Audience
Software developers who code with AI agents, and engineering teams hiring for AI-assisted development
About kodwai
kodwai is a platform where developers solve real coding challenges on their own machine with their own AI coding agent (Claude Code, Cursor, or Codex) and get scored on how well they direct the agent, across three axes: Direction, Outcome, and Lift. Pick a ticket-sized challenge (a multi-tenant rate limiter, an idempotent ETL pipeline, a Raft-lite log), run npx @kodwai/cli@latest challenge <slug> to pull the problem, starter code and tests into a fresh git repo, solve it the way you actually work, then run npx @kodwai/cli@latest submit. The score is 0 to 100, and every signal cites evidence from your transcript, commits and test runs. Free for developers with a public profile and leaderboard. Hiring teams can run private real-world interviews and see how candidates work with AI agents: the prompts, the recovery, the verification, the result.
Pricing
Integrations
Company Information
Videos and Screen Captures
Product Details
kodwai Frequently Asked Questions
kodwai Product Features
Coding Challenge
kodwai is a coding challenge platform built for agentic coding. Challenges are realistic, ticket-sized tasks (from a bookshelf REST API to a Raft-lite log) and each one hides a few traps that a single prompt tends to miss. You solve them locally with your own AI coding agent, and the score reflects how well you directed it, not just whether the tests passed: Direction, Outcome and Lift, from 0 to 100, with evidence for every signal. There is a public leaderboard, a Direction rating that moves with every scored run, and a weekly league.
