A warm welcome from our summit MC Ethan and a look ahead to the day's agenda and events.

As systems take on more autonomy, control doesn’t disappear, it just becomes harder to define. Decisions are no longer made in a single step. They emerge across prompts, tools, and workflows that evolve over time. What looks controlled in isolation can behave differently once systems are live, making ownership, accountability, and intervention less straightforward. This panel explores where control actually sits in modern AI systems, how teams are designing for it, where it breaks down, and what it takes to keep systems predictable without slowing them down. Key takeaways: → Where control shifts as systems become more autonomous → How teams balance flexibility with guardrails in practice → What it takes to maintain oversight without introducing friction

In September 2025, Distillery partnered with the Oakland Ballers to build an AI system that managed a professional baseball game in real time, making calls on lineups, pitching changes, defensive positioning, substitutions, and late-game decisions. But the real lesson was not just whether the AI could make the call. It was what happens when an agentic system has to act with incomplete context, under live conditions, in front of people who care about the outcome. Built in just two weeks, the system pulled from live game stats, historical player data, matchup analytics, and environmental conditions to support real-time decision-making. Technically, it worked. But the experience also exposed the harder questions: what the system could not know, where humans still needed to intervene, and why technical success does not automatically create trust. In this session, Ethan Cole shares the inside story of building and deploying a high-stakes agentic system in the real world - from architecture decisions and inference under pressure to human-AI collaboration, trust, and the limits of automation when decisions carry visible consequences. Key takeaways: → What changes when AI moves from recommendation to real-time decision-making → Where agentic systems hit limits when context is incomplete or constantly changing → How teams can design for human override, trust, and accountability when AI starts making the calls