Datalumina

Getting started

Invoice Review

Build a hybrid invoice and receipt review app on Azure with Document Intelligence, Azure OpenAI, FastAPI, and React, starting from the client brief and a clean starter repo.

Invoice Review is a finance-review application for Northstar Facilities B.V., a fictional facilities-management company in Amsterdam. A finance administrator uploads a European supplier invoice or an employee expense receipt. Azure services extract the contents, deterministic code checks them against company policy, and a person makes the final call. Approve, reject, or send the supplier a correction request.

This handbook is the written companion to the video, and it covers the full arc, from the client brief and the Azure setup through every build stage to the deployment on Azure Container Apps and what it would take to make the result enterprise ready. Keep it open next to the video and copy the code and commands from here instead of pausing.

Build and Deploy a Document Review App on Azure (End-to-End Build)
Watch on YouTube · 2.5 hoursBuild and Deploy a Document Review App on Azure (End-to-End Build)

What you'll build

By the end of the video you have a complete application:

  • A hybrid extraction pipeline on Azure, with Document Intelligence as the primary extractor and Azure OpenAI in a supporting role
  • Deterministic finance rules in plain Python, because models extract evidence but code decides policy
  • A FastAPI backend with SQLite persistence and a React review portal built around the reviewer's workflow

The project is also a course in Azure itself. You create an account with free credits, work with the Azure CLI instead of clicking through the portal, and learn what resource groups, tiers, and regions actually mean when you provision real services.

Not a beginner course

This build moves at a natural working pace and uses AI coding agents throughout. You should be comfortable with Python, some TypeScript, and the command line. If you are new to Python, start with the free Python course first.

The repository

GitHubdaveebbelaar/e2e-invoice-review

1710

The main branch is the starting point for the build, and it is deliberately minimal. It contains the client brief, the target architecture, a fictional multilingual document corpus, environment templates, and pinned dependencies for the backend and frontend. Application code is intentionally absent; building it is what the video is for.

git clone https://github.com/daveebbelaar/e2e-invoice-review.git
cd e2e-invoice-review

If you go straight to a finished result you end up with a cool project, but you will not really learn anything. The value is in watching the system come together decision by decision, from the same starting point.

How to follow along

Read the brief and the architecture first, then work through the Azure setup pages. Each setup page starts with the outcome, walks through the steps, and ends with a checkpoint you can verify before moving on. With the accounts, resources, and starter repo in place, you are ready to build along with the video.

Dave builds the whole project with an AI coding agent and dictates nearly all of his prompts instead of typing them. The dictation bar you see popping up in the video is Glaido, and it is the fastest way to keep up with a build like this.

Accelerate your workflowDictate your prompts with Glaido

Glaido is the #1 dictation tool for developers, and the one Dave uses throughout the video.

Try Glaido free

Start here

On this page