Portfolio.

Two products in one project. (1) A local cockpit for multi-tool software development — assignment registry, two-phase actor handoff, coordination-event log, MCP server, CLI, Chrome extension; the operator-side measurement layer AI coding tools' agent-side metrics miss. (2) The portfolio's shared engineering brain — pattern library, architecture maps, session handoffs, cross-project assignment registry, API registry, decision log, capabilities catalog, and the capability-architecture doctrine the whole portfolio is built against.

Gridiron Platform — a fantasy football platform built around four converging efforts: a GM Command Center (lineup, waivers, trades, draft, rankings), a Python analytics API (PRISM and CAMS frameworks ported to football), an Insight Card system (PRISM trend / CAMS alignment / market-signal cards composed across surfaces), and Strategy League / Football IQ (a coaching-strategy game layered on fantasy leagues with a simulation engine).

A name chosen, not stumbled upon. Every baby-naming product helps parents find names; Namesake is the only one that helps them choose one. Built on twenty years of weekly search data, a per-name composite score (SSA stats × LLM-enriched meaning × cultural-event attribution), a tournament-bracket decision UX with village voting, and a cultural-diffusion research apparatus underneath.

A contemplative platform that began with fine-art figurative work and has broadened into four things at once — an Image System (player + Reveal + composites), a five-layer Written System (analytical essays · Mosaic testimony · fiction · readings · submissions), a Narrative Intelligence Platform (three-domain editorial spine), and an Adaptive Authorship substrate the rest of the portfolio is built to sit on top of. Editorial Office, Penwright in /labs, Artist Studies arcs (Warhol shipped; Schiele / Klimt / Sargent staged), and a preregistered research program at /study running underneath.

An AI-augmented authorship system — corpus control, packet-shaped composition, and a measurement framework that asks whether the writer is better with it, than without it, in six months.

Protected feedback and performance intelligence platform — surfaces what employees can observe but cannot safely say, scores team-level Capability / Alignment / Motivation / Support (CAMS), and renders one binding-constraint card per team. Precompute-and-playback architecture — the iTunes of analytics, not a dashboard. First external MCP consumer of the People Analytics Toolbox.

Two-shell production-factory substrate for the portfolio — an engine (OLD, AI-controlled, no human UI) that ingests books and research at chapter-respecting fidelity and runs a roster of named factories (Persona Factory, Survey Factory, Competency Factory, Models Factory, Requirements Factory, Prompt Factory, Publishing Factory, Business Ideas Factory, Application Designs Factory) producing canonical outputs; and an API host (PROD, Vercel) that exposes a v1.2.0 REST + MCP contract plus a cross-portfolio library layer (Stream 7, ~944 records) the rest of the portfolio reads from.

Independently-versioned analytical microservices for people analytics — psychometric diagnostics, preference modeling, privacy primitives, segmentation, statistical enrichment, compensation logic, decision forecasting, metadata-grounded codegen — deployed as a single Next.js application and exposed over two transports: HTTP for engineers, MCP for AI agents. One Vercel project, one Supabase project. The behavioral and statistical substrate consumer apps compose against.