Now working with early teams
Engineers today read unfamiliar code, direct AI tools, review generated changes, and design systems. Genspur is building an assessment platform that lets your team see those skills in realistic, structured sessions.
Round 1 · Code reading
lib/retry.ts
12async function retry(fn, attempts = 5) {
13 for (let i = 0; i < attempts; i++) {
14 try { return await fn() }
15 catch { await sleep(2 ** i * 100) }
16 }
What happens if fn keeps failing?
It waits longer each time, then silently returns undefined. I'd rethrow the last error.
Found the silent failure
Round 2 · AI-assisted coding
Prompt to coding agent
Add invite expiry. Keep the existing auth checks and add tests for stale links.
Clear constraints · scoped the change
Round 3 · Code review
src/invites/accept.ts
18−return invite.user
18+if (invite.expired()) throw new Gone()
19+audit.log({ action, actor })
20 return invite.user
The agent added an expiry check. Ready to merge?
Almost. Expiry uses server time, so I'd test clock skew first.
Spotted edge case · explained the risk
Round 4 · System design
Added a queue to absorb traffic spikes
What we build
Core product · Early access
Interview rounds built around real engineering work: reading code, prompting AI coding tools, reviewing changes, and system design. Each round gives your team a clear record of what the candidate did and why.
Project based
Focused tools for teams with recurring technical review or decision work, where AI can remove real friction. We scope each one with you around a specific problem.
How it works
Instead of one generic coding puzzle, each round has its own context, tools, and things to look for.
The candidate explains unfamiliar code under real constraints.
Shows comprehension
They direct an AI coding tool and correct its output when it goes wrong.
Shows direction
They inspect a generated change, find the risks, and defend their decisions.
Shows judgment
They sketch an architecture and talk through the tradeoffs.
Shows systems thinking
No single magic score. You get structured notes on how the candidate approached each round, so your interviewers can have a better, fairer conversation. Hiring decisions stay with your team.
Why now
Engineers now spend much of their time reading, directing, and reviewing AI-assisted work, not just writing code from scratch.
A realistic session reveals context, judgment, and communication that an algorithm puzzle never needs to show.
Visible decisions give your team something concrete to discuss, so feedback is more consistent from one interviewer to the next.
FAQ
Email us. We're working closely with early teams to shape the platform around real hiring needs, and we'd be glad to hear about yours.
It supports them. Interviewers get realistic exercises and a structured record of each session, and hiring decisions stay with your team.
Clear notes for each round on what the candidate did and why. Your team discusses real evidence, not a single number.
Contact
We'd be glad to compare notes and hear what your team is seeing. Email is the fastest way to reach us.