed, who gets the result and when it is deleted.
How is a review graded?
Each pull request has a fixed list of planted problems. An AI grader checks each one against the candidate's own comments and credits valid extra findings. You see their words next to every result, and you can flag any decision you disagree with.
How does pricing work?
Your first graded test is free. Then €19 a test, €129 for 10 (credits never expire), or Team at €99 a month for up to 30 tests. A test is charged only when the result is graded, never when you send it.
Can I get a refund?
We handle refunds case by case. Write to hello@majken.ai within 14 days of your purchase.
What is the free GitHub profile report?
A separate free tool. Enter a public GitHub username and get a report built from code the developer wrote. It can only see public work, and the methodology page explains what it measures.
About the free GitHub profile report: how it works.