ai-that-works/ai-that-works

🦄 ai that works - every tuesday 10 AM PST

What it solves

AI That Works helps developers bridge the gap between building AI demos and deploying reliable, production-ready AI applications. It focuses on the practical engineering challenges of scaling agentic systems.

How it works

The project hosts weekly, hour-long live sessions on Zoom where hosts Vaibhav Gupta and Dex Horthy conduct live coding, Q&A, and deep-dive discussions. Each session focuses on specific production-grade topics—such as memory pipelines, eval systems, and agent orchestration—using a shared toolkit that includes BAML for prompting, Cursor for development, and various agentic coding tools.

Who it’s for

It is designed for AI engineers and developers who want to move beyond basic prototypes and learn how to build, test, and maintain robust AI systems in real-world environments.

Highlights

  • Weekly live coding sessions every Tuesday at 10 AM PST.
  • Focus on production-ready AI engineering and architecture.
  • Hands-on exploration of tools like BAML, Claude Code, and agentic coding frameworks.
  • Expert-led discussions on performance optimization, evaluation design, and system architecture.

Related

  • Project
    memorax-ai/memorax-code

    A shared memory layer for AI coding agents that preserves architectural context, engineering lessons, and user preferences across sessions.

  • Project
    stormzhang/ai-coding-guide

    A comprehensive, free Chinese-language tutorial series that teaches users how to effectively use AI coding tools like Codex and Claude Code through practical, step-by-step guides.

  • Project
    openclaw/clawsweeper

    ClawSweeper is an automated, safety-guarded maintenance bot for GitHub repositories that uses LLMs to review issues and pull requests, providing structured reports and performing high-confidence, policy-based cleanup.

  • Project
    xenodium/agent-shell

    Emacs Agent Shell is an Emacs package that provides a native REPL‑style buffer for interacting with any LLM coding assistant that implements the Agent Client Protocol (ACP). It launches the provider’s CLI (Claude, Codex, Gemini, etc.) in ACP mode, handles authentication, environment setup, and even image/screenshot input, letting developers chat with AI agents directly inside Emacs.