Mid-Market Management Consulting Firm
4x faster proposal turnaround with AI knowledge search and document generation.
The client is a management consulting firm with 180 employees across New York, Chicago, and London, specializing in operational transformation for mid-market healthcare and financial services companies. Annual revenue was about $42M at engagement, targeting $55M within two years. The growth plan depended on increasing proposal win rate and volume without a proportional headcount increase.
The firm had 12 years of project deliverables, proposals, case studies, frameworks, and client research across an estimated 38,000 documents. That institutional knowledge should have been their main competitive advantage. Instead, it was inaccessible. Documents were scattered across a SharePoint instance with inconsistent folder structure, individual consultants' OneDrive accounts, a legacy Confluence wiki that had been half-migrated then abandoned, and a shared drive that predated the SharePoint deployment.
When a partner or senior consultant needed to put together a proposal, it was slow. The typical approach: email three or four colleagues asking if anyone remembered a similar engagement, search SharePoint with keyword queries that returned hundreds of irrelevant results, and manually review past proposals for reusable sections. A partner estimated that assembling a competitive proposal took an average of 34 hours of senior consultant time across two to three weeks. The firm was doing about 8 proposals per month and winning 22% of them.
Knowledge loss from departing employees made this worse over time. When a principal with 9 years of tenure left, an estimated 40% of the institutional knowledge around their client relationships and sector expertise left with them. New hires spent their first three to four months asking colleagues where to find things and rebuilding personal reference libraries.
A previous initiative to organize the knowledge base — a six-month taxonomy project led by a KM consultant — produced a detailed classification scheme that was never adopted because it required consultants to manually tag and categorize their own documents. Tagging compliance dropped below 5% within two months.
Built around the principle the firm's previous taxonomy project missed: the system has to meet people where they work, not ask them to change how they work. Finding and reusing knowledge had to be easier than emailing colleagues — without requiring anyone to tag, categorize, or migrate documents.
Diagnose: knowledge audit and architecture (weeks 1-3)
First three weeks: understanding what existed, where it lived, and how people searched for it. A structured audit of the four repositories found 38,400 documents, about 29,000 substantive (the rest were duplicates, empty templates, and outdated drafts). Interviews with 14 consultants across all seniority levels mapped actual information-seeking workflows — who people asked, what search terms they tried, and where they gave up. Five high-value document categories accounted for 80% of reuse: past proposals, project deliverables, sector research, client presentations, and internal frameworks. The RAG architecture was designed around these categories, with retrieval tuned to return specific sections within documents rather than whole 80-page deliverables.
Design and deploy: RAG system and semantic search (weeks 3-8)
The RAG system had three layers. First, a document ingestion pipeline connected to SharePoint, OneDrive, and the legacy shared drive, processing documents into retrieval-optimized chunks. Each chunk kept its source metadata — document title, author, date, client (anonymized for search), and project type. Second, a vector database with embeddings from a fine-tuned model, using hybrid search that combined semantic similarity and keyword matching. Third, an LLM layer that synthesized retrieved chunks into direct answers with source citations. A consultant could ask 'What operational metrics did we track in the Mercy Health supply chain project?' and get a synthesized answer with links to the specific sections of the relevant deliverables — not a list of 30 documents that might contain the answer.
Deploy: proposal generation engine (weeks 8-12)
The proposal engine sat on top of the RAG system. A partner entered the prospect name, industry, engagement type, and a brief scope description. It retrieved relevant past proposals, pulled reusable sections (firm credentials, methodology descriptions, similar case studies, team bios, pricing structures), and assembled a first-draft proposal in the firm's standard template. The draft wasn't meant to be sent as-is — it was a 70-80% starting point for a senior consultant to refine and finalize. The engine also flagged potential conflicts of interest by cross-referencing the prospect against the anonymized client database. Partners described it as having a senior associate who had read every proposal the firm had ever written.
Scale: deployment and adoption (weeks 12-16)
Rolled out in two phases. The search tool went firm-wide first — a simple chat interface on the intranet and a Slack integration for quick queries. Usage was voluntary, no training mandated. We tracked weekly active users. Within three weeks, 67% of consultants had used it at least once, 41% daily. The proposal engine went to partners and senior managers in week 14, with individual onboarding sessions. Search queries, generated proposals, and consultant edits all fed back into the relevance model, so results improved with use.
4x
Faster proposal turnaround
34 hours to 8 hours average assembly time
31%
Proposal win rate
Up from 22% — higher quality proposals, faster response
60%
Research time reduction
Relevant past work found in minutes, not days
67%
Firm-wide adoption in 3 weeks
No mandatory training or usage requirements
$3.8M
Incremental revenue pipeline
First quarter post-launch, from increased proposal volume
12
Proposals per month
Up from 8, with the same team
The most telling sign came from new hire onboarding. A consultant who joined six weeks after launch described it as having a senior colleague with perfect recall of every project the firm had done, available whenever they needed it. The managing partner noted that proposal quality improved not just on speed — proposals now consistently referenced the firm's most relevant past work, because the system surfaced engagements the proposal author might not have known about. The London office, which had limited visibility into US engagements, ended up using the search tool more than either US office.
“The previous taxonomy project failed because it asked 180 consultants to change how they work. This succeeded because it didn't ask anyone to change anything. You search the way you think, and the system figures out what you need. Our proposal process went from a scavenger hunt to a starting line.”
Managing Partner, Management Consulting Firm
Institutional knowledge trapped in shared drives?
If your team spends more time searching for past work than building on it, we can change that.