Thanks for this thoughtful write up of your process. I’m increasingly thinking about what context the model has and keeping it as focused as possible - both to reduce token usage, and to ensure it doesn’t have any cruft in it that potentially causes the model to go down an un-useful path. The prompts for this read like what I imagine a conversation with a junior developer would be when handing off a task.

In practice, this is usually clearing the context after quite small changes and the prompting for the next one with just what I think it is going to need. I guess this is ‘context engineering’ although that sounds like too fancy a term for it.

Proxmox on the metal, then every service as a docker container inside an LXC or VM. Proxmox does nice snapshots (to my NAS) making it a breeze to move them from machine to machine or blow away the Proxmox install and reimport them. All the docker compose files are in git, and the things I apply to every LXC/VM (my monitoring endpoint, apt cache setup etc) are all applied with ansible playbooks also in git. All the LXC’s are cloned from a golden image that has my keys, tailscale setup etc.