Lance Keay · Senior full-stack & DevOps engineer
I build software and keep it running. Then I write down what actually broke.
This is my CV and my working notebook: hands-on reviews of AI tools, agents and self-hosted software, plus a monthly look at what model tokens actually cost.
Latest notes
The verdict first, the detail below it.
- Keep I run it
- Try worth an afternoon
- Wait not yet
- Skip I wouldn't
Sample entries. These listings show how posts and verdicts are laid out; titles and verdicts are placeholders until Lance publishes the real ones.
-
AI token market, November 2026
In one line: input, output and cached-token prices per million for the main hosted models, in one wide table, with what changed since October.
Monthly12 min read -
LiteLLM as a home-lab model gateway: three weeks in front of four providers
In one line: worth running the moment you call more than one provider; not worth it if you only ever call one.
Keep14 min read -
Two weeks of a terminal coding assistant in a real repository
In one line: quick and tidy on small, well-described changes; you still have to hold the plan.
Try11 min read -
Moving the home lab from Compose files to a self-hosted PaaS
In one line: nicer deploys, but I gave up more control over networking than I wanted to.
Wait9 min read -
Leaving a coding agent running unattended overnight
In one line: it finished the tasks and broke the tests it never ran. Not yet.
Skip8 min read
Hire me
The feature shipped, and the pipeline still green.
I take contracts for full-stack work and the infrastructure under it: CI/CD, containers, cloud and on-prem, and putting AI tooling into a team's workflow sensibly. Remote first; on site by arrangement.