✓ systems nominal — welcome to the Lyceum.
A school for the age of agents. Short essays on agentic AI — how these systems work, how to build them, and how to build them responsibly. Lessons here favor interaction over media: dialogues you can steer, terminals you can type into, ideas you can poke at.
Press / and type help — this site is navigable
entirely from the shell below.
latest transmissions
- 2026-07-11 How agents remember
Memory is not a feature you add to an agent — it is a decision about what the agent is.
- 2026-07-11 Introducing melchizedek
A capable model is not a capable system — coordination is what turns talent into predictable work.
- 2026-07-11 One agent, seven windows
How a market-analysis agent synthesizes many narrow data functions into a single defensible view.
- 2026-07-11 The patient advocate
An agent that remembers everything about your care so you can walk into the next appointment prepared — now live in melchizedek.
- 2026-07-11 The spec before the image
Predictable image generation comes from approving a JSON contract, not from polishing a prompt — reverse-engineered from one real print.
tooling
Open-source instruments built alongside the writing — starting with melchizedek, a multi-model, multi-agent orchestration framework. → all tools