Llm

The bottleneck in AI-assisted coding isn’t the models—it’s the interface. After months of experimenting with various AI-powered development tools, I’ve landed on a voice-first, multi-agent setup that removes the friction between thought and code. For context, my primary role is an Engineering Manager. I don’t write production code at work, but I build apps on the side and experiment with new AI tooling. The challenge: typing instructions slows down iteration, especially when exploring ideas or debugging complex problems. ...

After I switched to engineering management, I realized that I missed coding. With my new job, I spend more time on github, and innovation is very much encouraged at the company. As such, I’ve been fiddling around with LLM’s to see what works (and not). As I explore various models and learn more, I’ve developed a workflow that leverages multiple LLMs, each chosen for its specific strengths. Here’s how I use various AI models to boost my development productivity. ...