11 - Platform Breadth
What You Will Learn
- AWS Bedrock: Converse API for unified model access, Knowledge Bases for managed RAG, Guardrails, and AgentCore
- Databricks and Spark: the medallion architecture, Delta Lake, Unity Catalog, MLflow, and DBU cost levers
- Azure AI Foundry: model catalog/deployments/evaluations, Microsoft Fabric vs BigQuery, Azure SQL/Cosmos DB
- How to translate GCP-stack (Vertex AI) experience into credible AWS and Azure vocabulary
- A reusable Vertex AI ↔ Bedrock ↔ Azure AI Foundry comparison table for interviews and architecture discussions
Chapter Map
| # | File | Topic | Difficulty |
|---|---|---|---|
| 1 | AWS Bedrock | Converse API, Knowledge Bases, Guardrails, AgentCore | Intermediate |
| 2 | Databricks & Spark | Medallion architecture, Delta Lake, Unity Catalog, MLflow, PySpark, DBU pricing | Intermediate |
| 3 | Azure AI Foundry | Model catalog, Fabric vs BigQuery, Azure SQL, Cosmos DB | Intermediate |
| 4 | Platform Comparison Table | Full Vertex AI ↔ Bedrock ↔ Azure mapping across model access, data, and MLOps | All levels |
| 5 | Q&A Review Bank | 15+ Q&A pairs across all topics | All levels |
Recommended Learning Paths
Path A: Cloud-by-Cloud
- AWS Bedrock
- Databricks & Spark
- Azure AI Foundry
- Platform Comparison Table - tie it together
Path B: Interview Preparation (Accelerated)
- Platform Comparison Table - the fastest path to sounding fluent across clouds
- Q&A Review Bank - drill the specifics
- Whichever single-cloud note matches the role you're interviewing for
Path C: Databricks-Specific Roles
- Databricks & Spark
- Cross-reference Model Lifecycle & Rollout - MLflow is the concrete tool behind that note's registry concept
Resources
- Q&A Review Bank - 15+ Q&A pairs in this module
- Cross-topic Interview Questions
Key Cross-References
- Managed RAG concepts these platforms wrap → RAG Fundamentals
- Guardrail patterns Bedrock/Azure implement → Agentic AI: Evaluation & Observability
- Registry concept MLflow implements concretely → Model Lifecycle & Rollout
Next Topic
This is the final module in the current PyTorch → Fine-Tuning → Serving → Production → Platform Breadth tranche. See Knowledge Check for cross-module review.