Most teams don't plan for it. They ship a summarisation tool, a copilot, something scoped and manageable. Then it starts calling tools, chaining steps, making decisions without a human in the loop. At some point the thing you built stopped generating and started acting, and the playbook stopped working.This session is about that transition: what changes in how you build, monitor, and maintain AI systems when they move from reactive to autonomous. Key takeaways: → Where observability tooling breaks down for agentic systems and what teams are replacing it with → How deployment governance evolves when your system is taking actions, not just generating outputs → The team structure shifts that tend to follow when AI starts doing more of the work

Every team building generative AI hits the same fork eventually: keep pushing one model to do everything, or start splitting the work across specialised components. Neither answer is obviously right, and the teams getting it wrong are finding out the expensive way. This session brings together practitioners who have landed on different sides of that decision, covering when compound architectures actually improve reliability and when they just add complexity and cost without a real payoff. Expect disagreement on where the line sits. What this session will cover: - When splitting a system into specialised components improves reliability, and when it doesn't - How teams are deciding between one capable model and several coordinated ones - The hidden costs of compound systems that don't show up until production - Real tradeoffs teams have made, including ones they'd reverse