How Rosie is built.
An AI research agent for the Product Innovation team — a deterministic orchestrator that routes across Internal Research, Synthesis, and Targeted queries and returns a grounded, four-lens read of MillerKnoll’s end-user research.
Rosie — deterministic research orchestration
Rosie grew out of the Innovation Insights Experiment (LEANAI-38, now closed) and was replatformed onto Copilot Studio’s new agent experience. It’s an orchestrator with deterministic, button-based routing across three query types — Internal Research, Synthesis, and Targeted. The built-out Internal Research capability is grounded on the End User Research SharePoint library and returns a structured four-lens analysis with required citations and evidence-rigor levels.
Hover or tap an agent above to see its pipeline and what it returns for this bid.
◆Rosie— Research orchestrator
The entry point for the Product Innovation team. Rather than free-form intent detection, it uses deterministic button-based routing to send a request down one of three paths — Internal Research (grounded synthesis of MillerKnoll’s own research), Synthesis, or Targeted — so the path is predictable and the behavior is repeatable across users.
- ToolInternal Research route · grounded synthesisto the child capability below
- ToolSynthesis route · cross-source synthesis
- ToolTargeted route · specific, scoped questions
Why it matters · Button-based routing makes the agent’s behavior predictable and testable — the deterministic-systems discipline the portfolio is built on.