Azure AI Fundamentals Micro-Credential
Duration: 3-4 Hours
Description
For teams already building on Microsoft’s stack, Azure AI is often the shortest path from “we should use AI” to something running in production. This session is a hands-on tour of the Azure AI platform: Azure AI Foundry for building and deploying models and agents, Azure OpenAI Service, and the pre-built Cognitive Services (vision, language, speech) that solve common problems without training anything from scratch. Participants deploy a model, call it from a simple application, and wire up basic monitoring and cost controls.
Audience
This session is for developers and solution architects working in a Microsoft/.NET or Azure environment who need to add AI capability to an existing application or platform. It assumes comfort with the Azure portal but not prior AI/ML experience.
Objectives
- Navigate the Azure AI platform and choose between Cognitive Services, Azure OpenAI Service, and custom model deployment
- Deploy a model in Azure AI Foundry and call it from an application
- Apply the responsible AI tooling built into the Azure platform
- Understand cost management and scaling considerations for Azure AI workloads
Prerequisites
Basic programming experience (C# or Python) and general familiarity with the Azure portal are expected. No prior AI/ML experience is required.
Related AI Courses
See the full AI training roadmap and course directory for how this fits into a broader learning path.
Need the RAG and retrieval layer to go with this? See Beginner’s Guide to RAG Micro-Credential and Introduction to Vector Databases for Developers Micro-Credential. Building agents on top of Azure AI Foundry? See Beginner’s Guide to Agentic AI Micro-Credential.
Course Outline
Module 1: The Azure AI Landscape
- Cognitive Services vs. Azure OpenAI Service vs. Custom Models
- Introduction to Azure AI Foundry
- Setting Up a Project and Resource Group
- Lab – Call a Pre-Built Cognitive Service from Code
Module 2: Building with Azure OpenAI Service
- Deploying a Model in Azure AI Foundry
- Calling the Model from a .NET or Python Application
- Grounding Responses with Your Own Data
- Lab – Deploy and Query a Model End-to-End
Module 3: Running It Responsibly and at Scale
- Built-In Content Filtering and Responsible AI Tooling
- Monitoring, Logging, and Cost Management
- Scaling Considerations for Production Workloads
- Lab – Add Monitoring and a Cost Alert to a Deployed Model