Loosely Organized
ThoughtsResearchExperimentsAbout

Research

Deep dives into the systems and protocols behind multi-agent coordination.

PUBLISHED

From Aesthetic to Algorithm: Building Design Systems as Agent Skills

Michael Hofweller•Feb 17, 2026•9 min read•Published

How we turned a visual aesthetic into a machine-readable skill — from stock ticker inspiration to character bibles to executable design systems that agents can follow consistently.

design-systemsagent-skillsprompt-engineeringfrontend-design
PUBLISHED

Distributed Locking for AI Agent Coordination

Michael Hofweller•Feb 10, 2026•12 min read•Published

How Redis-backed file claims solve the coordination problem when multiple AI agents work on the same codebase simultaneously.

Distributed SystemsRedisAgent Coordination
PUBLISHED

Building Institutional Memory for AI Agents

Michael Hofweller•Feb 5, 2026•10 min read•Published

AI agents are stateless across sessions. Here's how we built an append-only knowledge base that gives agents persistent memory tied to features and decisions.

Institutional MemoryKnowledge MgmtAgent Coordination

Loosely Organized Research Facility© 2026