Skip to content
0727
InsightsAcademyCasesEventsSign in
中文/EN
Cases/McKinsey & Company
← Back to cases
← Previous13 / 127Next →

McKinsey & Company

Lilli enterprise knowledge and agent platform
First-party enterprise source Management consulting Enterprise deployment ⚙ Technical reference Deep case | Key delivery chain is substantially documented Evidence level A Firm-wide scale / continuous rearchitecture
A Evidence level
Meet Lilli: McKinsey’s custom-built gen AI platform
Publisher: McKinsey & Company · First-party platform retrospective · Direct case-level source
Claim origin: Company product-lead disclosure · Independent verification: No · Accessed: 2026-09-19
Evidence level measures whether a source can be located and reviewed; it does not mean vendor-reported claims were independently audited.
Deep case | Key delivery chain is substantially documented 12 / 12
Business context2 / 2
Transformation workflow2 / 2
Technical workflow2 / 2
Human roles & governance2 / 2
Measured outcomes2 / 2
Source traceability2 / 2
All six dimensions meet the current completeness threshold.
Lilli documents both the journey from a four-person proof of concept to a firm-wide platform and the second transformation triggered by real cost pressure: moving from a single provider to a multi-model, LLM-agnostic architecture.
Business problem

Nearly a century of McKinsey knowledge was distributed across more than 40 internal sources, making discovery and synthesis time-consuming. The first platform version also depended on one model provider; as usage grew, cost, speed, and accuracy could no longer be optimized together.

Solution

A four-person team built a proof of concept in one week, an MVP in roughly five weeks, and tested it with 200 alpha users before a three-month gradual rollout. Lilli became an orchestration layer combining large and small models, internal and external knowledge, and access controls. The team later rearchitected it as a composable, LLM-agnostic open-source platform and gates new capabilities through alpha/beta testing, user feedback, and quality metrics.

Technical architecture & production workflow
Step 01
More than 40 internal knowledge sources plus external knowledge
→
Step 02
Access control, data security, and content governance
→
Step 03
Combination of large models and smaller specialist models
→
Step 04
Intent recognition, knowledge orchestration, and answer generation
→
Step 05
Composable, LLM-agnostic open-source platform
→
Step 06
Alpha/beta tests, usage analytics, output-quality evaluation, and unit-cost tracking
Key technology & infrastructure components
LilliMulti-model orchestrationEnterprise knowledge sourcesAccess and security controlsAgent frameworkUsage analytics and quality evaluationLLM-agnostic architecture
Human roles & accountability

Consultants use Lilli for retrieval, synthesis, and drafting but decide whether output fits the client context and remain accountable for delivery. The product team observes users, prioritizes use cases, runs alpha/beta tests, and manages risk; knowledge contributors improve the underlying corpus.

FDE delivery actions
  • Use a one-week proof of concept to validate executive sponsorship
  • Prioritize use cases through workshops, interviews, value, and feasibility
  • Test the MVP with 200 alpha users before broad release
  • Use real unit economics to move from one provider to a multi-model architecture
  • Gate capabilities through alpha/beta users and explicit quality metrics
Reusable delivery patterns
  • The product roadmap should start from user problems, not model features
  • Single-provider architecture can become a cost and performance bottleneck at scale
  • Gradual rollout brings real usage evidence into architecture decisions
  • Professional judgment and client accountability remain with consultants
Business outcomes & delivery results

McKinsey reports 72% active adoption, more than 500,000 prompts per month, and up to 30% time savings in knowledge search and synthesis. The team grew from four people to more than 150.

Evidence boundaries & verification notes
  • The 72% adoption, 500,000+ prompts, and “up to 30%” time savings are first-party metrics and do not represent uniform outcomes for every employee or task.
  • McKinsey explicitly describes Lilli as a multi-model orchestration layer, not a single RAG instance.
Primary source: Meet Lilli: McKinsey’s custom-built gen AI platform ↗ Additional sources: Building Lilli at the speed of change ↗ Additional sources: Plan for midstream adjustments ↗ Additional sources: Rewiring the way McKinsey works with Lilli ↗
Traceable does not mean independently audited
Open primary public source
0727.ai · Trusted agents, built together.Case research: FDE-case-library ↗ · MIT