If you are using Claude Code regularly, the right plugins can make a much bigger difference than tweaking prompts. The best ones do not just add features they improve how you navigate codebases, write cleaner code, automate repetitive work and connect Claude to the tools you already use. In this post, I have highlighted 5 plugins that stand out for improving productivity and making Claude Code a more capable development environment. Whether you are building AI agents, shipping products or experimenting with automation, there's likely something here worth adding to your workflow. 💬 Which Claude Code plugin has become essential in your setup? I would love to discover more from the community.

I did a quick search here, but didn't see many posts that even mention the French AI/LLM "Mistral" (https://mistral.ai/)? What are some of the community's opinions or experiences with this? Even YT doesn't have much on it. Upside: Frontier model, open weights, options to self host, token costs (less than the big three, more than the Chinese AIs), 25% cheaper basic paid subscription ($15US instead of $20). Downside, it's in the EU, it's French (lol) and there's the whole digital wallet thing and EU nanny state mentality. I've been looking at it's features with a few chats this week and I wonder if it's a viable alternative. This is about the best video I've found on it so far: "The AI Model Nobody's Talking About — Mistral 3.5 & The Sovereignty Question" https://www.youtube.com/watch?v=LkbREGlNX8Y

When Bas first added me to this group, I could barely have told you what an API was. I've been mostly quiet since, because I was heads down building something, and I finally get to show you. But the win I want to share isn't the one I thought I'd be writing about. A few weeks in, I was at my kitchen table testing a feature, and my own app wrote something back to me. A little message, the kind it sends to a stylist. I read it and I cried. Me. The person who built the thing. It had just made me feel seen, as a hairstylist, and I wasn't ready for that. I'm a solo hairstylist. That's my actual job. The app is called Rooty, a companion for stylists who are tired of being told the only way to stay booked is to become a full time content creator. I built it between clients over about seven weeks. Here's the part I think this group will appreciate, and it genuinely surprised me: the code was not the hard part. The boring receipts: - 212 commits, about seven weeks, built between appointments - One Python file, roughly 8,000 lines, zero dependencies, just the standard library - 132 tests - Multi-tenant, real logins, running live right now with actual stylists signing up - Claude Code did the heavy lifting on the code, Anthropic's Haiku model runs the AI features - I directed all of it. Every product decision, every word of the voice, every call about what it should and shouldn't do. I'm not a programmer. I'm the person who knew what it needed to feel like. That last line is the whole thing, so let me stay on it. The code, honestly, the AI and I got through together. What I could not outsource, what no prompt handed me, was knowing when a message sounded like a brand instead of a friend. When it was technically fine and emotionally wrong. I felt those the way I feel a bad section in a haircut, right away, in my gut. And I sent them back. So the "it feels like it gets me" that people react to, that came from real decisions: - The captions and replies learn from my actual writing, not a formula. They sound like a person because they're trained on one. - Every AI feature is its own little room with exactly one job. None of them is a general chatbot. A tool that tries to do everything feels like nothing. A tool that does one thing warmly feels like a friend. - And me. I was the reject button. I read hundreds of generated lines and killed every one that rang false.

Many of today's fastest-growing AI roles focus on skills like communication, marketing, customer success, content creation, product strategy and technical support—not advanced coding. As AI adoption grows, companies are looking for people who can bridge the gap between technology and business. Which AI role interests you the most? Follow for more AI insights and practical resources.

Most people still use AI like a chatbot. Write a prompt. Get an answer. Rewrite the prompt. Repeat. Loop engineering changes that. Instead of manually reviewing every response, you create a workflow where AI evaluates its own output, follows predefined rules and continuously improves until it meets your standards. This approach isn't about replacing human judgment—it's about reducing repetitive work and building more reliable AI systems. In this guide, you'll learn how to: - Build your first review loop with Codex - Structure projects using AGENTS.md - Create repeatable AI review workflows - Automate quality checks for code and content - Develop systems that improve through iteration The most effective AI systems are not built from a single perfect prompt. They are built from simple, reliable loops that consistently solve one problem at a time. How do you see loop engineering changing the way we build with AI over the next few years? I'd love to hear your thoughts.