Field Notes in Agentic Engineering: The Graph Is Not the Factory

Months before loop and graph engineering became popular AI builder terms on social media, I was building two open-source tools about durable state, governed execution, independent verification, and observable control.

Field Notes in Agentic Engineering: Software Factories Need Quality Control

5 things about deterministic checks and loop engineering for code quality in software factories

Field Notes in Agentic Engineering: AI Made Velocity Easier To Fake

Refining agentic engineering velocity metrics we need to measure for engineering velocity and developer productivity.

Token Efficiency is an Architecture Decision

What a Skills-vs-MCP benchmark reveals about where models should reason, where code should execute, and what enterprise teams should measure.

Field CTO Is Executive Developer Relations for AI

Why AI companies need leaders who can go deep with developers, wide with engineering leaders, and turn field insight into product and market direction

Why AI Coding Needs Code Integrity Built In

Frameworks Are Multipliers, Not the Default

Why I chose Jinja over a frontend framework for my policy enforcement AI coding engine

Field Notes in Agentic Engineering: Not Every AI Problem Is a Tool Problem

What conversations with professional software engineers reveal about people, process, and messy systems they begrudgingly work with.

Field Notes in Agentic Engineering: SDLC Traceability is an Unsolved Problem

Inside the SDLC traceability gap I kept hearing about at DevNexus

Field Notes in Agentic Engineering: What Enterprise Teams Shared With Me

What I heard from enterprise engineers at DevNexus about speed, standards, and software integrity.

How to Preserve Understanding When AI 10x's Your Code Output

AI Security Resources for Developers

A Comprehensive Guide to Red Teaming LLM-Integrated Applications

Platform Engineers Are Building the AI-Native Enterprise (Full Breakdown)

The AI Transformation Few are Talking About: How Platform Teams Are Turning AI Noise Into Real Organizational Advantage—Backed by Data, Experience, and the DORA Report

What is Viable Coding?

The Practice That's Saving Enterprise Development Teams From AI Chaos

Chasing AI-Native Software Development

How I'm Helping Enterprise Software Developers Shift from Vibe Coding to Viable Coding

How to Choose AI Developer Tools That Improve Team Productivity

Stop Buying AI Tools Based on Feature Lists: A Framework for Workflow-Native Evaluation

The Great Generative AI Architecture Gap: 8 Critical Patterns We Need to Define Now

How the AI industry's breakneck pace is creating massive architecture gaps—and why the next 12 months will determine who owns the infrastructure layer of AI.

Securing the ML Pipeline: Why AI/ML Demands a Security Mindset

Why Securing the MLOps Lifecycle Is Non-Negotiable

The Double-Edged Sword: The Reward is in the Risks of AI

How technologists can harness AI’s full potential, safely and responsibly.

Gen AI Testing is Not Software Testing: Rethinking QA for Intelligent Systems

Traditional testing won’t cut it. To build intelligent, reliable AI systems, product teams need a new playbook.

AI in Every Commit: The Ultimate Playbook for 50% Faster Delivery and 400% ROI

Integrate AI Across Your SDLC to Ship Features Faster, Cut Costs, and Capture 4X ROI

The Hidden Risks in the LLM Supply Chain — and What We Can Do About It

From Data to Deployment: Why LLM Supply Chain Security Is the Next DevSecOps Frontier

Sentiment Analysis of the Generative AI Community (2025)

AI’s Mood Swings: From 10x Productivity Dreams to Burnout, Bubble Talk, and AGI Anxiety