Blog Archive
Getting started with Amazon Bedrock inference profiles
AWS have released a native way to apportion model invocation cost and usage, as well as spread requests across models hosted in multiple regions for increased resiliency. Learn how to get started!
Read Post
Apportioning Amazon Bedrock invocation costs
Generative AI workloads have the potential to run up huge costs. Where multiple workloads are using Amazon Bedrock in the same account, it's essential to apportion costs accurately. Read to learn how!
Read Post
re:Invent 2024 Session Guide
A curated guide of sessions at re:Invent 2024, aligned to the Well-Architected Framework.
Read Post
Banishing the Curse of ClickOps
Follow the story of Clara, a Cloud Engineer, to understand how to eliminate the practice of ClickOps in AWS environments through Infrastructure-as-Code, improving efficiency and reducing errors.
Read Post
Architecting for Global Scale
A guide on architecting AWS applications for global scalability, focusing on foundational decisions and key AWS services.
Read Post