Write something
Pinned
11d •
New here? Introduce yourself 👋
Welcome to AI Production Hub! Really glad you’re here. Here, we learn practical AI skills together, share what we’re building and help each other figure things out. We’d love to hear a little about you in the comments: 1. Where are you in your AI journey, and what are you working on at the moment? 2. What would you like AI to help you build or improve? Feel free to join in with other people’s posts! You might have a question, a useful tip or a few words of encouragement to share. We’re here to learn, share and connect, and those conversations help us get to know each other and make progress together 🔥 Talk soon!
1
0
Pinned
11d •
🛠️ What are you building this week?
I’d love to hear what everyone’s working on this week and how it’s going 🔥 Feel free to share something you’ve been building, an idea you’re exploring, or something you’re working through. Screenshots and work in progress are welcome—you don’t need a finished project to share! If someone’s working on something that interests you, feel free to join the conversation.
1
0
3d •
Claude Code and Codex can now share AGENTS.md
One instruction file for Claude Code and Codex. AGENTS.md holds your project’s rules—things like writing style and when to ask for your approval. Claude Code now supports it too (v2.1.277+). By default, it falls back to AGENTS.md when no applicable CLAUDE.md is present. Already have both? Compare them, resolve disagreements and keep the useful rules. Check your setup before deleting anything. Official details https://code.claude.com/docs/en/memory#agents-md
0
0
7d •
New video: Why I would start Astra on Low 🎥
My new video is live on YouTube! I ran OpenAI Astra for a week. It is my favourite model so far. I get a more finished first draft than I did with Claude, with fewer hallucinations. It also loves burning tokens. I was hammering it for most of that week on extra-high reasoning or Ultra, with a lot of windows open. I maxed out my credits on the $200 plan, used OpenAI's resets three times, and still blew through the lot. Ultra is the same model at the same reasoning level, and it burns far more tokens. So I would start on Low with a task I can judge, check the result, and step up only when the work needs it. On the Artificial Analysis chart, Astra Low scores 46 for intelligence at $0.82 per task and GPT-5.6 Sol Max scores 47 at $1.99. Those are benchmark task costs, not anyone's bill. Which model is doing most of your work right now, and what made you pick it? https://youtu.be/T_CdGSK0AXk
0
0
10d •
New video: Share your Claude Code setup across projects 🎥
My new video is live on YouTube! I show how to set up a global config repo to share your Claude Code skills, hooks and MCP server configurations across multiple projects. I walk through the setup in VS Code and explain how symbolic links let you update shared resources in one place, with the changes appearing across your linked projects. https://youtu.be/1EovUMMoCUY
1
0
1-5 of 5
skool.com/ai-production-circle
Learn practical AI skills, build your first real systems, and share what works. Clear tutorials, useful prompts, and a community to grow with.
Powered by