Bruno: An AI Product Manager for Scientists

We propose \emph{Bruno}, a semi-autonomous coordination agent for scientific research teams. Rather than generating hypotheses or running experiments, Bruno covers the \emph{coordination layer}: it ingests state from the tools a lab already uses (Slack, GitHub, Overleaf, Weights & Biases, calendars, transcripts), maintains a project-scoped model of tasks, decisions, and artifacts, and surfaces that state through Slack and dashboards. Its action space is restricted by design to messages, dashboards, and human-confirmed task mutations; it has no write access to code, manuscripts, datasets, or instruments. We argue this constraint is the load-bearing design choice for deploying agents in high-stakes scientific workflows, and describe an evaluation roadmap built around a pilot in a project-based graduate computational biology course.