Get This Tool
kodwai
Pricing
- Model
- Free
Summary
Every hiring signal in the LeetCode era collapses the moment a candidate pulls up Claude Code — an agent clears the whiteboard puzzle in under five seconds, and you learn nothing about the engineer. Kodwai scores what actually matters: how you direct an agent through a real problem, catch it when it ships something wrong, and verify the result before calling it done.
The platform delivers ticket-sized coding challenges you run on your own machine with your own agent — Claude Code, Cursor, or Codex. A CLI via npx downloads the problem, initialises a git repo, and starts the clock. When you submit, it packages your code, git history, test runs, agent transcript, and elapsed time, then scores you across three axes: Direction, Outcome, and Lift. A one-shot prompt that flukes a green test suite still scores low — the scorer reads the whole session, not just the final diff. The leaderboard is public, so your score builds a visible track record of agent oversight skill.
Bottom line: Pick Kodwai when you want an objective signal on how well you direct AI coding agents through real tasks — but if your goal is practice without a public record, or you need challenge types beyond what the current catalogue covers, the platform's fixed catalogue and lack of private mode will push you to build your own internal evaluation harness.
Community Performance Report Card
No community ratings yet. Be the first to rate this tool!
Community Benchmarks Community
Sign in to submit a benchmarkNo community benchmarks yet. Be the first to share a real-world data point.
Pros
Sign in to edit- Scores the full agent session rather than just the final diff, which means a one-shot guess that accidentally passes tests gets exposed as the non-skill it is — something a green CI badge will never surface.
- Runs entirely on your own machine with your own agent, so the problem-solving environment matches production reality rather than a constrained sandbox, and you get a score that reflects how you actually build.
- CLI setup via npx with no installation friction, so you can start a timed challenge without fighting a new environment before the clock even matters.
- Public leaderboard rankings give developers a portable, shareable record of agent-direction skill — filling the gap left by assessments that only measure what you memorized.
- Fully free with no paid tier, so there is no point at which access to challenges or scoring gets gated behind a paywall.
Cons
Sign in to edit- The challenge catalogue is fixed and curated by the vendor — when you exhaust the available problems or need a domain-specific scenario (internal tooling, proprietary stack, compliance-sensitive context), there is no way to author private challenges, and teams end up building a separate internal evaluation framework.
- No API and no self-hosted option means the platform cannot be embedded into a hiring pipeline, team onboarding flow, or CI-adjacent workflow; teams that need scored agent-direction assessments at scale or inside their own infrastructure hit this wall immediately and move to building custom evaluation harnesses.
- Agent access is entirely your responsibility — Claude Code, Cursor, or Codex subscriptions are prerequisites, so developers without existing access to one of those three tools cannot use the platform at all, and the platform provides no fallback.
Community Reviews
Sign in to write a reviewNo reviews yet. Be the first to share your experience.
About
- Platforms
- Web, CLI (npm)
- API Available
- No
- Self-Hosted
- No
- Last Updated
- 2026-06-30T12:24:23.603Z
Best For
Who it's for
- Developers using AI coding agents daily
- Engineers preparing for roles involving agent oversight
- Users seeking objective measurement of prompt engineering and verification skills
What it does well
- Practicing AI agent direction on realistic coding tasks
- Building a public profile via leaderboard rankings
- Comparing collaboration skills across different agents and approaches
Integrations
Discussion Community
Sign in to commentNo discussion yet. Sign in to start the conversation.
Compare kodwai
Spotted incorrect or missing data? Join our community of contributors.
Sign Up to ContributeCommunity Notes & Tips Community
Sign in to contributeBe the first to contribute. General notes, observations, gotchas, and tips from people who use this tool day-to-day.
Frequently Asked Questions
- Is kodwai free?
- Yes — kodwai is fully free to use. There is no paid tier.
- Is kodwai open source?
- Yes. kodwai is open source.
- What platforms does kodwai support?
- kodwai is available on: Web, CLI (npm).
Hours Saved & ROI Stories Community
Sign in to contributeBe the first to contribute. Concrete time/cost savings, with context. e.g. "Cut my code review backlog from 4h to 45m per week."
Curated lists that include this category
Kodwai is a challenge platform for developers who work with AI coding agents daily. The core loop is: browse a catalogue of ticket-sized problems, start a session via `npx @kodwai/cli challenge `, work the problem in your own editor with your own agent, and submit with a single command. The CLI collects everything — prompts, git history, test outcomes, agent transcript, time taken — and the scorer surfaces per-signal evidence against three axes: Direction (how you guided the agent), Outcome (what shipped), and Lift (the measurable improvement the agent provided under your direction).
The differentiating design decision is that passing tests is explicitly not the score. The vendor states that a careless one-shot prompt can make the suite go green and still score low, because the platform reads the full session. This targets the gap where traditional coding assessments reward recall and ignore judgment — the ability to decompose a problem into a useful spec, catch a hallucination before it merges, and verify what the agent actually built versus what it claims it built.
Kodwai fits developers who want a measurable, shareable signal of agent-direction skill — whether that’s preparing for roles where AI oversight is central or building a public profile via leaderboard rankings. The platform requires you to bring your own agent subscription and tooling; it provides no sandbox, no hosted execution environment, and no agent access of its own. That means the challenge experience mirrors real work closely, but it also means the platform is not useful for developers who don’t already have access to Claude Code, Cursor, or Codex. No API is available, there is no self-hosted option, and the docs describe no private or team-scoped challenge mode.