Overview

Google, IBM & Meta Certificates – 40% Off

One Coursera Plus subscription covers most Professional Certificates on Coursera.

Establish the architectural foundation for enterprise Azure AI solution design. This course maps the full Azure AI service portfolio, including Microsoft Foundry, Azure OpenAI Service, Azure AI Search, and the specialized Azure AI services, and develops the solution planning and cost modeling skills needed to move from business requirements to a defensible architecture recommendation. You'll design a Microsoft Foundry workspace architecture with identity configuration and governance controls, analyze enterprise requirements against compliance constraints including HIPAA and data residency, and apply build-vs-buy-vs-configure decision frameworks and token economics to solution planning. No prior AI architect experience is required. However, foundational Azure familiarity is expected.

Syllabus

Azure AI Landscape: Map the Service Portfolio
- This module frames Azure AI service selection as a cost optimization and engineering efficiency discipline moving towards internalizing three declarative decision frameworks: the Predictability Scale, the Data Modality Filter, and the Operational Blueprint. By the end of the module, learners can map any enterprise business request to the correct Azure AI service category and understand how the eight services connect as a production pipeline rather than a list of siloed tools.
Azure AI Landscape: Select the Right Architecture Pattern
- This module develops architectural pattern judgment, the ability to evaluate a solution requirement against three structural pillars (Knowledge Boundary, Logic Depth, and Memory Lifetime), apply a diagnostic elimination process, and select and defend the appropriate pattern. You move to realistic stakeholder conversations, learning to frame trade-offs in the language of cost, speed, and control that clients and leadership use to make decisions.
Foundry Platform: Understand the Hub-and-Project Architecture & Foundry Capabilities
- This module establishes a precise understanding of the Microsoft Foundry platform—its hub-and-project structure, core capabilities, and governance model—before learners apply that knowledge to workspace design in Module 2. Learners develop the conceptual foundation needed to make defensible decisions about hierarchy design, identity configuration, and resource governance in enterprise environments.
Foundry Platform: Design a Production-Ready Workspace Architecture
- This module applies the platform knowledge from Module 1 to a complete workspace blueprint design exercise, then extends that work into the communication skills required to get the blueprint approved. You apply a structured three-step design methodology to produce a production-ready Foundry workspace blueprint for a realistic enterprise scenario, then practice presenting and defending that design to a skeptical security stakeholder in a simulated executive review.
AI Solution Planning: Analyze Requirements & Configuration Constraints
- This module develops the skill of translating enterprise business requirements into structured Azure AI service selections and deployment configurations, such as accounting for the real-world constraints of data residency, compliance, and latency, and applying those decisions to realistic deployment specification scenarios that reflect the architectural work practitioners encounter on the job.
AI Solution Planning: Model Cost Architecture & Apply Optimization Strategies
- This module develops the quantitative and strategic skill of modeling the full cost architecture of an Azure AI solution, from token economics and throughput configuration to storage and API call volume, and applying structured optimization strategies to right-size the solution for a given budget and usage profile.
Project Module: Azure AI Solution Architecture & Opportunity Assessment
- Learners work through a realistic enterprise scenario as a practicing architect, making twelve sequential architectural decisions across agent opportunity assessment, data grounding readiness, service selection, architecture pattern selection, requirements constraint mapping, and cost modeling. This mirrors the actual decision sequence an Azure AI Solutions Architect follows during an early-stage client engagement.