For years I had ideas I couldn't build without resources I either didn't have, or had to convince others of the need and wait on someone's calendar. AI changed that.

A browser-based pattern workspace for crafters, and my main commercial product. In open beta now, with go-live planned for Q4 2026. You design a symbol chart by hand and it builds the chart, writes out the pattern, and checks the stitch math.

Manual-first, with no AI in the tool itself. One structured pattern model keeps the chart, the written pattern, and the follow-along mode in sync, plus a PDF studio, pattern grading, and garment schematics. Knit and colorwork studios are part of the same beta family, with quilting and more crafts on the bench.

A creative canon of 319 world-bible entries with enforced voice consistency, built with AI, for an original world. It also holds four constructed languages and a Voice Lab that speaks them aloud.

Enforced tonal registers per character type; a repeatable write → critique → revise → human-gate loop designed to produce consistent, canon-accurate output at scale without drifting into generic AI prose. Underneath sit four full constructed languages, each with three historical eras, on a deterministic engine, with a Voice Lab that pronounces any of them in a chosen character's voice.

The project I built to actually understand AI and learn its capabilities. An AI-native system for work: submit intent in plain language, it decomposes the goal into a task graph, routes work to specialized agents, and executes under human governance.

My deep end of the pool. Building it forced me through orchestration, durable workflows, agent design, knowledge persistence, and governance, the systems concepts that make AI genuinely useful instead of just impressive.

TypeScript · Temporal · PostgreSQL/pgvector · Next.js