Welcome to my blog. Here I share practical insights on AI implementation, lessons learned from building RAG systems, and thoughts on bridging the gap between industrial expertise and artificial intelligence.
Whether you're an engineer exploring AI, a company evaluating AI solutions, or a developer building intelligent systems—you'll find actionable content based on real-world experience, not just theory.
Back to Basics Series I: The Origin
A simple bracket-balancing problem from a technical interview sparks a back-to-basics series. First pass: no AI, just a stack and clear thinking. Then we hand the same problem to an LLM with a Socratic prompt.
Testing the Chaos: Why LLM Failures Move Our Work Upstream
When an LLM fails deep inside your code, how do you test that? The answer reveals how AI shifts the real engineering work upstream—into system design, boundaries, and fault tolerance.
AI Doesn't Remove Work: It Moves It Upstream
AI didn't make developers obsolete—it shifted the bottleneck. From 20+ years in oil and gas to writing software with AI: why the real work is now upstream, in thinking, design, and judgment.
From Drilling Engineer to AI Engineer
Why 22 years in drilling operations made me a better AI engineer—and why domain expertise is the missing ingredient in most AI projects.
The Hidden Cost of Buried Knowledge
Your engineers spend days searching through manuals for information that should take seconds to find. Here's why it happens and what to do about it.
Building a RAG System for Technical Documentation
A step-by-step walkthrough of building a production-grade RAG system for analyzing academic papers—from document parsing to deployment, with actual code and architectural decisions.
Why Most AI Projects Fail (And It's Not the Technology)
After analyzing 800+ enterprise leaders and reviewing industry research, the pattern is clear: 80% of AI projects fail—and technology is rarely the culprit. Here's what actually derails AI initiatives.
The Engineer's Guide to Evaluating AI Vendors
Stop getting dazzled by AI demos. Here's the technical framework engineers need to evaluate AI vendors, spot red flags, and make smart build-vs-buy decisions.
If you have read some of my posts, you have realized that I love AI, but am also aware of the power it steals from us. I used to feel joy in programming, but since the arrival of "vibe coding", this seems not to be anymore true.
A student in our AI with Python cohort recently sent me an email that struck a chord.
"I have no special talent. I am only passionately curious." — Albert Einstein
The demo was flawless.
Three months into a $500K AI project, the CTO of a manufacturing company stared at a dashboard that should have been optimizing their production line.
Your company has hundreds of pages of technical documentation. Your engineers need answers fast. Traditional search returns keywords, not answers. RAG (Retrieval-Augmented Generation) changes that—turning static documents into an intelligent assistant that actually understands questions.
Here's how it works and how to build one.
After 22 years in oil & gas drilling operations, I made the leap to AI engineering. Many people ask me why I didn't make the switch earlier—or why I bothered with AI at all when I had a successful engineering career. The answer is simple: I realized that my industrial experience wasn't something to leave behind. It was my competitive advantage.
Your company has the documentation. The procedures exist. The technical standards are written. So why does your team still spend days searching for information that should take minutes to find?
After 22 years in drilling operations, I lived this problem. And now I help companies solve it.