The problem
What was broken before AI
Consulting research often meant hunting through old decks, reports, interview notes, expert directories, and internal knowledge systems before a team could even frame the right approach. Valuable context existed, but it was scattered across formats and practices, with much of the firm’s knowledge living in PowerPoint. Newer consultants also had to know what to search for, who to ask, and which prior work was most relevant.
What changed
What the use case made possible
Lilli gives consultants a conversational front door to McKinsey’s internal knowledge. According to Business Insider, users can ask a question, have Lilli aggregate key points, identify five to seven relevant internal content pieces, and point them toward appropriate experts. McKinsey says the platform has been widely adopted since its 2023 rollout and reports time savings in searching and synthesizing knowledge.
Why this matters
Why this use case is worth studying
This case shows why enterprise AI gets more useful when it is connected to proprietary context, citations, and people. A generic chatbot can help draft a hypothesis, but a knowledge assistant connected to a firm’s own work can help a team understand precedent: what has been done before, which documents matter, and who inside the organization has real experience. For consulting, that changes the first hour of a problem from blank-page searching into a more informed discussion.
Use this when
When this pattern applies
Use this pattern when your organization has valuable knowledge trapped across decks, reports, wikis, transcripts, and expert networks, and employees waste time rediscovering what others already know.
