Insights for the Rest of Us
Analytics and AI without the intimidation. Plain-language guides to SQL, data work, and practical AI — examples you can use at work, a little humor, no PhD required.
Latest posts
All articles →
One local stack end to end (Ollama-style)
Kenji had Ollama, LM Studio, and a Docker llama.cpp on three ports, then sent a prompt to the one that was off. This part picks one local stack, walks a 30-minute Ollama path, and shows where the model file and the RAM live.
Quality without benchmark theater
A Slack screenshot with a model two slots above Llama is not a quality test. Run five real tasks from your week,…
Docs: outline to draft with control
Docs plus Gemini stays useful when you control the path: brief, outline, section drafts, human facts, then voice edit. Part 2 of…
Friendly desktop runners from zero
Desktop runners like Ollama and LM Studio are how normal people get open weights onto a laptop. Install one app from the…
Privacy reasons normal people care
A local desktop runner can still ship your prompt to a host if cloud mode is on. This part maps what leaves…



