You know what I’m talking about: a Claude generated UI. This was before some of the design skills were available @ github, but I have yet to see AI designs rival a human eye. This is the initial UI. I didn’t care about looks because I was more concerned on function. When I attacked the… Continue reading
Nemo Guardrails was providing rails for medical claims, assessing both inputs and outputs. Or was it? I’d integrated it early, specifically to catch medical intent; things like “will this cure my anxiety” or “what should I take for chronic pain.” Cannabis retail has real compliance exposure around medical claims, so guardrails weren’t optional. NeMo seemed… Continue reading
As a sysadmin many moons ago, I had about 5 email servers under my purview. Considered mission critical, I had a monitoring dashboard on my computer running at all times such that certain colored or blinking lights would alert me to a potential issue. Here I am again with a stack of cloud servers, so… Continue reading
I’m checking my own stack, after reading an excellent summary written by Shelly Palmer: How Anthropic Thinks About Agents, Workflows and Tasks. Her article is based upon a talk given by Barry Zhang/Anthropic at an AI Engineer conference in 2025. I’ll embed the video if you want to see his entire talk. Summarizing the summary:… Continue reading
for this Breaking News: Yesterday, a very prolific platform, Vercel, announced a security incident. You can read the details here. And guess who is using Vercel? Moi. So, I immediately prompted Claude to assess potential vulnerabilities in my stack. Fortunately, a decision I made early on for completely different reasons turned out to be the… Continue reading
(Continued from: Building It Right — Staging, Compliance, and Analytics) The previous three parts of this series covered the bumpy road from a laptop running Docker containers to a cloud-deployed system with a staging environment, compliance guardrails, and real observability. By the end of that phase, I had something I could stand behind. GPT-4o-mini was… Continue reading
(Continued from: Moving to the Cloud — and Finding the Right Model) By this point the core system was working. GPT-4o-mini was holding context, the product cards were giving customers a tangible output, and the hallucination problem was largely under control. I could have pushed to production and called it done. Instead I built a… Continue reading
(Continued from: What If a Dispensary Had an AI on Staff?) The local build had done its job. I knew the concept worked. I knew what the limitations were. Now I needed something I could actually demo to a dispensary owner without carrying my laptop into the store. The move to the cloud was surprisingly… Continue reading
A new category. I come across things that I feel compelled to play with and it likely doesn’t have anything to do with projects here. The first toy: Soot Spiral. This visual search came across my radar maybe a year ago. I recently re-visited it and was enthralled. Kinda makes me dizzy, but it’s nonetheless… Continue reading
(Continued from the AI Budtender Project) The AI Budtender is a customer-facing assistant that helps cannabis dispensary customers find products, get personalized recommendations, and build shopping lists — all powered by live inventory and purchase history. These are the details of the oft bumpy road that lead to the MVP. The first version was about… Continue reading