Azure AI Foundry Essentials
A ~36-minute builder's tour of Azure AI Foundry. Hub-project-connections, model catalog, identity, evaluation harness, deployment types, cost monitoring, 20-item production-readiness checklist. Voice: Emma.
8
Chapters
~36 min
Duration
Intermediate
Level
No
Certification
Who this is for
For Azure-native engineers, ML platform teams, and solution architects taking LLM workloads from prototype to production on Microsoft's stack.
How this course works
- 8 audio-narrated slide chapters · ~36 min of focused content
- Narrated by Emma (Azure neural voice)
- Capstone with interactive Markdown builder you take to your team
- Trust trip-wires on every play — what not to cross
- Free verifiable certificate on completion
What you'll walk out with
Specific outcomes from this course — no fluff.
- The Foundry 3-layer architecture (hub · project · connections) and when raw Azure OpenAI beats Foundry — premature consolidation is overhead, late is rework
- Model catalog navigation across 4 families (Azure OpenAI · open-weight · partner · custom) and 3 deployment types — picked on YOUR eval set, not vendor benchmarks
- Identity done right: managed identity + Key Vault + private endpoints — making the wrong way harder than the right way
- The 4 built-in Foundry evaluators (groundedness · relevance · coherence · safety) and the 3-pattern custom evaluator workflow
- Deployment-type fit: serverless ≤5M tokens/month · PTU ≥10M · managed compute for open-weight · batch for async
- Cost monitoring across Azure Monitor + Cost Management + Foundry dashboards, with 3 alerts that fire before invoice day
- The 20-item production-readiness checklist with 3 disqualifiers nobody crosses (no managed identity · no eval flow · no rollback path)
- 4-section production sign-off pack + 4 trust trip-wires + interactive sign-off builder for the platform team
Course content
8 chapters · ~36 min
Welcome
A 1-minute orientation — what the course covers, how to navigate, and what you walk out with. No audio on this screen.
Foundry architecture
3-layer architecture (hub · project · connections) · Foundry vs raw Azure OpenAI · migration path.
Model catalog navigation
4 model families (Azure OpenAI · open-weight · partner · custom) · 3 deployment types · 3 selection criteria.
Project setup and identity
Managed identity pattern · Key Vault for credentials · private endpoints for regulated workloads.
Evaluation harness
Built-in evaluators (groundedness · relevance · coherence · safety) · 3 custom patterns · 4-step workflow.
Deployment options
4 deployment types (serverless · PTU · managed · batch) · when each fits · 3 latency rules.
Cost monitoring
3 telemetry sources · 3 alerts (daily · forecast · spike) · 3 mandated tags (feature · env · owner).
Production readiness checklist
20-item checklist (4 categories × 5 items) · 3 disqualifiers (no managed identity · no eval flow · no rollback path) · documented sign-off.
Capstone — Foundry production sign-off
4-section sign-off pack · 4 trust trip-wires · interactive sign-off pack builder.
Want this delivered inside your organisation?
The course is the starting point. The same content powers a 4-week pilot, an org-wide rollout, or a continuous build engagement — set up on your data, with your team, by Gennoor Tech.