I used Claude Design to rebuild my AI Automation Society site and my personal site in about 20 minutes each, and the results felt way more polished than what I had before. In this video I walk through the full process of going from an idea to a deployed website, including how to plan with Claude, use Claude Design's tweaks and comments, push everything to GitHub, and host it on Vercel. I also break down what actually eats your usage limits so you can stretch every session a lot further

Anthropic just released the advisor strategy, and it's a big deal for anyone building with Claude. Instead of running every task through Opus, you can pair it as an advisor with a cheaper model like Sonnet or Haiku doing the actual work. In this video I built a dashboard to test how it performs across easy, medium, and hard prompts, and I also show you how to use the same idea inside Claude Code with opus plan mode to stretch your session limit further. GITHUB REPO

It's March 16th, and I love wrestling. Happy 3:16! A couple of things over the weekend really hammered home the importance of flexibility. Algorithms are changing. Tools are changing. Everybody is pissed about Antigravity's new usage limits right now. It just burns in the importance of owning your shit. Data, stack, audience, can't trust things will stay the same. What's something you're building right now to make sure you actually own your setup? And that’s the bottom line. 🖕🖕

Hey everyone, I made a tiny dashboard that shows all your running Claude Code sessions in one place. See which projects they're in, whether they're working or idle, and click to jump straight to that terminal. It's free and open-source, thought it could help some people out :) https://github.com/lukejbyrne/see-claude

Google just dropped Gemini Embeddings 2, a new model that natively understands images, videos, and text all at once. In this video I use it with Claude Code to build a full visual search engine from scratch. The crazy part is you don't have to build any of the chunking or ingestion pipeline yourself anymore. Just describe what you want, point it at your files, and Claude Code handles everything. It extracts content from images, generates descriptions, builds out your Pinecone vector database, all of it. You basically just throw everything you want to be searchable at it and it works. This is a massive unlock for anyone building with RAG.