# One File In. Many Documents Out

Automatically split and classify mixed document streams — no manual sorting, no preprocessing, no guesswork.

## Messy Inputs Break Automation

You don’t control what gets uploaded — your users do.

Most document workflows don’t start with a single, perfectly labeled file. In reality, your customers or end users are the ones uploading documents — and **they upload whatever they have.**

That usually means:

- Bundled PDFs containing **multiple documents**
- **Mixed document types** from different sources

Before any extraction can happen, teams are forced to **manually** split, classify, and route documents — slowing down workflows and introducing errors.

## Automatic Separation. Intelligent Identification.

Invofox handles messy, user-generated uploads the way production systems need to.

Invofox combines Splitter and Classifier to **automatically separate, identify, and route** documents — even when everything arrives bundled together.

No preprocessing. No manual sorting. No rigid upload rules.

## How Teams Use Splitter + Classifier in Production

One uploaded file. Many document types. Fully automated processing.

### Ingest files
1. Upload single PDFs or batched files containing multiple documents.

### Detect document boundaries
2. Splitter uses AI-trained models to analyze page structure and identify where each document begins and ends, even when layouts are inconsistent or unknown.

### Split the file into individual documents
3. Once boundaries are detected, the file is split and new PDF files are generated, with each resulting document processed as an independent unit.

### Classify each document
4. Classifier uses AI-trained models to automatically identify document types based on content, layout, and the data that needs to be extracted.

### Route to the right workflow
5. Each document is processed using the appropriate extraction and validation logic.

All splitting and classification results — including document IDs and page ranges for each document — are returned via the API, giving your system **full visibility** into how each uploaded file was processed.

In real workflows, a single uploaded file may contain **multiple document types bundled together.**

For example, one file might include: Loan or mortgage documents, multiple payslips, an invoice or a bill of lading.

Splitter separates each document, and Classifier identifies each document type — **automatically** routing every document to the correct extraction workflow.

## Split. Classify. Extract. Route.

### **Splitter**
Automatically **separates multi-document files** into individual documents, even when files are unstructured or not consistently formatted.

### **Classifier**
**Identifies document types** for each document independently, eliminating manual labeling and fragile upload rules.

### **Extraction**
Extracts the required data from each document using the **appropriate extraction logic** based on document type.

### **Routing**
**Route extracted data** to the correct downstream workflow or system, without changing how users upload files.

Everything needed to automate mixed file uploads.

## **Automate Document Routing at Scale**

Stop fixing documents before you can process them.