How OffDeal Uses Claude to Close $91M in M&A Deals with a Team of Four Bankers
OffDeal is an AI-native investment bank that uses Claude to run every stage of M&A advisory — from sourcing sellers and finding buyers to writing investment memoranda and running diligence. After migrating to the Claude Agent SDK and iterating on MCP design, the firm raised internal eval accuracy from 25% to 85% and collapsed 12 independent agentic workflows into a single general-purpose agent called Archie. With four bankers each managing 5–8 concurrent deals, OffDeal closed 8 transactions totalling $91 million in its first year.
Impact
85%
Internal eval accuracy after migrating to Claude Agent SDK
12 → 1
Agentic workflows consolidated into one agent
5-8
Concurrent deals managed per banker
$91M
Transaction value closed in first year
Up to 4 hours
Autonomous buyer research runtime
Challenge
Twelve independent agentic workflows were brittle and context-limited: each API call was isolated, deals involved hundreds of millions of tokens of context, and any change to a standard operating procedure broke the corresponding workflow.
Solution
OffDeal migrated to the Claude Agent SDK and redesigned around MCP principles, collapsing 12 workflows into a single general-purpose agent called Archie that holds full deal context and moves fluidly across every stage of the advisory process.
Tools & Technologies
What Leaders Say
“I think we’re the only investment bank in the world that has more engineers than bankers.”
Sign up to read complete case studies, access detailed metrics, and unlock all use cases.
Full Story
OffDeal is an AI-native investment bank built on the belief that the middle market — founder-led businesses with $1–20 million in annual profit — deserves the same quality of M&A advisory as large corporations, but has historically been too expensive to serve well. The firm pairs bankers with software engineers and uses AI to do the work that would otherwise require a large team.
"I think we’re the only investment bank in the world that has more engineers than bankers," said CEO Ori Eldarov. With five engineers and four bankers, OffDeal runs every stage of a deal through software: originating clients, sourcing buyers, building seller and buyer lists, writing confidential investment memoranda, and running diligence.
The early architecture was a collection of 12 independent agentic workflows, each designed for a specific task. Every API call was smart in isolation, but the system was brittle. When a standard operating procedure changed, the corresponding workflow broke. The deeper problem was context: a single deal can involve more than a hundred million tokens of information, and the models couldn’t hold enough of it to handle problems outside their predefined scope.
Migrating to the Claude Agent SDK and redesigning around MCP principles changed the architecture entirely. Twelve workflows collapsed into Archie, a single general-purpose agent that holds the full context of a deal and can move fluidly between tasks. Eval accuracy — measured against an internal benchmark — jumped from 25% to 85%. Failed API calls from context overflow dropped to zero overnight. The buyer sourcing agent now runs autonomously for up to four hours, researching potential acquirers across 10 different sourcing methods without human intervention.
In its first year, OffDeal closed 8 deals totalling $91 million in transaction value, with each banker managing 5–8 concurrent deals and meeting 2–3 new potential clients per day supported by AI-generated preparation materials. The firm is proving that a small, software-augmented team can operate at the output of a much larger bank.
Amazon Bedrock