A research agent whose POC proved the data was ready
Rosie is a deterministic research orchestrator for Product Innovation. Its most valuable output wasn’t the agent — it was the discovery that MillerKnoll’s end-user research corpus was ripe for a knowledge graph, which moved the work to the Data Science team.
The opportunity
The Product Innovation team sits on a deep library of end-user research. The hard part was never collecting it — it was synthesizing it on demand, across the right lenses, with citations a researcher could trust.
What AISE built
Rosie is a deterministic orchestrator with button-based routing across three query types — Internal Research, Synthesis, and Targeted — so its behavior is predictable and testable rather than a black box. The built-out Internal Research capability is grounded on the End User Research library and structures every answer across four lenses — User Experience, Customer Insights, Business Strategy, and Knowledge Gaps — with evidence-rigor levels and required citations.
The benefit to the business
Building Rosie against the research library did more than ship an agent: it revealed that the underlying corpus was structured and rich enough to power a knowledge graph. On the strength of that finding, ongoing ownership moved from AISE to the Data Science team (Steve Meadows) to pursue that direction. A POC that ends by pointing to a bigger opportunity is a POC that worked.