Designing GenAI Solutions and Selecting Models

Requirements to architecture: proofs of concept on Bedrock, the Well-Architected Generative AI Lens, model selection by benchmark and capability, provider-switch and cross-Region resilience, and the customization lifecycle.

Content current as of 2026-10.

Lessons

1. From requirements to architecture — and the GenAI Lens
2. Selecting foundation models: benchmarks, capabilities, tradeoffs
3. Resilient model architectures: provider switches and cross-Region inference
4. The customization lifecycle: adapters, registry, rollback

Sources

• AIP-C01 exam guide — Content Domain 1 (tasks 1.1–1.2)
• AWS Well-Architected Generative AI Lens
• Amazon Bedrock user guide — cross-Region inference
• Amazon SageMaker AI developer guide — Model Registry