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. 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 →Who
About Eric Caskey
Eric Caskey is a Senior Software Engineer at Amazon, based in New Jersey. He joined Amazon in June 2022 and has held the Senior Software Engineer title since August 2024, on a platform team where he architects a multi-region workflow orchestration platform whose validation guardrails run before anything executes, and owns the monitoring platform that keeps 3 million monitors standardized across 2,750+ application stages. Those guardrails have run 500,000 safety checks. Before Amazon he spent nine years at Prudential Financial in Remote Access SRE, building the MFA self-service portal used more than 18,000 times in six languages and keeping the VPN running for 60,000 corporate users through the early months of COVID. He brings the same rigor to AI: spec-driven systems, curated context, and validation that catches a wrong "yes" before it ships. He writes about how this work gets done at Caskey Engineering.
Questions
Common questions
- Who is Eric Caskey?
- Eric Caskey is a Senior Software Engineer at Amazon and a platform engineer based in New Jersey. He has spent fifteen years across five roles making production infrastructure safe enough to automate: at Amazon since June 2022, and at Prudential Financial for nine years before that. He writes about safety-critical platforms and AI reliability at Caskey Engineering.
- What does Eric Caskey work on at Amazon?
- He owns the monitoring platform that keeps 3 million monitors standardized across 2,750+ application stages, and architected a workflow orchestration platform built safe by default. Its validation guardrails run before every automated change and have run 500,000 safety checks. He also drove the platform's spec-as-code system, which gives AI coding agents curated context instead of raw access.
- What has Eric Caskey built outside work?
- A spec-driven engineering platform that runs one engineer and a fleet of AI coding agents through a work queue and an attested merge gate, written up as a case study and a lesson series on Caskey Engineering. Ballast, an open-source RAG system with a guardrails gateway, engineered to refuse when it should. SpecSelf, a spec-driven personal operating system whose AI agents read but never write. A C++ Black-Scholes options engine tuned from 15 to 215 million prices a second. A Finance Reviewer that presents deterministic factor scores narrated through six investor perspectives.
- How do I contact Eric Caskey?
- The contact form at ericcaskey.com/contact is the fastest route; he reads everything and replies within a week. He is also on LinkedIn at linkedin.com/in/ericrcaskey and on GitHub at github.com/CaskeyCoding.