Back to Events
Past

AI Coding Tools Compared: ChatGPT, Claude, Copilot, Cursor, Lovable and AI Agents

July 21, 2025, 02:00 Europe/Berlin
Alexey Grigorev

Continue with the workshop writeup

Open the canonical pages, recording, materials, and code repo.

View workshop writeup

We compare AI coding tools by asking each to help build the same small app, Snake in React. We compare the tools rather than ship one polished build. The walkthrough follows the tool categories, moving from chat applications to coding assistants and IDEs, then to project bootstrappers and agents.

Links

The main resources:

The comparison

The same app appears in several workflows:

flowchart LR PROMPT["Prompt implement snake in react"] CHAT["Chat apps ChatGPT, Claude, DeepSeek, Ernie, Microsoft Copilot"] IDE["Coding assistants and IDEs Claude Code, GitHub Copilot, Cursor, Pear"] BOOT["Project bootstrappers Bolt, Lovable"] AGENTS["Agents tools, file access, computer use"] CHATAPP["Local app snake-chatgpt"] CLAUDEAPP["Local app snake-claude-code"] PREVIEW["Hosted app Lovable preview"] PROMPT --> CHAT CHAT --> CHATAPP IDE --> CLAUDEAPP BOOT --> PREVIEW AGENTS --> IDE AGENTS --> BOOT

We build two Vite React projects. snake-chatgpt keeps the game in one component, so it shows what a chat app can produce from a short prompt.

snake-claude-code splits the page shell from the game component. It adds a score and a start-and-restart flow, plus WASD controls and a walls-versus-pass-through mode.

Hosted by

Alexey Grigorev

Alexey Grigorev

Chief Agent Officer at AI Shipping Labs

Software engineer and machine learning practitioner with 15+ years of experience building production ML systems. I focus on practical, production-grade ML and AI systems, from early prototypes to reliable systems in production.

I'm the founder of DataTalks.Club, a free community that connects tens of thousands of practitioners worldwide, and the creator of the Zoomcamp series, free, code-first programs that have reached 100,000+ learners globally.

At AI Shipping Labs, I'm building the kind of environment that would have accelerated my own career growth. After years of teaching at scale, I wanted something more focused: a space for action-oriented builders who want to turn AI ideas into real projects. The community gives members the structure, accountability, and peer support to ship practical AI products consistently, even alongside their main jobs.

alexey@aishippinglabs.com

Feedback