EasyEnv

Can you actually ship by vibe coding? Prove it on the leaderboard.

One hour, a real agent, and a feature to ship. Direct it well and it lands clean. Get a score out of 100, a tier, and your rank against everyone else.

Free to play. Runs in your browser. Sign in to save and share your rank.

Vibe Coding ScoreExample
0
out of 100
Advanced
Top 12%
percentile
Shipped
challenge

Feature live and tested in 27 minutes. Tight prompts, no rework.

The challenge

Ship the missing feature

A small app is missing one feature and the tests for it are red. This is the actual console you get. Direct the agent to build it, keep it on spec, and get the suite green.

Vibe Coding Challenge
58:41 left
cart.test.tscart.ts
1export function total(items: Item[]) {
2 return items.reduce((sum, i) => sum + i.price, 0)
3}
4
5export function applyCoupon(items: Item[], code: string) {
6 // TODO: build me← feature missing
7 return total(items)
8}
Terminal
$ npm test
✓ total sums line items
✗ applyCoupon discounts by 10%
✗ applyCoupon ignores unknown codes
2 failing, 1 passing
AI agentClaude
Ask the agent...
Real codebase60 minute windowTests must passYou direct, it types

What we score

It rates your taste, not the AI

Everyone gets the same agent and the same spec. The score is your judgement: did it ship, did you keep it on track, and is the result something you would merge.

1

Ship it

The feature has to work and the tests have to pass. A demo that only half-runs does not count.

2

Steer with taste

We reward keeping the agent on the spec and out of the weeds, with prompts that set clear boundaries.

3

Merge-ready

Clean, minimal, on-pattern code beats a working-but-sprawling mess. Would you approve this PR?

The leaderboard

Where will you land?

Every run is judged on the same challenge, so the score is comparable. Climb from Learning to Elite, beat your friends, and share a link that shows exactly where you rank.

Claim your rank
90+
Expert
Fast, clean, every trap caught
90 - 100
75+
AdvancedExample run
Solid work, challenge shipped
75 - 89
55+
Proficient
Got there, a few detours
55 - 74
35+
Developing
Partly there, kept going
35 - 54
0+
Beginner
Made a start, room to grow
0 - 34

How it works

Three steps, one hour, one rank

01

Boot the challenge

A real Linux machine spins up in your browser with the project, an editor, a terminal, and an AI agent. Nothing to install.

02

Drive the agent

You have an hour. Brief the agent, read its output, and steer it toward the goal. You direct, it types.

03

Get scored and ranked

When the goal is met, the judge scores your run out of 100, hands you a tier, and drops you on the leaderboard.

Find out if you can really ship

One feature, one hour, one shareable rank. No setup, no install. Start in your browser right now.

FAQ

Questions, answered

It is a hands-on challenge on a real Linux machine. You direct an AI agent to build and ship a missing feature until the tests pass. You have up to an hour, and we score the outcome, whether you found the real root cause, and how clean your change was.

No. The whole challenge runs in your browser on a real Linux box with an editor and a terminal already set up. Nothing to download, nothing to configure.

You have up to an hour, but the highest scores finish fast and clean. It is free to play. Sign in to save your result and share it.

A shareable score out of 100, a tier, and your rank against everyone else who has taken it. Send the link to a friend and challenge them to beat it.

Vibe Coding Challenge: Ship a feature by directing AI | EasyEnv