02 · AI automation · Logistics
Automated document processing
A logistics provider processed hundreds of delivery notes, waybills and customs documents every day — manually, error-prone, slow.
Client project · client anonymized (confidentiality) · project from 2024
- n8n
- OCR
- PostgreSQL
- Ollama
- 85%
- less manual data entry
- according to the client
- 4 min → 12 s
- processing time per document
- according to the client
- ≈ 99%
- extraction accuracy
- according to the client
01 · Problem
Up to 400 incoming documents a day in various formats — PDFs, scanned images, email attachments. Three employees each spent 3–4 hours a day manually entering data into the ERP system. Data entry error rate according to the client: approx. 3%, which regularly led to delivery delays.
02 · Solution
vona used n8n to build an automated pipeline with human review when the model is uncertain: incoming documents are converted to text via OCR, then classified and extracted into structured data by a locally hosted LLM (Ollama + Llama 3). When the model is uncertain, a human is notified to review. The extracted data flows directly into the existing ERP system. Because the model runs locally, no documents leave the company — data protection was planned in from the start.
03 · Result
According to the client, 85% of documents are processed fully automatically, processing time per document fell from an average of 4 minutes to 12 seconds, and around 99% of the data is extracted correctly. The three employees were relieved of data entry and moved into quality assurance roles.
04 · Workflow
- Documents: PDF, scan, email attachment
- RUNS LOCALLY · NO CLOUD: OCR (Recognize text), Local LLM (Ollama + Llama 3)
- Sure?
- 85% AUTOMATIC: Automatic, no intervention
- WHEN UNCERTAIN: Human reviews, gets notified
- ERP system: Data directly
Related services
We can do this for you, too.
The services behind this project — with examples, process and frequently asked questions.
Keep reading
Background from practice.
Blog
Reducing Ongoing AI Costs: Why Not Every Step Needs AI
Why AI automations often cost more than necessary, when conventional code is the better choice, and how an orchestrated workflow cuts costs significantly – using document management as an example.
Read more →Blog
Automation with AI Workflows: A Guide with Checklist
Which processes suit AI automation, how a workflow is built, which tools exist and how to calculate expectations and benefit realistically.
Read more →Blog
AI Agents in Everyday Work: Uses, Limits and Safety
What sets AI agents apart from chatbots and workflows, when which solution fits, which fields of use have proven themselves and which safety rules you need from the start.
Read more →Next project
Your project here?
Tell us about your problem. The first conversation is of course free of charge and without obligation.
Request a project →