Platform engineering · AI reliability
Eric Caskey
I build production platforms engineers can depend on.
Fifteen years making production infrastructure safe to depend on. At Amazon I architect a multi-region workflow orchestration platform with validation guardrails that run before anything executes. I also own the monitoring platform that keeps 3 million monitors standardized across 2,750+ application stages. I bring that same rigor to AI: spec-driven systems, curated context, and validation that catches a wrong “yes” before it ships. I write about how this work actually gets done at Caskey Engineering.
Work
Featured work
- 500,000 safety checks
- 3 million monitors
Architected a workflow orchestration platform built safe by default: validation guardrails run before every automated change, and a spec-as-code system gives AI coding agents curated context instead of raw access. Its guardrails have run 500,000 safety checks across Amazon's fleet. I also own the monitoring platform underneath it, which keeps 3 million monitors standardized across 2,750+ application stages.
Case study on Caskey Engineering →- 200,000+ administrative actions
- 60,000 corporate users
Built the MFA self-service portal used over 18,000 times in six languages, automated 200,000+ administrative actions, and kept the VPN running for 60,000 corporate users through the early months of COVID.
Case study on Caskey Engineering →An open-source RAG system with a guardrails gateway, engineered to refuse when it should.
Read how Ballast handles trust →An operating system for a life, run like a spec-driven codebase: principles, goals, and decisions as versioned spec files, with AI agents that read but never write.
SpecSelf Starter at specself.ai →Writing
Selected writing
Ballast: An LLM App Whose Best Feature Is Saying 'I Don't Know'
June 27, 2026 · Caskey Engineering
A RAG system whose most important feature is refusing to answer. How trust got built into the architecture instead of the prompt.
Designing Safety Guardrails for Distributed Workflow Orchestration
April 10, 2026 · Caskey Engineering
What I've learned building validation engines for infrastructure where an incorrect “yes” is a production incident.
Get in touch
Get in touch about an engineering project, a question about the writing, or a professional conversation. I read everything and reply within a week. The contact form is the fastest route.
Contact →