<IA/>
Projects

CASE STUDY / 03

Automate intelligent document processing (IDP) with a multi-agent system.

A SaaS platform that reads, classifies and routes documents — with no human touch on the standard flow.

ROLE
Multi-agent system design
SCOPE
OCR · Classification · LLM extraction · Routing
STATUS
Shipped
YEAR
2026
PythonCrewAILangGraphHugging FaceFastAPI
01

CONTEXT

The problem

Processing a mixed stream of documents (invoices, forms, letters) normally requires several tools and manual sorting to route each type.

02

RESPONSE

The response

I designed a multi-agent system that orchestrates OCR, classification, field extraction via a calibrated LLM, and document routing based on a composite score — each agent responsible for a single stage of the pipeline.

03

FLOW

The document pipeline

  1. 01

    OCR

    Extract raw text from the source document.

  2. 02

    Classify

    An agent determines the document type.

  3. 03

    Extract

    A calibrated LLM extracts the relevant fields.

  4. 04

    Route

    A composite score decides the document's destination.

04

TRADE-OFFS

Design decisions

01

One agent, one responsibility

Separate OCR, classification, extraction and routing instead of one general-purpose agent.

02

Composite scoring

Route on several combined signals rather than a single classification confidence.

NEXT PROJECT

Digi-Form