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