Broken Branch — a dev studio by Ben Schippers

A playground for the work I actually care about, built with Claude.

Interactive physics sims. AI tools. Production apps. Weird little explorables that don't belong on a resume. Microsoft is one side of the work — enterprise Copilot, at scale. This is the other side. Both real.

Flagship Projects

The work I care about most — physics sims, AI tools, and products I actually ship.

Everything below is built with Claude as the pair. How that works, in the writing.

Live

Vibecrafting

AI-powered physical product design from idea to shop-ready plans. Describe what you want to build, and Claude generates a full spec—cut lists, shopping lists, exploded views, and 3D-printable connectors that replace traditional joinery. Parametric geometry engine, OpenSCAD exports, and a brainstorm mode that suggests builds from your existing material stock.

Claude API Next.js 15 FastAPI Supabase OpenSCAD
Visit Site →
Live

ScoutsPlus.org

Gamified achievement platform for adults. Badge progression, troop management, photo-verified requirements, and Stripe-powered subscriptions. Full-stack production app with 19 database tables.

TypeScript Supabase Stripe
Visit Site →
Prototype

Canary

Prototype mutual benefit platform concept for tech workers. Pooled fund model with simulated risk modeling, employer-cap diversification, and a two-sided marketplace. Built the pricing engine, benefit calculator, and simulated claims workflow. Not a licensed financial product.

TypeScript Fintech Risk Modeling
Visit Site →
Demo

Bi-directional RAG

Collaborative knowledge system where AI doesn't just read—it maintains, labels, and improves the knowledge base. Natural language intent detection, auto-tagging, confidence scoring, and real-time orchestration view.

Python ChromaDB Claude API
📷 View Screenshot
In Dev

Workstation Zero

Distraction-resistant desktop environment. Full-screen CRT terminal aesthetic with Pomodoro integration, focus-gated media, and embedded productivity tools.

PyQt6 Python Deep Work

Writing

Behind the Screens — thoughts on AI, product, and building in public

Growth Rings — 10 Months of Job Searching, Building, and Shipping with AI

203 applications. 76 rejections. 34 ghosts. 2,710 GitHub contributions. 6 live products. A data-driven cross-section of 10 months in the 2025-2026 tech market — the funnel, the ghosts, what actually worked, and the parallel build sprint that changed the trajectory.

Read the Data Story →

The Productive Compute Framework

Self-sustaining AI infrastructure for global public good. A framework for converting idle compute capacity into verified outcomes through UN outcome-based funding. Whitepaper, DRAFT v2.0.

Read the Paper →

If You Can Read a Recipe, You Can Now Be a Developer

The $1K Experiment Part 2: What happens when the framework compounds. 5.5 hours to working MVP. 2,031 lines became 106,000. Shipping is addictive—here's the warning label.

Read on LinkedIn →

The $1K Claude Code Credit: What Happens When a PM Learns to Ship

Could a senior PM with product clarity but no coding background actually build and ship real software? 31 days, 215 commits, 38K lines of TypeScript. The 64/33/3 collaboration model that made it work.

Read on LinkedIn →

The 90-Day Death Spiral: Why 95% of AI Projects Fail

Research suggests only 5% of AI pilots deliver measurable impact. The early warning system hiding in your support tickets—and the metrics that predict failure before day 90.

Read on LinkedIn →

Labs

Experimental projects and works in progress

In Dev

∞-ball

Interactive exploration of mindfulness and mechanics. Blending hard science with contemplative practice.

TypeScript Experimental
Coming Soon

C-Monkies

Multi-platform simulation game. More details coming soon.

Unreleased
In Dev

Dead Radius

Location-based ASCII survival simulation. Uses real geography for procedural world generation.

C# Geo-based
Demo

Quantum Oracle

Randonautica-inspired exploration experiment. Quantum entropy from ANU's RNG scattered across a map, statistical anomaly detection to find clusters, and OpenStreetMap verification to confirm you can actually walk there. An excuse to stitch together a dozen APIs and see what breaks.

React TypeScript Quantum RNG
Visit Site →

Backstory — The Arc

Ten years at Microsoft, a 10-month gap where shipping in public became the job, and back at Microsoft since March 2026. The numbers, the case study, and the CV live below for anyone who wants them.

Background

Microsoft

Senior Program Manager, AI Platforms & Enterprise Operations

Across 5 years, spanning Copilot · Graph · Windows 365 · Teams Devices

Owned a portfolio of internal platforms across 8 product lines—signal systems, routing intelligence, self-service tools, and quality measurement. The infrastructure that turned customer friction into engineering action.

  • Rebuilt the signal-to-engineering pipeline from scratch. 95+ features shipped through this system; adopted org-wide.
  • Built routing intelligence that classifies incoming work by complexity and matches it to the right skill level.
  • Scaled self-service from pilot to ~50% adoption on flagship products. Tens of thousands of tickets per year that never get created.
  • Created early risk detection identifying 700+ at-risk customer situations before they escalate.
  • Built and shipped a recommender reaching 14K enterprise customers with 14% conversion.
  • Led crisis response for a 433K-user transition—near-zero churn.

Microsoft Premier Support

Built Premier Engineering from a 3-person pilot to 150 agents handling 60K incidents/year.

Managed partner programs spanning 1,000+ Office 365 migrations across 12 global partners.

Education

B.S. Interdisciplinary Science & Technology — University of Arizona

Former dendrochronologist. Yes, tree rings. It's where the domain name comes from.

Case Study: Copilot Extensibility — From Silos to Signal

Led the cross-functional effort to build enterprise AI adoption intelligence across multiple product lines. Created the signal-to-engineering pipeline that identified 76 blockers, unblocked 7,380 users, and contributed to 94,000 seats added.

76 blockers found 7,380 users unblocked 94K seats added 47% self-help success

A major enterprise AI rollout was accelerating across multiple product lines with no shared visibility into adoption patterns. Customers were hitting adoption walls that no single team could see. I assembled a cross-functional team, deployed real-time case analytics, and built the feedback loop that turned support signal into engineering priorities. The framework created a sustainable system for surfacing and resolving adoption blockers across the enterprise AI ecosystem.

By the Numbers (Microsoft era)

3 → 150 agents Co-founded the program, hired the team, built the playbook
700+ blockers Surfaced from support signal that product teams couldn't see
95+ features shipped 64% of requests submitted to engineering accepted
220K users unblocked Adoption walls removed before they became churn events
94K seats added Customers who expanded after we resolved their blockers
$355M+ aggregate value Across retained ARR, cost avoidance, and growth enablement

Let's Talk

If something here sparked an idea — or you want to trade notes on building weird things with Claude — reach out.

Atlanta, GA

Ask about Ben's work Powered by Claude

Hey — I'm the site's AI assistant. Ask me anything about Ben's background, projects, or the Productive Compute Framework.