Exploring AI agent platforms
81 snips
Jan 22, 2026 Ben O'Mahony, a principal engineer at ThoughtWorks and co-author of the upcoming book on AI agent platforms, joins Fabian Nonnenmacher, a software engineer with a rich Java background turned AI practitioner. They dive into the crucial role of AI agent platforms in future work, discussing definitions of agents and their characteristics. The duo emphasizes extending existing platforms, the importance of observability, and security measures for autonomous agents. They also explore prototyping and the merging of AI engineering roles, offering insights into the evolving tech landscape.
AI Snips
Chapters
Books
Transcript
Episode notes
Practical Definition Of An Agent
- An agent is software that can impact the real world and make semi-autonomous decisions.
- Ben O'Mahony says agency matters more than debating philosophical definitions.
Platform As An Internal Product
- A platform is a curated assembly of APIs, tools, services, knowledge and support arranged as an internal product.
- Ben O'Mahony highlights user journeys and continuous product thinking for platforms.
Add Evaluation Tooling For LLMs
- Build platform support for LLM evaluations and experiment tracking to measure non-deterministic outputs.
- Fabian Nonnenmacher advises capturing evaluation scores and running experiment variations as core capabilities.


