According to Hollingsworth, R&D teams aren't short of data; instead, they're drowning in it. Designing and performing the right experiment to move product development forward requires a series of steps — searching for results from past experiments, exporting data to a spreadsheet, visualizing it in a graphics program, and documenting findings in an electronic lab notebook — that can add up to hours of unproductive work. “Most enterprise AI tools answer questions, but the insights remain in a chat window, leaving the workflow unchanged,” Hollingsworth said.

Available in the sidebar of every page in Uncountable's platform, Bodie allows search, analysis, and action to happen in a single conversation. Before Bodie, Uncountable already structured and centralized data from multiple sources, including spreadsheets, SharePoint, and other disconnected tools. Bodie extends those capabilities by helping scientists act on the data directly.

For example, suppose a scientist needs to find every experiment from the past year that used a specific ingredient, plot performance against cost, and share the results with the project team. With a single Bodie prompt, the chart is generated, embedded in a notebook, and ready to share within minutes.

Another example of Bodie's capabilities can be seen in Uncountable's formulation recommendation engine for Design of Experiments (DOE). In a conversation with Bodie, a scientist can describe formulation guidelines, performance targets, and the training set. Bodie then analyzes the project's historical data, generates recommendations for the experiment, and provides real-time explanations of the factors driving those recommendations. The scientist receives a well-designed experimental setup while understanding the source of the recommendations. In this way, Bodie makes DOE more approachable to scientists who know what they want to test but lack the deep statistical or other specialized knowledge needed to structure the experiment.

Organizations can also bring their own AI models into Bodie or connect external AI assistants to Uncountable through a Model Context Protocol (MCP) connector, enabling the platform to fit within existing AI strategies and technology stacks.

Learn more at uncountable.com.