Exploring AI agent platforms
Thoughtworks Technology Podcast
Thoughtworks
4.5 • 58 Ratings
🗓️ 22 January 2026
⏱️ 38 minutes
🧾️ Download transcript
Summary
If AI agents really are the future of how work will be done — in software engineering and beyond — the platforms on which they are built, run and maintained will be crucial. This is a topic two Thoughtworkers, Ben O'Mahony and Fabian Nonnenmacher, are currently writing about.
Although not due to be published until early 2027, the first two chapters of Building AI Agent Platforms are now available as part of O'Reilly's Early Release scheme. Its goal is to provide readers with a complete roadmap for developing AI agent platforms, from agent development to architectural principles to observability and governance.
In this episode of the Technology Podcast, the authors speak to regular host Ken Mugrage about the book, why agent platforms are a critical part of any AI strategy and some of the challenges of developing and maintaining them. Listen for an early look at what looks set to be a valuable book in the world of AI development and to gain a clearer perspective on what agentic AI really means at the start of 2026.
Learn more about Building AI Agent Platforms: https://www.oreilly.com/library/view/building-ai-agent/0642572243906/
Transcript
Click on a timestamp to play from that location
| 0:00.0 | Hello, everybody and welcome to another episode of the ThoughtWorks Technology podcast. |
| 0:12.4 | My name is Ken McRage. I'm one of your regular hosts. I'm joined today by a couple of our |
| 0:17.2 | thought workers that are also writing a book that's pretty interesting about AI agents. |
| 0:22.3 | So I'll allow them to do to themselves and then we'll get started. So I guess Ben, I'll start |
| 0:26.0 | with you. Hi, nice to be everyone. I'm Ben O'Mani. I'm Prince Boyer engineer with ThoughtWorks. |
| 0:31.2 | I've been here for two years or so, working in the global AI service lines. Before that, |
| 0:41.9 | working in the global AI service lines, before that working in traditional ML and VP of engineering for a number of different small startups. So yeah, lovely to get on the podcast. |
| 0:47.8 | And yeah, maybe introduce my colleague Fabian. |
| 0:51.7 | Hi, everyone. I'm Fabia Nonmacher. I'm based in Hamburg from Solvark, Germany. |
| 0:58.0 | I'm now five years with Solbergs. |
| 1:00.0 | And different to Ben, I'm coming more from the software engineering side, was a classical Java |
| 1:07.0 | developer and now in the recent years shifted more into the AI space. |
| 1:13.0 | Happy to be here. |
| 1:14.5 | Great. |
| 1:14.8 | Welcome both. |
| 1:16.2 | So, you know, this won't come a surprise to anybody. |
| 1:19.2 | AI is everywhere. |
| 1:20.3 | That's all we talked about in 2025, including, frankly, many things that weren't |
| 1:25.0 | AI that we just pretended they were, different machine learning |
| 1:28.3 | things or different, you know, if-then statements that we would pretend with AI. But really what we're |
| 1:33.8 | trying to do, at least at thought works. And you'll see it in all of our stuff if you're, if you're |
| 1:38.4 | watching social and stuff this week and next and so forth, is AI that works. So, you know, |
... |
Please login to see the full transcript.
Disclaimer: The podcast and artwork embedded on this page are from Thoughtworks, and are the property of its owner and not affiliated with or endorsed by Tapesearch.
Generated transcripts are the property of Thoughtworks and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.
Copyright © Tapesearch 2026.