How AI made my one-on-ones deeper
I record every one-on-one, let AI extract the important bits, and walk into the next meeting prepared for real conversations.
I write about building software with AI agents, the projects I ship on evenings and weekends, and things I've picked up from 20 years of leading engineering teams. No frameworks or manifestos, just notes from someone doing the work.
I record every one-on-one, let AI extract the important bits, and walk into the next meeting prepared for real conversations.
Started singing lessons, loved them, but practicing at home without feedback was guesswork. So I built Intonavio to give me a pitch graph of any song.
After three AI projects I realized voice input gets better results than typing. Existing transcription apps wanted $100+/year. So I built my own.
Everyone talks about AI productivity gains, but nobody measures them. I'm starting to track my multi-agent system with real metrics to see if my $100/month is justified.
I shipped real-time video translation and a WhatsApp bot to solve actual family problems without a development team. Here's the step-by-step breakdown.
After two weeks of being the sole interpreter for my Polish parents in Egypt, I built a PWA that translates speech between any two languages in under two seconds.
My Polish parents and Egyptian in-laws share a WhatsApp group. I got tired of being the human relay, so I built a bot to translate for them.
Twenty years across QA, product, and engineering leadership took me from Warsaw to Cairo. Here's why I started writing about it.
If you’re working with AI coding agents or figuring out how they fit into your team, I’d be happy to compare notes. Drop me a message.
Say hello