The AI side of my work kept producing notes worth keeping in one place - which AWS service to reach for, the concepts behind the choice, and what changes once you move from reading about Bedrock to building with it.
- Chapter 1 (Fundamentals) - concept-focused, assumes no prior AI/ML background.
- Chapters 2-3 (build) - assume Chapter 1 as background, hands-on with specific AWS services.
- Chapters land as the hands-on work behind them gets done, not on a fixed schedule.
The series
Chapter 1 - Fundamentals
Algorithm types, performance metrics, AWS AI services, inference options, Bedrock vs SageMaker, and prompt engineering techniques - the concepts I kept returning to.
Chapter 2 - Building with Bedrock Knowledge Bases (coming soon)
Hands-on walkthrough of building a RAG application with Bedrock Knowledge Bases - what works, what surprised me, and when RAG is the right call over fine-tuning.
Chapter 3 - Bedrock vs SageMaker: Choosing the Right Tool (coming soon)
A practical decision framework for Bedrock vs SageMaker, drawn from building with both rather than comparing feature lists.
Quick reference - which AWS AI/ML service for which job:
| Need | Reach for |
|---|---|
| Use a foundation model via API, no infrastructure to manage | Bedrock |
| Ground a foundation model’s answers in your own documents | Bedrock Knowledge Bases |
| Train or fine-tune a custom model on your own data | SageMaker |
| Pre-built AI for a specific task (OCR, translation, transcription) | Textract, Translate, Transcribe, Comprehend, Rekognition |
Notes
- This series pairs with my AIF-C01 study notes - the fundamentals chapter is the concept reference behind that cert.
- AWS AI services move fast, particularly Bedrock - treat service-specific chapters as a snapshot of what was true when written, not a permanent reference.
- Next: Chapter 1 - Fundamentals