📰 Dev.to · Raj Murugan

Eight rungs mapping what shipping production Agentic AI on AWS actually takes, marked honestly as covered, strong, flagship or gap rather than filled in to look

The senior-lens Python patterns that actually bite in a production agent loop: why boto3 blocking the event loop is the first one, and four more that follow fro

A personal Bedrock-adjacent build that went through three iterations and an architecture pivot. Five lessons that map directly to production AWS AI work.

Designing a production agent over sensitive data, the hardest part was that the most capable component in the system is the one you cannot trust. Here is the co

The agent doesn't read your wiki. It calls four tools that pull frontmatter-filtered chunks out of a Bedrock Knowledge Base. Here's the contract, the code, and

OIDC setup, dual-tag ECR strategy, automated Runtime updates, and multi-environment promotion.

How to build the Python agent that runs inside AgentCore: Strands SDK, prompt caching, dual-model strategy, and AgentCore Memory integration.

Real cost breakdown, prompt caching savings, Nova Pro vs Claude, idle timeouts, and CloudWatch alarms.

The linux/amd64 flag, .env.local pattern, mounting AWS credentials, and testing with curl.

A complete CDK v2 TypeScript stack for Bedrock AgentCore with inline comments for every deployment trap — naming constraints, ECR bootstrap, missing L1 construc