kodwai Description
Anyone can get an AI agent to turn tests green on a toy problem. kodwai measures the part that is harder to fake: how well you direct it. Developers pick a real engineering challenge (a CRDT text buffer, an event-sourced ledger, a zero-downtime migration), pull it down with npx @kodwai/cli@latest challenge <slug>, and solve it locally with Claude Code, Cursor or Codex. No browser sandbox. When they run npx @kodwai/cli@latest submit, kodwai reads the session (prompts, commits, test runs) and returns a 0 to 100 score across three axes: Direction (how you steer, verify and decompose), Outcome (what shipped, replayed and stress-tested) and Lift (how far you beat a solo AI). Each signal cites its evidence, and the score comes with a confidence interval instead of false precision. Developers get 3 free scored submissions, then connect their own Anthropic key for unlimited runs. Teams can use the hiring track to run private real-world interviews.
Pricing
Integrations
Company Details
Media
Product Details
kodwai Features and Options
Coding Challenge Platform
Kodwai is an innovative platform designed for hands-on coding challenges that emphasize agency in coding. The challenges presented are practical, bite-sized tasks—ranging from creating a bookshelf REST API to implementing a simplified version of the Raft consensus algorithm—and each task incorporates subtle pitfalls that a simple prompt might overlook. Participants tackle these challenges locally using their own AI coding agents, and the scoring system evaluates not only the success of the tests but also how effectively the user guided their agent. Scores are based on three criteria: Direction, Outcome, and Lift, with a scale from 0 to 100 and detailed evidence for each metric. The platform features a public leaderboard, a dynamic Direction rating that updates with each scored attempt, and weekly competitions to foster a sense of community.
kodwai User Reviews
Write a Review- Previous
- Next
