Cost and Performance Engineering

Inference economics — instance families, purchasing options, right-sizing — the troubleshooting stack from X-Ray to AgentCore Observability, budgets and quotas, and GenAI cost levers.

Content current as of 2026-10.

Lessons

1. Inference economics: instances and purchasing options
2. X-Ray, AgentCore Observability, dashboards
3. Budgets, Cost Explorer, and quotas
4. Token budgets, embedding compute, vector storage

Sources

• Automatic scaling of Amazon SageMaker AI models
• What is AWS X-Ray?
• Amazon Bedrock AgentCore: add observability to your resources
• Managing your costs with AWS Budgets