finance_ops · finance · workflow
OffDeal powers every stage of M&A advisory with one Claude-based agent
OffDeal ran more than 12 separate agentic workflows that broke whenever SOPs changed, and hit a hard ceiling when deal context exceeded the million-token limit of their prior provider, causing API calls to fail outright.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Deal phase task initiated
A deal phase task — originating new clients, finding buyers, preparing materials, or running diligence — kicks off the workflow.
Tools used
Claude Agent SDKArchieMCPDeal PortalClaude Code
Outcome
After migrating to the Claude Agent SDK, internal eval accuracy rose from 25% to 85%, context overflow failures dropped to zero, and each banker now manages five to eight concurrent deals; the firm closed eight deals totaling $91M in its first year.
What failed first
OffDeal had been using a long-context model from another provider, packing the full context into each call to preserve accuracy over RAG, but that approach failed when context exceeded the million-token limit.
Results
Time saved2 to 3
Volume25% to 85%
Cost replaced$91M
Running sinceDecember
Grounding & classification
Source type: vendor customer story
46 fields verified against source quotes.
agentic workflowai agentcontent generationdata extractionmulti agent workflowemailfailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedfinancial servicesaccuracy improvementcost reductionemployee productivitythroughput increasetime savedvendor customer storyfinance opslead processingsales outreachagentic task executionautonomous resolution