Azure AI Foundry Essentials
A 55-minute builder’s tour of Azure AI Foundry — projects, model catalog, evaluation, deployment, and the production-readiness checklist.
Last updated: 2026-05-19
What you'll learn
By the end of this course you'll be able to:
- Azure AI Foundry architecture — projects, hubs, connections, and what runs where
- Navigating the model catalog: Azure OpenAI, Mistral, Llama, Phi, and partner models
- Project setup, managed identity, and Key Vault integration done right
- Building evaluation harnesses inside Foundry, including LLM-as-judge
- Deployment options — serverless, managed compute, and batch
- Cost monitoring, quotas, and the production-readiness checklist
Who this is for
Azure-native engineers, ML platform teams, and solution architects taking LLM workloads from prototype to production on Microsoft’s stack. Especially useful if you’ve been gluing Azure OpenAI, AI Search, and a handful of Functions together and want the cleaner Foundry-centric pattern that scales without becoming an ops mess.
Curriculum
8 chapters · 2 hands-on exercises · capstone challenge
Each chapter ends with the learning objectives ticked off. Quizzes are auto-graded with feedback; exercises are open-ended and produce artifacts you can take to your team.
1. Foundry architecture
- Map Foundry hubs, projects, and connections to your existing Azure resource model
- Identify which workloads belong in Foundry vs raw Azure OpenAI
2. Model catalog navigation
- Compare Azure OpenAI, open-weight, and partner models on latency, cost, and licensing
- Pick the right deployment type (serverless API vs managed compute) per model
3. Project setup and identity
- Configure managed identity, RBAC, and Key Vault-backed secrets for a Foundry project
- Wire private endpoints and VNet integration for regulated workloads
4. Evaluation harness
- Run built-in Foundry evaluators for groundedness, relevance, and safety
- Extend with custom LLM-as-judge and code-based evaluators
5. Deployment options — serverless, managed, batch
- Choose between Provisioned Throughput Units, serverless, and managed online endpoints
- Pick batch endpoints when latency doesn’t matter and cost does
6. Cost monitoring
- Set up Azure Monitor and Cost Management views for Foundry workloads
- Catch runaway token spend before the month-end invoice does
7. Production readiness checklist
- Walk a 20-point checklist covering security, evals, observability, and rollback
- Identify the 3 items that disqualify a workload from go-live
Capstone: Capstone: Promote a Foundry project to production
- Document the deployment, eval, and cost plan for a real Foundry workload
- Produce the production-readiness sign-off your platform team will accept
Capstone deliverable: Every learner who completes this course produces «Your Foundry Production Sign-Off Pack» — a tangible artifact you take back to your organization.
Curriculum live · full chapter content rolling out through 2026.
The outline, learning objectives, references, and capstone deliverable are published. Full chapter content (video, narration, exercises) ships progressively. Get notified when each chapter goes live.
References & sources
Built on cited sources — not vibes.
Every course is researched fresh against vendor documentation, regulatory sources, and peer-reviewed work. Sources used in this course:
Azure AI Foundry Documentation
Microsoft Learn · Source link
Azure OpenAI Service Documentation
Microsoft Learn · Source link
Azure AI Search Documentation
Microsoft Learn · Source link
Microsoft Learn — AI Services Overview
Microsoft Learn · Source link
Course details
Track
Builder
Level
Intermediate
Audience
Technical practitioner
Function
IT & Engineering
Industry
Cross-Industry
Stack
Microsoft
Paired Gennoor Way phase
innovate, build
Format
video, hands-on, interactive
You finished the course. Now what?
From course to outcome.
Reading this course is step one. The next step is applying it where you work. Here's how Gennoor helps — without the deck, without the pitch.
Run this for your team
A 2-day workshop or virtual cohort for up to 25 of your people, with exercises run on your data and a 30-day adoption plan.
From $5k · 2 weeks · function-specific
Apply this to your data
A 4–6 week pilot that takes what you learned and ships a working system inside your environment. Fixed scope, fixed price, code transferred day one.
From $25k · 6 weeks · production-grade
Just want to talk?
Free 30-minute call. No deck, no pitch. We listen to your situation and tell you honestly what makes sense — even if it isn't us.
Free · no commitment · 30 minutes
Or just keep learning. We recommend next:
Just finished «Azure AI Foundry Essentials». Want this to go further at your organization?