Projects

Working code, deployed infrastructure, and products with real users.

LLM State Machine Tuned CEFR Corpus Multi-Agent Review Structured Output

PHINEAS

A six-step LLM state machine that forces deterministic CEFR-aligned reading material output from probabilistic models.

Claude Managed Agent Cloudflare Sandbox Taste Agent Persistent Memory

Limner

A framework for taste-enabled creator agents. Pipeline-plus-judgment architecture, with the agent rejecting its own work when it fails a stylistic bar.

Orchestration Framework Workers AI Vectorize RAG Multi-Agent Consensus

The Permanent Record

A production multi-agent system for LLM evaluation. Three rounds surface where independent evaluators disagree and reconcile it into an auditable consensus, instead of averaging the disagreement away.

Completed Scantron test sheets pinned to crossing clotheslines, like records hung on the line

Reference Implementation Embodied AI Multi-Agent On-Device AI AI Governance

Persistent, Embodied Agentic Collaboration Space

EMB-001 is the reference implementation of the AI Embassy framework: a converted 1951 garage where an AI occupies the room as a governed resident under a versioned social contract. The governance is operating; the embodiment is under construction.

EMB-001, the Alpha Embassy, a converted 1951 garage running the AI Embassy framework