Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.
Title
OffDeal consolidates 12+ agentic workflows into one Claude Agent SDK-based M&A advisor
…and prompting Dropped failed API calls from context overflow to zero overnight Consolidated 12+ independent agentic workflows into a single general-purpose agent, Archie Achieved 5 to 8 concurrent deals managed by each banker, with AI handling work…
Description
OffDeal, an AI-native investment bank serving founder-led businesses with $1-20 million in annual profit, migrated from a long-context model to the Claude Agent SDK and consolidated over a dozen separate agentic workflows into a single general-purpose agent named Archie. The switch raised internal evaluation accuracy from 25% to 85%, eliminated context-overflow API failures, let each of its four bankers manage 5 to 8 concurrent deals, and produced a buyer-sourcing list that used to cost $12,000 and a week of analyst time for about $200 in compute. The firm closed 8 deals totaling $91 million in its first year with a team of two bankers.
…e market by deal count but historically the least served. With Claude, OffDeal: Increased eval accuracy from 25% to 85% after switching to the Claude Agent SDK and iterating on MCP design and prompting Dropped failed API calls from context overflow to zero overnight Consolidated 1…
Company
OffDeal
…by each banker, with AI handling work across every phase of the deal lifecycle OffDeal is an AI-native investment bank that helps founder-led businesses sell their companies. By pairing bankers with software engineers, the firm brings full-service M&A ad…
Region
North America
…inancial services Company size: Small Product: Claude Agent SDK Claude Platform Location: North America 25% to 85% internal eval accuracy after migrating to the Claude Agent SDK and r…
Industry
Financial Services
…fDeal powers every stage of M&A advisory with one Claude-based agent Try Claude Industry: Financial services Company size: Small Product: Claude Agent SDK Claude Platform Location: North A…
Problem
Before the Claude Agent SDK, each OffDeal workstream (seller lists, buyer lists, confidential investment memorandums, and more) ran on its own dedicated agentic workflow that did very poorly on problems outside its predefined instructions, and every time a standard operating procedure changed, the corresponding workflow broke. The deepest constraint was context: a single deal can involve more than a hundred million tokens of buyer profiles, past transactions, financial documents and market data, and the team's long-context model from another provider simply failed once API calls hit its million-token limit.
…ormation: buyer profiles, past transactions, financial documents, market data. "The gap was coming not from the model intelligence, but from context, lack of context," Eldarov said. The team had been using a long-context model from another provi…
Solution
OffDeal consolidated nearly all of its AI workloads into Archie, a single general-purpose agent built on the Claude Agent SDK, connected to more than 20 data sources and handling work across every phase of a deal via modular, self-contained "skills" that Archie can combine and apply flexibly rather than hardcoded per-workflow logic. A buyer-sourcing skill encodes an experienced banker's roughly 10 sourcing approaches and runs autonomously for up to 4 hours, cross-referencing findings and recursively refining its search, while non-engineers, including a banker, can build new skills like branded presentation generation without engineering help.
…oads into Archie, a single general-purpose agent built on the Claude Agent SDK. Archie is connected to more than 20 data sources and handles work across every phase of a deal. Instead of hardcoding each workflow, the team now builds modular capabilities t…
Business value
Switching to the Claude Agent SDK and then refining MCP design and prompting raised OffDeal's internal eval accuracy from 25% to 85%, and context-overflow API failures dropped to zero overnight. Each banker now manages 5 to 8 concurrent deals and meets 2 to 3 new potential clients per day, a buyer list that used to take a team of analysts more than a week and upward of $12,000 now costs about $200 in compute, and a branded deck that used to take 30-40 hours now takes about an hour. The firm closed 8 deals totaling $91M in transaction value in its first year with a team of two bankers, and its average deal size climbed from $11M to over $20M in 2026.
…o 3 new potential clients per day, supported by AI-generated prep and materials Closed 8 deals totaling $91M in transaction value in the firm’s first year, with a team of two bankers The challenge Context, not intelligence, as the bottleneck OffDeal uses AI acro…
AI capabilities
Agentic AI, Generative AI
…to preserve client confidentiality. One agent across the entire deal lifecycle Since December, OffDeal has consolidated nearly all of its AI workloads into Archie, a single general-purpose agent built on the Claude Agent SDK. Archie is connected to more than 20 data sources and handles work across every…
Technology
Claude Agent SDK, Claude Code, Model Context Protocol (MCP)
…which point API calls simply failed. Building agents with the Claude Agent SDK The Claude Agent SDK is a collection of tools that helps developers build powerful agents on top of Claude Code. Read more The solution Claude Agent SDK for subagent orchestration The team sta…
Headline outcome
…e market by deal count but historically the least served. With Claude, OffDeal: Increased eval accuracy from 25% to 85% after switching to the Claude Agent SDK and iterating on MCP design and prompting Dropped failed API calls from context overflow to zero overnight Consolidated 1…
Use case type
Workflow automation
…ted to more than 20 data sources and handles work across every phase of a deal. Instead of hardcoding each workflow, the team now builds modular capabilities they call "skills," self-contained instructions that Archie can combine and apply flexibly. Take buyer sourcing: finding the right 300 to 400 potential acquirers out of mi…
