I really am using the Gemini Live feature in Google AI Studio every day. It’s one of the most incredible AI features — for me — in recent times.

I use it a lot to guide me or to pair with me. I’ve used it to: learn how to use Docker, put n8n on Docker, generate a token on GitHub (last time I’d done it, it was still login), teach how to use it together with n8n… and so on.

I always turn on the option to let it search; it improved things A LOOOOT. You know how it is: most of the time the problem isn’t the model, but the context engineering. :)

I feel I get very “dangerous” with this pair of mine helping \o/

The original post includes an image.


Originally written in Portuguese and published on LinkedIn on November 19, 2025. I translated it into English with the help of AI (Claude): it let me bring my LinkedIn posts to people who don’t read Portuguese without rewriting each one from scratch. I reviewed the translation to keep my original meaning and tone.