Agents in Production was excellent

Mike's Notes

Some initial reflections. I will add to this post over the coming week.

Resources

References

  • Reference

Repository

  • Home > Ajabbi Research > Library >
  • Home > Handbook > 

Last Updated

20/11/2025

Agents in Production was excellent

By: Mike Peters
On a Sandy Beach: 20/11/2025

Mike is the inventor and architect of Pipi and the founder of Ajabbi.

I attended the online MLOPs event "Agents in Production held yesterday. It was hosted in the Netherlands. It started at 3am NZ time, so I missed most of it. But all the videos will be available soon, and I'll watch them all.

It was fantastic. The 30 speakers were leaders from engineering teams from every major AI company. NVIDIA, Google, Meta, OpenAI, Microsoft, Redis, Databook, Prosus, etc.

All talking about agents in depth. Lots of architecture here.

The audience was even broader, as great questions came through.

I could follow along and understand what they were talking about. This is in sharp contrast to NZ, where nobody is interested in this stuff. Nobody understands what I'm talking about, even in the NZ AI tech group, which focuses on using AI to build apps. This was about building AI itself and solving its problems.

It was fascinating. 

One thing I learned, which really surprised me, is that none of the AI agents described in the talks can evolve or learn.

The agents in Pipi 9 all evolve and learn.

I also found a solution to a big problem for Ajabbi.

I can't find anyone to help me. In this room, there were plenty of people. Now I know where to look.

It was a lucky moment. I don't recall how I found out about this community and event. Maybe I got an invite. Next event, I will be better prepped and have questions to post in the Q&A. Will also figure out how to contact other participants. I look forward to meeting them.

Future

Maybe I will get to give one of these talks sometime. I find it really useful to bounce ideas in an open discussion. Always come back with more ideas. Listening is more important than talking.

Bolt on

I also had another epiphany last night while sleeping. I could use some of these LLMs as input into Pipi 9, combining the strength of both. This also confirms what I have been learning from testing Krobar.

Tristan, I might have a job for you. :)

I had been thinking about outputting to an LLM, but it never occurred to me to go the other way until I watched these talks and worked it out visually.

No comments:

Post a Comment