Agents
How Long Should an AI Agent Live? The Hidden Cost of Keeping Agents Alive
I thought long-lived agents would become smarter, but they drained my cloud tokens and introduced context rot.
AgentsVideo
From Architecture to Demo: Jev, Skills, and Agentic Incident Enrichment
The result brings together several concepts I've covered in previous posts, but this time in a working demo.
AgentsVideo
Agentic Incident Enrichment, the Lowest Hanging Fruit of Agentic IT Use Cases
Finding practical enterprise use cases for agents, without handing them the keys to the data center.
Lab Build
Llamagate: A Gateway in Front of My Home Lab's Ollama
Llamagate is a transparent reverse proxy for Ollama that adds token usage counting today, with observability and access control on the roadmap — built…
Applied AI
CatWatch: Computer Vision on the Edge
A family project — detecting which cat is at the door using a local model, because cloud APIs don't need to know about my cats.