- Learning Path Libraries: This path is only available in the libraries listed. To access this path, purchase a license for the corresponding library.
- Cloud
- Data
- Security
Build a Generative AI Solution with Azure
### Move Beyond the Chatbox. Become an AI Engineer.
Transition from standard cloud development to **AI Engineering**. In this code-first, hands-on path, you will build a production-grade "Smart Support Ticket" system. You will architect a serverless backend that automatically ingests raw text, processes it with Azure OpenAI, and stores the structured results for analytics.
Learn to navigate real-world enterprise constraints by securely integrating with pre-existing AI resources and handling strict API rate limits.
Content in this path
Evolution
The industry has shifted from "using" AI models via chat interfaces to "building" applications that leverage them programmatically. Developers need to know how to orchestrate API calls to LLMs, manage the non-deterministic data they produce, and store it structurally.
This evolution path focuses on the "Modern AI Stack" on Azure: Python automation (Functions), NoSQL Databases (Cosmos DB), and Generative Models (Azure OpenAI). It addresses the specific need to build environment-agnostic, scalable AI backends using managed services.
Try this learning path for free
What You'll Learn
- 1. Architect a scalable, Python-based backend using Azure Functions and Cosmos DB to ingest and process data.
- 2. Programmatically integrate Azure OpenAI Service to transform unstructured text inputs into structured business insights.
- 3. Implement production-grade error handling (exponential backoff) to manage API quotas and rate limits robustly.
- This path is designed for experienced Azure practitioners who want to build, connect, and operate a generative AI solution using Azure OpenAI, Azure Functions, Azure data services, and application monitoring.
- Learners should be comfortable:
- Architecting Azure solutions that combine compute, storage, database, identity, networking, and monitoring services
- Building and troubleshooting event-driven workloads with Azure Functions or similar serverless patterns
- Working with Azure Blob Storage, Cosmos DB, secure application settings, and diagnostic logs
- Writing and modifying Python code that calls external APIs, handles errors, and persists structured data
- Reasoning about authentication, regional placement, rate limits, retries, observability, and operational resilience
- This path does not introduce Azure fundamentals, basic Python programming, or entry-level generative AI concepts. The content assumes senior engineer or architect-level judgment and focuses on building a production-shaped AI workflow that integrates model calls, data ingestion, structured storage, monitoring, and hardening controls across the Azure ecosystem.
Learn with the best
