M&A Team Cuts Due Diligence Research From 40 Hours to 4 With AI Agents

The Problem

A mid-market private equity firm was evaluating 15–20 acquisition targets per year. Each preliminary due diligence required analysts to manually review thousands of documents in a data room, cross-reference financials against public filings, and produce a risk summary. This took 40+ hours per deal and created a bottleneck: they could only seriously evaluate 3–4 targets simultaneously.

The Agent Pipeline

They built a three-agent pipeline:

1. Ingestion Agent: Connects to the data room via API, categorizes all documents (financial statements, contracts, IP filings, HR records, litigation history), and creates a structured index.

2. Analysis Agent: Reads each document category with domain-specific prompts. For financials: extracts revenue trends, margin patterns, and working capital signals. For contracts: flags change-of-control clauses, customer concentration, and unusual terms. For litigation: identifies open cases and settlement history.

3. Synthesis Agent: Cross-references findings, flags contradictions between data sources, and produces a 5-page executive summary with risk ratings.

Results

• Preliminary DD time: 40 hours → 4 hours
• Documents processed per deal: up to 12,000
• Risk items surfaced for human review: average 34 per deal (vs. 18 from manual review)
• Deals evaluated simultaneously: 3–4 → 10–12
• One deal: agent flagged a customer concentration risk (1 customer = 67% of revenue) that the manual review team had missed

Human Oversight

The agent's output is explicitly labeled "preliminary flags for attorney review." No investment decision is made on agent output alone. The agent's job is to ensure nothing gets missed — human judgment determines what the flags mean.

Related Cases

• Law Firm Cuts Contract Review Time by 85%
• AI Agent Drafts NDAs in Under 60 Seconds