GPT-6 Astra vs Claude Fable for Knowledge Work: My Experience
My experience with GPT-6 Astra and Claude Fable for research, proposals, and consulting: both are smart enough. I want the same intelligence cheaper and faster.
Engineering and applied AI leader turning emerging agent capabilities into production systems
I'm the VP of Technology at Elios, where I lead engineering, set the technical bar for Forward Deployed Engineers and AI Engineers, and help teams deliver AI-powered solutions in complex client environments.
I stay hands-on across full-stack development, TypeScript, LLMs, workflows, agents, MCP, and agent skills. I publish practical engineering guidance and create agentic coding tools including Peanut Butter Chocolate, Friendly Adversary, and Zero Defect.
Previously with Accenture and Umbrage, which was acquired by Bain & Company. Based in Orlando, Florida.
Interested in an AI strategy session?
Let’s talk about how AI can be deployed into your team’s real workflows.
Book here
More Thorough AI Review for Claude Code, Codex, and Claude Cowork
Open-source adversarial review for code and business work with Friendly Adversary and Zero Defect across Claude Code, Codex, and Claude Cowork.
Linux Codex Desktop App with Remote Control: How I Got 'Control Other Devices' Working
A practical debugging writeup on getting the unofficial Linux Codex Desktop App remote control flow working so Linux can control a Mac mini.
Claude Rules vs CLAUDE.md: Pattern-Scoped Conventions Your Team Is Missing
CLAUDE.md is directory-scoped. .claude/rules/ is pattern-scoped. Most teams only use CLAUDE.md and miss the rules mechanism entirely. Here is how we use both in a real Nx monorepo.