Practical perspectives on AI implementation, governance, and engineering leadership.
AI absorbed the coordination work that filled middle management calendars. At the same time, AI broke the hiring pipeline that would have found the people who can actually make AI work. Both happened at once. Most engineering leaders haven't connected them.
Read more →Building a high-performing agentic engineering environment isn't about prompting — it's about encoding three things into a structured operating system: your development process, your domain model, and your technical architecture. Here's how they map to rules, subagents, memory, and the knowledge graph.
Read more →AI coding tools out of the box generate plausible code that doesn't fit your system. The difference between AI as a novelty and AI as a force multiplier is the harness — structured memory, rules, subagents, and skills that encode your architecture into AI behavior.
Read more →How I used Claude Code to build a 33-page website, AI voice receptionist, AI-powered contact form, content ops system with 5 research agents, and a full marketing pipeline — in a single working session.
Read more →How a Neo4j knowledge graph connected via MCP gives AI development agents deep understanding of complex product domains — and what it reveals about AI-first operations.
Read more →Lessons from building two Model Context Protocol servers — a PR reviewer and a knowledge graph — that extend Claude's capabilities for real development workflows.
Read more →When root causes are unclear and the codebase is a mess, AI-assisted defensive engineering can systematically eliminate failure modes. Here's how I approach legacy maintenance with AI.
Read more →AI governance delivers multimillion-dollar benefits for healthcare insurers through risk reduction, efficiency gains, and improved decision-making. Here's what the ROI actually looks like.
Read more →The shift from User Experience to Agent Experience demands a fundamental rethink of how we design AI-augmented systems. UX principles don't directly translate to AI contexts.
Read more →How LLMs handle context and code understanding — and why memory management is the key challenge for AI-assisted software engineering.
Read more →Traditional per-seat SaaS pricing is misaligned with AI-delivered value. The industry is shifting to usage-based and outcome-based models — here's what that means.
Read more →Rules engines are the digital backbone of healthcare insurance operations — enabling systematic compliance, consistent policy application, and operational efficiency at scale.
Read more →How healthcare insurance is evolving from rule-based RPA to autonomous AI agents. The orchestration patterns, governance challenges, and implementation strategy.
Read more →Single-model AI alignment creates a false sense of security. Like medieval castles, AI safety requires multiple independent layers of defense. Here's why and how to build them.
Read more →Compensation is the most neglected concern in microservices architecture. Distributed sagas, orchestration patterns, and strategies for maintaining transactional consistency.
Read more →A risk-based AI governance framework with five-tier classification for healthcare insurance organizations, from critical clinical decisions to productivity tools.
Read more →A systematic framework for assessing generative and agentic AI risks across data governance, model training, output validation, bias, and regulatory compliance.
Read more →Principles and practical guidelines for ethical and responsible AI implementation in healthcare payor organizations, from governance structures to system operations.
Read more →Combining Outcome-Driven Innovation and Jobs-to-be-Done theory into product requirements that measure both customer job efficiency and business value.
Read more →How to transform product management from feature-centric to benefit-driven. Structured PRD methodologies show 45% higher adoption when focused on measurable outcomes.
Read more →A structured framework for evaluating software business impact across eight universal benefit categories — from operational efficiency to innovation.
Read more →Eight universal benefit categories that apply across all software types — from operational efficiency to innovation — with real metrics and implementation guidance.
Read more →
AI Implementation Group