Writing
Perspectives on what enterprise AI demands next: accountable agents, measurable value, workforce readiness, industrial transformation, and reliable systems.
Essays
Long-form deep dives on important topics
Agents Need an Operating Model Before They Need More Autonomy
The hard part of enterprise agents is not building another agent. It is making authority, evaluation, exceptions, security, and ownership explicit.
The AI Roles Employers Actually Need: From Tool Fluency to Enterprise Execution
AI literacy is spreading, but employers need something harder to hire for: people who can redesign work, manage risks, and prove business results.
The Next AI Advantage Is Operational, Not Just Digital
The next difficult AI problems live in factories, logistics networks and service operations, where local context and operational trust matter more than demos.
Why AI Productivity Gains Disappear Before They Reach the P&L
Time saved by an AI tool is not automatically economic value. A practical accounting model for turning AI activity into measurable operating results.
Why RAG is Harder Than It Looks
Retrieval-Augmented Generation seems simple in demos but breaks in a dozen ways in production. Here's why most RAG projects fail and what to do about it.
The Hidden Cost of Technical Debt
Technical debt isn't just about messy code—it's about compounding decisions that slow teams down over time. Here's how to measure and manage it effectively.
Reliability Patterns in Production AI: Designing for Graceful Failure
Your AI system will have its worst moment in front of your most important user. Strategic approaches to designing systems that fail gracefully instead of spectacularly.
User Trust in AI Systems: Strategic Approaches to Adoption and Reliability
As AI systems become more prevalent, user trust becomes the limiting factor for adoption. Strategic insights on designing trustworthy AI products that users actually adopt.
The Unglamorous Parts of AI Engineering
Twitter shows AI demos. Production requires data pipelines, permission systems, eval harnesses, and on-call rotations. Here's what AI engineering actually looks like.
Posts
Shorter articles and tactical insights
How to Debug a Failing RAG Pipeline
Your RAG system is returning bad answers. Here's a systematic approach to find out why and fix it.
Prompt Engineering Patterns That Actually Work
After writing thousands of prompts, these are the patterns that consistently improve results. No magic tricks—just engineering principles.
Agent Architecture Fundamentals: Tool Use Patterns for LLM Systems
Understanding the architectural patterns behind LLM agents with tool use. Establishing the core loop and design principles that define how agent systems work in production.
Enterprise Chatbot Failures: Strategic Lessons from Production Deployments
Five critical patterns that separate successful enterprise chatbots from failures. Strategic lessons from production deployments that define how chatbots should be architected.
Testing AI Systems Beyond Vibes
Looks good to me is not a testing strategy. Here is how to build a real evaluation framework for AI systems that actually catches problems.
When to Use RAG vs Fine-Tuning
Two approaches to customizing LLMs for your use case. Here's a practical decision framework for choosing between RAG and fine-tuning.
Five Principles for Scaling Engineering Teams
Lessons learned from scaling teams from 5 to 50+ engineers while maintaining productivity and culture.