In my previous post comparing subagent chaining against agent teams, I built a five-agent roster, ran the same application through it three times under three different coordination models, and put a note in the middle of
I was speaking to a colleague the other day about how LLMs process tokens and predict the next word (discussing the technical details of LLMs excites me), and when I brought up speculative decoding, which
Claude Memory is one of the most misunderstood features in AI tooling today. In my work as an architect, I end up in a lot of conversations about AI developments, and one topic I keep
I spent some time testing LM Studio Bionic a week after it was released on July 16, 2026 and the experience immediately was what inspired me to write my previous blog post The Gap Between
Why the Future of Local LLMs Doesn’t Depend on Being the Best I’m going to do something very different from my usual blog posts, which typically fall into one of three categories: A walkthrough of
I’ve always found that keeping up with technology news was difficult and while there are plenty of mailing lists you can sign up for, the emails coming into your inbox, no matter how
As a follow up to my previous post: Handling truncated Logic App AI Agent output for autonomous agent workflows without human interaction … where I ran into and worked around truncated AI agent output, I
Browser MCP LM Studio is the setup I’ll walk through in this post. 2025 has been the busiest and probably the most demanding year of my career. While I’ve gone through periods of long work
While Open WebUI is typically used with locally hosted LLMs, it is possible to configure it to use cloud hosted LLM services such as OpenAI and Azure. I work primarily in the Azure space and
As a follow up to my previous post: Running LLMs on a local PC with Ollama Interacting with Large Language Models (LLMs) via the console is often not the most efficient method for leveraging the
