Why Your AI Coding Agent Gets Expensive Before It Gets Useful
AI coding agents incur cost while searching, reasoning, editing, and retrying. Their value appears only when the resulting change is validated and accepted.
Personal intro
I lead engineering teams and work across architecture, resilience, and practical AI-enabled software delivery.
I am passionate about building better systems, improving developer workflows, and helping technical organizations move faster without losing judgment, quality, or trust.
Leading teams through ambiguity, improving engineering habits, and aligning technical execution with business outcomes.
Designing systems, guardrails, and operational practices that improve reliability, maintainability, and confidence at scale.
Exploring practical ways AI can improve software delivery, testing, decision quality, and developer workflows.
About
I’ve spent my career working across enterprise software delivery, engineering leadership, architecture, quality, and resilience. I’m especially interested in how teams can adopt AI thoughtfully without losing technical judgment, trust, or discipline.
The goal of this site is simple: help people understand what I do, read how I think, and reach out for thoughtful conversations.
Selected writing
AI coding agents incur cost while searching, reasoning, editing, and retrying. Their value appears only when the resulting change is validated and accepted.
Coding agents may expand who can contribute without expanding who can understand, review, and maintain the resulting code.
Why the winners in AI will redesign workflows, not just add agents to old ones.
Experience snapshot
Senior engineering leader with hands-on experience across architecture, enterprise delivery, software quality, resilience, and modern engineering practices.