The Infoq Podcast

Are you ready for your new non-deterministic co-workers? Autonomous agents promise to help build, operate, and run software systems, but they can also be unpredictable, chaotic, and difficult to control without the right operating model. In this episode of Next Generation Architecture Playbook, Shweta Vohra and Joseph Stein explore what changes when software systems start planning, acting, and making decisions on their own. The conversation distinguishes truly agentic use cases from traditional automation and looks at how architects and engineers should think about boundaries, orchestration, and system design in this new environment. The episode also explores the practical realities organisations face early in adoption. These include emerging risks such as prompt injection and tool misuse, the growing need for stronger observability and explainability, and how human-in-the-loop models fit into autonomous workflows. Joseph shares lessons from building a centralised AI platform used across multiple teams and p