Ahmed Abdelwahed

Cloud & Systems Specialist | Microsoft Certified Trainer

Open to New Opportunities

Azure AI – Hands-On Guide

Last updated on January 5, 2026

Azure AI | Hands-On Guide

A practical, screenshot-driven guide covering Azure AI services end-to-end — from training custom image classifiers and deploying object detection apps to working with Azure OpenAI, DALL·E, and real-time audio models.

This guide takes a hands-on, do-it-yourself approach to Azure AI. Rather than theoretical coverage, every section walks through a real lab you can replicate: creating Custom Vision projects, training image classifiers, building Streamlit web apps, deploying Azure OpenAI with your own data, and experimenting with DALL·E image generation and real-time audio. All screenshots are taken from live Azure environments, so what you see in the guide is exactly what you’ll see on screen.

What This Guide Covers

This guide walks you through twelve practical Azure AI labs across six service areas:

  • Image Classification — Train a Custom Vision model to classify cats, dogs, and lions, then retrain with big cat datasets from Kaggle
  • Object Detection — Build a fruit detector that draws bounding boxes around objects in images using Azure Custom Vision
  • Streamlit Web Apps — Deploy prediction apps on Linux VMs and Streamlit Cloud, with webcam support via GitHub integration
  • Computer Vision (OCR) — Set up Azure Computer Vision and build a Flask OCR web app to extract text from uploaded images
  • Azure OpenAI + RAG — Deploy GPT-4o in Azure AI Foundry, connect your own documents via AI Search, and publish a chat web app
  • DALL·E & Audio — Generate images from text prompts using DALL·E 3, and experiment with real-time audio using GPT-4o audio models

Complete Lab Index

The guide is structured into 12 hands-on labs:

  • Lab 01: Image Classification with Custom Vision — create resource, upload images, tag and train to 100% precision & recall in Iteration 1
  • Lab 02: Classify Big Cats — download Kaggle big cat dataset (cheetah, leopard, lion, tiger) and train a multiclass classifier
  • Lab 03: Prediction via Python API — publish trained iterations, obtain prediction URL & key, and call the API from Python
  • Lab 04: BigCat Streamlit App on Linux — install Streamlit on Rocky Linux, build an upload-and-predict app, run on port 8501
  • Lab 05: Object Detection — Fruit Detector — tag bounding boxes for 7 fruit classes (15+ images each), train, publish, and test Quick Test
  • Lab 06: Object Detection App + Webcam — deploy the fruit detector on Streamlit Cloud via GitHub with live webcam and snapshot support
  • Lab 07: Computer Vision & OCR Flask App — create Computer Vision resource, build Flask app on Ubuntu VM, expose on Azure port 5000
  • Lab 08: Azure OpenAI Chat Playground — create Azure OpenAI resource, deploy GPT-4.1, explore Chat Playground in Azure AI Foundry
  • Lab 09: RAG — Add Your Own Data — connect Azure AI Search, upload documents, configure semantic chunking, and query your data
  • Lab 10: Deploy OpenAI as a Web App — one-click deploy from AI Foundry to Azure App Service with Entra ID auth and CosmosDB chat history
  • Lab 11: Real-Time Audio — GPT-4o — deploy gpt-4o-realtime-preview in East US 2, enable microphone, and hold live voice conversations
  • Lab 12: Image Generation — DALL·E 3 — deploy DALL·E 3 in the Images Playground and generate images from text prompts

Perfect For

  • AI-900 / AI-102 Students wanting hands-on companion material for Azure AI Fundamentals and AI Engineer certifications
  • AI / ML Developers looking to spin up real Vision and OpenAI workloads quickly, with working Python code included
  • MCT Trainers & Solutions Architects needing a live lab reference for delivering Azure AI courses or evaluating service options for vision, NLP, and generative AI use cases

Guide Details

  • Platform: Microsoft Azure
  • Format: Screenshot-Driven Labs
  • Length: 12 Hands-On Labs
  • Version: 25.04

Ready to Build with Azure AI?

Download the complete hands-on guide — 12 practical Azure AI labs covering Custom Vision, Computer Vision, Azure OpenAI, DALL·E 3, and real-time audio. Free to download, no sign-up required.

📥 Download the Azure AI Hands-On Guide (PDF)


Have questions about Azure AI services or completed the labs? Connect with me directly through the links below!