Skip to content

README_en.md

Latest commit

 

History

History
56 lines (34 loc) · 2.52 KB

README_en.md

File metadata and controls

56 lines (34 loc) · 2.52 KB
Raw

AgentCode

中文

AgentCode is a training platform for real engineering work in the AI Coding and Agent era.

It is not a traditional LeetCode-style platform, and it does not mainly train people to handwrite algorithm solutions. AgentCode trains the skills that matter more in the AI era: completing real development tasks with AI / Agents and reviewing whether AI / Agent generated code is safe to merge.

One-line positioning:

Practice real coding work in the AI agent era.

More directly:

LeetCode trains you to write code. AgentCode trains you to ship code and review code written by AI.

Why This Exists

The AI era is already here, but many companies still evaluate engineers with traditional LeetCode-style interviews.

People spend huge amounts of time grinding Hot100 problems and practicing handwritten algorithm questions. In the past, maybe we had fewer options. But the AI era should not keep working this way. The scarce skills now are requirement decomposition, AI-assisted delivery, code review, risk judgment, test design, and merge decisions.

That is what AgentCode is built for: a new practice ground for the skills that matter in the Agent era, helping people become AgentCoders for the Agent era.

Core Modes

  • Task Mode: complete realistic engineering tasks with AI assistance.
  • Review Mode: review AI / Agent generated PRs and decide whether they can be merged.

The live V0 set currently focuses on Review Mode: 20 traceable AI PR review challenges are available now. Task Mode will become live after the runner, starter repositories, visible tests, and hidden checks are ready.

Docs

Current Stage

V0 focuses on 20 high-quality challenges. The current live set is:

  • 20 Review Mode challenges.
  • Task Mode is planned after the runner and test harness are ready.

It does not start with algorithm Hot100, complex community features, contests, leaderboards, or a complete online IDE. The first stage is about challenge quality, evaluation credibility, and a real training loop for AI-era engineering skills.

Brand

  • Repository: agentcode
  • Domain: agentcode.codes