McKinsey Builds AI Assistant to Scan Data and Answer Analyst Questions

McKinsey has built a generative AI solution to help its analysts generate insights for clients wherever the data resides.

Dubbed Lilli, the AI solution can scan more than 100,000 documents and interview transcripts.

McKinsey staff can type in a question and Lilli scans McKinsey’s array of data to return relevant insights. It can also summarize key points, include links and identify relevant experts. Lilli works on both internal data and external sources.

“Lilli aggregates our knowledge and capabilities in one place for the first time and will allow us to spend more time with clients activating those insights and recommendations and maximizing the value we can create,” said Erik Roth, a senior partner with McKinsey who leads the firm’s Lilli development team.

The AI platform is named after Lillian Dombrowski, the first professional woman hired by McKinsey in 1945, who went on to become the controller and corporate secretary for the firm.

McKinsey plans to upskill staff on prompt engineering and content validation to better use Lilli.

The unveiling of Lilli comes as McKinsey steps up its AI efforts. The consulting giant acquired the likes of Iguazio to support QuantumBlack, McKinsey’s AI consulting team.