Banking · Compliance
DocuMind.
On-premise pipeline that processes PDFs with Qwen 2.5 7B running locally. A single Go binary extracts, analyzes and returns structured JSON — zero external APIs, zero data to third parties.
- Result
- Private automation connected to internal workflows.
- Time
- 6-8 weeks
- Built with
- Go, LLM, llama.cpp, S3, Queue
How the project went
Why they called us
They wanted to automate document reading without sending sensitive data to external APIs.
The problem they had
Manual PDF review was slow, inconsistent and hard to integrate with internal systems.
How we solved it
We designed a local pipeline that processes documents, extracts fields and returns JSON other systems can validate.
Technical approach
Go, processing queues, local/S3-compatible storage and Qwen 2.5 7B through llama.cpp running on-premise.
Impact
Private, repeatable processing that plugs into existing flows without exposing documents outside the client's infrastructure.
How long it took
6 to 8 weeks for prototype, testing with real documents and hardening the pipeline.
What we needed from the client
Provide representative PDFs and define which fields were correct or actionable.
Process friction
Medium: AI needs iteration with real documents, but local deployment lowers legal and security friction.