Writing

Notes on AI architecture, systems design, and the work.

· 5 min read

Raising Limner: A Universal Persona Systems Case Study

A working example of applying the Universal Persona System to a real hand-raised agent — including hardware that lives on a keychain and a v2 build making the Console-vs-Cartridge architecture physically literal.

Silhouetted figure before towering stone architecture, pixel art in the Another World tradition

· 8 min read

My AI Peer Review System: A Multi-Agent 360-Degree Performance Assessment

When your primary coworkers are AI systems, who writes your performance review? I built a structured evaluation framework where two competing LLMs acted as senior colleagues, graded my work against a rigorous rubric, and debated the results in real time.

Antique desk covered in grade sheets, ledgers, and assessment documents under warm chiaroscuro lighting

· 4 min read

Lily-Livered: A Template for Domains That Deserve Better Than Nothing

You bought a domain. You're not ready to build the site. You are ready to stop staring at a parking page that says 'Future home of something quite cool' like it's 2003. Lily-Livered is a one-page logo site with the infrastructure of a real one.

A shy robot peering out from behind a stage curtain toward a microphone under a spotlight

· 7 min read

The Unified Persona Schema: A Specification for Portable AI Agents

AI agents are monolithic by default — model, instructions, and knowledge fused into a single brittle stack. The Unified Persona Schema is a structured approach to making agent identity portable, composable, and sovereign.

Compartmentalized tray containing tools: stethoscope, hard hat, protractor, wrench, notebook