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
(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
As much as I’ve enjoyed posting on Esprit de AI, maintaining two sites takes too much time. I’ve essentially copied Esprit de AI here to maintain the continuity of my AI journey. You’ll see more details on the projects taking shape as well as the tools I’m using and the ones I’ve discarded. Buckle up… Continue reading
I leaned heavily on ChatGPT (“Chat”—we’re on a first-name basis now) for automation and scripting guidance. We started in Zapier. Juggling actions, triggers, and scripts led to nothing but QuickBooks errors. So we switched to Make. After several rounds of modifications, Chat insisted I click an area to “Add another Line Item.” I couldn’t find… Continue reading
The Fork in the Road When ChatGPT 3.0 launched, I dove into prompt engineering like it was the only game in town. But models evolve fast, and these days even a clumsy prompt can get polished on the fly. Prompting is still important, but I wanted something bigger. So here I am, shifting my blog… Continue reading
Attention all Prompt Engineers! Read: “How I Won Singapore’s GPT-4 Prompt Engineering Competition” by Sheila Teo.
Continue readingIt’s titled “Navigating LLM Threats: Detecting Prompt Injections and Jailbreaks”. The virtual event will air at 10am PST on Tuesday, January 9th.
Continue readingLast time, I test-drove Taskade. Here’s a look at Miro, which looks like a virtual Post-It wall. After digging around and playing with it…wow!
Continue reading