Practical AI · AI Builders · November 2026
Chris Benson asked how federated learning applies to agents. Lorenzo says the pitch isn't only protecting private data, it's getting access to data that is otherwise unavailable.
…can get a premium plan for just $199 per month. Go to hostinger.com/slash practical and use code practical for an additional 10% off Black Friday and Cyber Monday pricing. That's hostinger.com/slash practical and use code PRACTICAL for an additional 10% off Black Friday and Cyber Monday pricing.
…issues, you know, privacy and stuff around it. Could you, to turn a corner a little bit, could you talk a little bit about how you're applying federated learning, some of the use cases, maybe how Agentics fit into the framework and some of the use cases or applications that you've been diving into?
Absolutely. So in my first experience, research experience during my PhD, we started to develop federated learning technologies for Training language models. Back then it was pretty challenging and fairly new. Basically, the idea behind it was that we were able to source much more data than what was available, right? So the idea there is: I'm not using federated learning just to preserve privacy, but also to be able to tap into new data sources that could be very valuable. So, in the context of language models, right now, what I've seen applied and what I've applied myself is mostly related to these kind of outputs. Like, I really want to use the federated learning technology so that I could use this massive amount of data that otherwise it's not available. And hopefully, I'll be able to construct much better models or models that can reflect much better what…
Sure.
And if you want to improve your Agentic systems that are relying on this kind of trajectories, Federated Learning is a natural way to train in a distribution these AI systems.
Could you talk a little bit about, like, you know, we've dived into some of the complexity of introducing Agentix and all those trajectories. And like, and I think one of the things I'm trying to grasp right now is like what it's when we were talking about just the model before the break, it was…