I help teams make AI work in the real world, and I write about what I learn along the way. I'm an AI and data science consultant. Most of my work is evaluating AI systems: reviewing machine learning code written by large language models, finding what's broken, figuring out why, and fixing it so it can be trusted. I also build practical AI solutions, from LLM-powered text classification and summarization to OCR pipelines and automation workflows. Over 8+ years, I've worked with clients and teams across healthcare, supply chain, real estate, finance and media, in roles from software engineering to data engineering to data science. What I write about: → Where AI breaks: the bugs, blind spots and failure patterns I see in AI-generated code, and how to catch them → Using AI properly: prompts, checks and workflows that make AI tools reliable → What the data says: hands-on analyses and lessons from real ML and NLP projects → Building a career in AI: honest advice from someone who got here the long way Everything I write comes from real work, not hype. If an article saves you an hour of debugging or one bad decision, it did its job. Working on an AI or data project and need a second pair of eyes? Reach out on LinkedIn. Follow to see new posts, or subscribe to get them by email. I read every response, so say hello.
