Summary: I ran AI Engineer Coach, an open-source VS Code extension from Microsoft, over the past 90 days of my own agent sessions. The scan was humbling in a useful way. My prompts were usually det...

Summary: A coding agent did not make our small delivery team faster on its own. Most of the speed came from the standards we had spent the previous year writing down. The agent used what was alread...

Summary: The bulk store in my homelab ran as a two-disk RAID 0 stripe from the day I built it, for one bad reason: 33 TB sounded better than 18. It was holding about 955 GB, which is 3% of the arra...

Summary: For most of this year my AI lab has run entirely on hardware I own: a local speech pipeline, local models on one GPU, a retrieval layer over my own notes, and a set of assistants that talk...

Summary: Every architect carries a coin. One face reads agent of change, the other reads agent of chaos, and which one people see often has less to do with the quality of your work than with how mu...

Summary: My desktop copy of AnythingLLM now has fifteen custom agent skills and five flows. They answer the questions I actually ask about the lab: how it's doing, what's on the GPU, whether the ba...

Summary: I ran a usage tool across my AI coding assistants and it told me four weeks of work was worth $2,941.30. It wasn't a bill. Working out why it wasn't a bill meant actually mapping how four ...

Summary: Helen, the default voice of my lab assistant, picked up three new abilities this week: she can run a small set of real operations by voice, she can answer general questions instead of defl...

Summary: This is the last post in the series, and it's about the thing all the rest of it was for. At seven in the morning and seven in the evening, Helen tells me how the lab is. The interesting ...

Summary: Helen can restart services on my machines. That made me uneasy enough to spend more time on the boundaries than on the capability itself. This post is about where the limits live, and the...