For those building AI-native apps, what are your thoughts on a Go + Vue stack? How does it compare to Next.js in practice? Are there situations where Go + Vue is clearly the better choice, or do you still prefer Next.js for most AI applications? I’d love to hear about real-world tradeoffs around performance, developer experience, deployment, and scaling.

Hi all, I kind of dropped off from the community during last few months as I got a good gig at a large bank to build an AI AML platform for them. But I will be dropping in again .. Sharing how my SDLC agentic harness look like and how I make sure quality of code I produce is high. I am still doing all this inside Claude Code. Can give a demo or presentation if community is interested.

https://www.youtube.com/watch?v=cdIJ92Tx20Y https://github.com/michaelshimeles/ralphy Seems like a create way to fasten pace from PRD to first POC....would be interested in what people think?

Hey, I want to share with the community my approach to Vibe coding in React Native, how i set up my rules, generators, context for ai, hot and cold start, and indexing the code base. and also including the Memory bank I have write about it here in details: https://codemeetai.substack.com/p/i-spent-6-months-losing-fights-with how you set it up, the theory behind each decisions, the outcome and also the prompt to initialize that in your system Any feedbacks, improvements,.. is highly appreciated

Google just dropped agents-cli to help AI assistants build AI agents 🤯 Has anyone checked out the new agents-cli from Google yet? It’s not another coding assistant—it's actually a specialized tool for your coding agents (Gemini CLI, Claude Code, Cursor, etc.). It basically gives your AI direct skills to scaffold, evaluate, and deploy Agent Development Kit (ADK) agents straight to Google Cloud without you having to handhold it through the boilerplate. Key features that stand out: - Fast Scaffolding: One command (uvx google-agents-cli setup) injects the skills right into your coding environment. - Auto-Deployment: You can tell your coding agent to deploy your project to Cloud Run or Agent Runtime, and it handles the Infrastructure as Code (IaC) automatically. - Human Mode: If you don't want the AI doing everything blindly, you can manually run the commands yourself for deterministic control. It looks like a huge time-saver if you're building in the GCP ecosystem. What do you guys think? Is the speed worth the GCP lock-in? Repo: https://github.com/google/agents-cli