Skip to main content

Deep Dives

Case Studies

Technical build logs and architectural decisions behind each project. Real engineering problems, real solutions.

Native macOSPublished

PasteDrop: 8 Days From Idea to the Mac App Store

A macOS menu-bar clipboard utility shipped through a new ship-apps pipeline. The entire codebase was written in a 21-minute sitting across three commits, then landed on the Mac App Store eight days later. PasteDrop is the pilot of a repeatable scaffold + template + XcodeGen + CLAUDE.md + ASC playbook system.

21-min codebase8 days to live80 tests
Mobile DevelopmentPublished

Building PrayerMap: React Native + Supabase + Mapbox

Full-stack mobile app architecture: real-time prayer connections, Mapbox GL integration, 6-dashboard admin command center, and a 3-tier AI behavior monitoring engine.

46 edge functions6 dashboards3-tier AI engine
Design SystemsPublished

Ethereal Glass: A Design System from My Idea to Figma to Production

How PrayerMap’s UI/UX was born in Figma as the "Ethereal Glass" design language, translated into a production React web app, then migrated to React Native with a 470-line animation preservation spec bridging Framer Motion to Reanimated and Skia.

Figma to production470-line animation spec60fps native target
Developer ToolingPublished

Claude Code Toolkit: Production Infrastructure for AI Agents

An open-source toolkit adding agent orchestration, smart MCP loading, quality evaluation, session intelligence, and project bootstrapping to Claude Code.

13 skills7 agentsSmart MCP Loader
AI InfrastructurePublished

Neurotoken: Adaptive Thinking Allocation for Claude Code

A prompt scoring engine that replaces static thinking allocation with a two-axis complexity × stakes matrix, 11 model/effort tiers, verb-aware parsing, context dampening, adversarial-tested signal tuning, and an opt-in ceiling mode for cost-optimized downgrade — all in zero-dependency Node.js.

183 tests11-tier matrixActive-ceiling mode
Multi-Agent SystemsPublished

Directors Chair: Mission Control for an Autonomous Agent Fleet

A real-time mission control dashboard monitoring an autonomous agent fleet across job search, project maintenance, and infrastructure.

12 agents integratedBuilt on Mother HenLive and running
OraPublished

Ora: An Orchestration Framework Extracted from Production

Extracted from the production MCP-WP system. Coordinates Claude Code, Cursor, GitHub, Pinecone, LangSmith, and Slack into a unified development pipeline with file-based agent coordination and a 5-minute bootstrap, 15-minute daily oversight model.

6-tool orchestrationFile-based agentsExtracted from MCP-WP
MCP ProtocolPublished

MCP-WP: A LangGraph Architectural Prototype for WordPress Analysis

A LangGraph-based architectural prototype for multi-agent WordPress analysis. 27 agent personas built on 7 LangGraph agent types, with Pinecone vector retrieval and a live orchestration harness. Performance scoring and revision loops are stubbed; the sync layer and orchestration are production.

27 agent personas7 LangGraph agent typesPinecone vector retrieval
AutomationPublished

The n8n Advantage: 29 Workflows Automating Everything

How I built 29 production n8n workflows spanning AI code review, daily orchestration, Slack bots, Instagram content generation, and session intelligence classification.

29 workflows14 active261 nodes
Native iOSPublished

LivCut: Privacy-First Video Editing (In Development)

Building a professional video editor with 66 Metal compute kernels, 11 on-device AI engines, 382 tests, and 209 Swift files. All processing runs locally on the Apple Neural Engine. In active development.

66 Metal kernels11 AI engines382 tests
Multi-PlatformPublished

Challenge Cup: AI Caddie + Apple Watch + Garmin

Cross-platform golf tournament app spanning React Native, Apple Watch (SwiftUI), and Garmin Connect IQ (Monkey C) with AWS Amplify Gen 2 backend and AI-powered shot recommendations.

Apple Watch appGarmin Connect IQAI shot analysis
Mobile DevelopmentIn Progress

Puber: An Ultramarathon Support App, Built End to End

A community app for the 100-mile ultra world: connecting trail runners with pacers and crew, plus per-race coordination boards. Expo SDK 54 mobile app, a Next.js ops console, and a Supabase backend with RLS on every table, a Postgres match state machine, 14 edge functions, 5 pg_cron jobs, and an offline Race Kit. Safety is designed in as architecture. v1 is built and running locally; the target is iOS + Android for the 2026 100-mile season. Currently building.

25 migrations14 edge functionsRLS on every table
Multi-Agent SystemsIn Progress

GBuild: An AI-Native Build System

A macOS desktop app that orchestrates 12+ AI coding agents (Claude Code, OpenClaw, Hermes) from a calm, voice-first interface. Electron + a Rust sidecar over JSON-RPC, pluggable agent drivers, a whisper/Piper voice pipeline, a RAG layer, bidirectional Obsidian sync, and an MCP gateway. Two surfaces: an approachable "Lattice" shell and a power-user "Batcave" portal. Marketing site live at gbuild.app; the desktop app is in private development. Currently building.

12+ live agents~150 Rust source files2 UI surfaces
Data SystemsIn Progress

Johnson Power Rankings: A World Ranking for the 200+ Mile Ultra

A data-driven, weekly world ranking system for ultramarathon runners, launching with the 200+ mile distance tier. A pure-TypeScript ranking engine (course-difficulty model, iterative field-strength, time-decayed weighted-mean ratings, backyard scoring) over a Supabase backend with 11 migrations, RLS on 20+ tables, 6 edge functions, and a Monday recompute cron. A Next.js web app, a separate admin panel, and an Expo mobile app. Built with my dad as the domain expert, in roughly two days. Live in preview; public launch pending. Currently building.

Pure-TS rating engine11 migrations~2 days, 36 commits
Case Studies — Jeff Michael Johnson | Technical Deep Dives