AWS Certified AI Practitioner
Selecting a Generative AI Model
Turn the exam's list of selection factors into a working order of operations: eliminate on hard constraints, evaluate the survivors on your own task, then optimize for cost and latency.
Intermediate 18 minutes 5 Learning Objectives
- Identify the factors the exam names for selecting a generative AI model, and the additional factors AWS lists in the model selection lifecycle stage
- Apply the three gates in order: hard constraints, capability on your task, then cost and latency
- Compare the evaluation options in Amazon Bedrock: programmatic, judge model, and human
- Explain why the largest model is usually the wrong default and what model complexity actually costs
- Describe why model selection is reversible on Bedrock and what must be redone after a switch