AWS Architecture Blog
Author: Dev Arora
Dev is a Technical Account Manager at AWS. He specializes in cloud observability, GenAI infrastructure, Amazon Connect and large-scale migrations - helping enterprise customers optimize performance and operational resilience on AWS. Dev has led initiatives spanning Amazon Managed Prometheus, EKS, GPU-intensive AI/ML workloads and Amazon Connect. He’s passionate about turning complex architectural challenges into scalable, production-ready solutions that drive measurable business outcomes.
Closing the AI agent trust gap with graduated autonomy
Most teams give AI agents either full access or read-only, leaving value unused or risk unmanaged. This post describes graduated autonomy, an architectural pattern in which agents earn expanded permissions through sustained reliability and lose them when performance degrades, built on Amazon Bedrock AgentCore, Amazon DynamoDB, and AWS CodePipeline.
Adobe Firefly: Simplified observability with Amazon Managed Prometheus
Learn how Adobe Firefly achieved 28x faster GPU metric queries by migrating from self-managed Prometheus to Amazon Managed Service for Prometheus, with improvements in query performance, infrastructure reliability, and operational efficiency.