Roland Busch

And this is what AI agents can do.

Finally, you still have to have somebody who is maybe...

Removing a blockage.

Maybe updating a software will be automatically, but changing a part, changing a piece, have a switch which is going wrong.

So you have to have people who know what to do.

We tell them what to do with classes.

I presented also in the presentation in the CES.

So this helps you interacting in your natural words and helps you fixing things, even if you don't know really all the details.

This is where agents coming in, orchestration agents, which is supported by a machine building agent, a machine agent, a product agent, a workflow agent, whatever.

And that's how the future looks like, which is very powerful.

It keeps your yield high.

Your quality process is very high and you're super agile if there's any change or change in your production because you have a different version you want to produce.

It's super smart and it doesn't take a week to reassemble your line, but it really goes automatically.

But not only.

It's based on an LLM.

depending on which one we are working on and different use cases, but it's based on LLM, but it's not good enough.

If you're just an LLM-based agent to fix a problem, I mean, the hit rate is nowhere near

I mean, everything that we need.

But we are training these LLMs on our data, on proprietary data, product data, machine data, and operation data.

Once you have that, and even the data of fixes in the past.