New: 3-part series on building an AWS DevOps Agent that knows your org — Intent vs State, the MCP layer, and wiring it all up with CDK. Read Part 1 →
About
I'm a Solutions Architect at Parallo (SoftwareOne), an AWS Advanced Partner. My day job is shipping production AI agents on AWS for enterprise clients. My nights and weekends are spent building the same kind of systems for my own problems and writing up what I learned.
The work I publish here is the work nobody else writes about: the IAM trust policy that takes an afternoon to debug, the VPC cold start that breaks streaming, the OIDC flow that silently fails for a month. AgentCore production gotchas. CDK patterns that survive a real deployment. Cost decisions that show up on the bill, not in the demo.
If you're shipping agentic AI on AWS and you've started hitting walls that the documentation doesn't mention, this blog is for you.
Stack
Featured Work
Production-ready Customer Service AI Agent on Amazon Bedrock AgentCore. Every deployment gotcha documented inline. The companion repo to the 6-part AgentCore series.
An MCP server that turns ADRs, incident reports, and runbooks into a queryable org-knowledge surface for AWS DevOps Agent. Four tools, Bedrock Knowledge Base, frontmatter-filtered chunks. From "agent that reads your docs" to "agent that knows your org."
Three Claude projects with Socratic tutoring, a weekly Cowork routine, three differentiated emails. Open-source spec, full design history including the v1-to-v2 architecture pivot. A personal build whose failure modes mirrored enterprise AI patterns.
Recent Posts
View all →What a Year 10 study system taught me about production AI failure modes
A personal Bedrock-adjacent build that went through three iterations and an architecture pivot. Five lessons that map directly to production AWS AI work.
Part 2: The MCP Server — Turning ADRs and Incidents into a Queryable Org-Knowledge Surface
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 the small decisions that make the difference between an agent that reads your docs and one that knows your org.
Part 3: Wiring It Into AWS DevOps Agent — AgentSpace, register-service, and the IAM Trust Policy That Ate My Afternoon
The MCP server is done. Now we plug it into AWS DevOps Agent: three CDK stacks, the AgentSpace + register-service flow, the composite-principal trust policy that you will get wrong on the first try, and a real-world OIDC gotcha that broke my own blog deploy for a month.