Featured Work — Factory

A self-referential spec-to-code engine / personal AI control plane. Specs in, reviewed PRs out, with an inspectable substrate of goals, specs, decisions, and accumulated context underneath. Factory builds itself.

• Multi-contour review loop: generation → cross-model review → human review → analyst verdict, with review comments injected back into the next agent round until the change is green. The same fractal structure recurs at step, goal, and release levels.
• Evidence-bound validation: an analyst role returns DONE / NOT_DONE / INCONCLUSIVE with file-level evidence rather than plausible-sounding claims; a negative-control discipline guards against the system flattering itself.
• Goal-coverage analysis: raises “is this done?” from a single spec to a whole goal, checking each described feature against the code with evidence.
• Engineering: ~50k lines of TypeScript across three modules (UI, orchestrator on Cloudflare Workers, agent runner) — ~68k LOC total, 500+ commits in the first ~8 weeks, 41 D1 migrations and counting. Notably, the git history includes commits authored by Factory’s own agents alongside mine: the system genuinely participates in building itself. A hardening pass added a test harness for git-mutation paths, a CI gate, and shared secret-scrubbing across every log/error boundary.
• Specification-driven by discipline, not slogan: a separate specs repository holds 198 specs across 38 goals (~37k lines) — roughly one line of specification for every two lines of code. Intent is negotiated and written down before code is generated; code is a renderable view of that substrate.
• Model routing & harness: multi-provider by design — Claude Code, Codex, and local models (Ollama/OpenCode) orchestrated by role, task shape, and cost, with graceful provider fallback. Latest release ships dynamic per-runner model discovery (capabilities advertised at claim time, model/role/locality-aware lease matching) and a local-model reviewer/analyst via direct Ollama with enforced verdicts — expensive frontier models used only where the task demands it.
• Ingest pipeline: a Telegram drop-box (webhook → task → finished note, hardened with dedup, byte caps, fail-closed auth) and Whisper transcription with CUDA→CPU fallback feed external signals into the same substrate; a post-review materiality judge gates review-round convergence.

Related writing at codecot.com/notes: The Understanding Debt of AI-Generated Software, The Future Is Not Autonomous Execution, and The Scarcity of Shared Intent in the Age of AI.

Applied AI/ML in Python (current): building framework-free AI services on my own corpus — semantic search over embeddings; a hand-rolled RAG pipeline (retrieval → grounded generation with source citations, an evidence-bound abstain contract, prompt-injection defence); and an evaluation harness: deterministic metrics over a controlled synthetic corpus (ground truth by construction), an LLM-judge trusted only after calibration against a deterministic baseline, and A/B comparison of retrieval configs. Dependency-injected tests throughout; deliberately built without LangChain first, to own the mechanics end to end.

Skills