Sourcing acquisition targets, handling broker communication, and drafting offer paperwork manually is slow and doesn't scale past a handful of live deals at once.
- 01Automated sourcing
Automations continuously scrape and pull new listings from multiple business for sale marketplaces, storing them centrally and updating daily.
- 02Broker reply handling (Agent 1)
When a broker replies to an inquiry, an AI agent reads the message (including extracting text from attached deal documents like CIMs), matches it against buyer criteria, and decides whether to qualify the deal, ask a clarifying question, or reject it.
- 03Follow up scheduling (Agent 2)
For deals awaiting a broker response, a second agent manages follow up timing and stop conditions, so nothing falls through the cracks without over messaging brokers.
- 04LOI drafting (Agent 3)
For qualified deals, a third agent drafts a Letter of Intent, which gets formatted into a properly structured document.
- 05Human approval gate
Before anything goes out, the draft LOI routes through a Slack approval workflow with interactive approve/reject buttons, keeping a human firmly in the loop on financial commitments.
- 06Send and tracking
Once approved, the LOI is sent from the client's own email address, and the deal's status is updated through the pipeline (from initial qualification through to 'LOI sent').
A high volume deal pipeline where sourcing, initial qualification, and paperwork drafting are automated, but every outbound financial commitment still passes through a human approval step.
Originally built for the financial services / m&a sourcing, the same architecture applies to any team facing a similar volume, compliance, or coordination problem. The stack (n8n, Claude API, Unipile, and others) is stable, self hosted where it matters, and designed to be operated by a small team without a platform crew.
- deal sourcing automation
- M&A automation
- AI LOI drafting
- acquisition pipeline automation
- n8nWorkflow runtime and orchestration. Every scheduled job, webhook, and branch lives here so the logic is version controlled and observable.
- Claude APIReasoning and structured outputs. The default LLM for anything that needs to be trusted in production.
- UnipilePart of the production stack for this build.
- SlackPart of the production stack for this build.
- Google DrivePart of the production stack for this build.
Given more runway I would build a first class analyst review UI on top of the pipeline instead of leaning on the CRM for review. The pipeline works, but analysts are the constraint and their workflow deserved first class treatment sooner.
Where to keep a human in the loop when automating deal sourcing. A strong thought leadership piece on the approval gate design pattern.
Does the AI send Letters of Intent without human approval?+
No. Every LOI is drafted by Claude and routed through Slack for human approval before it leaves the system.