Case studies
Selected engagements for operators, founders, and product teams — systems built to run
in production, not just look convincing in a deck.
Operations Software
Lab coordination for samples, staff, and drivers
Give a laboratory one place to prioritize tests, assign work across instruments and
people, schedule pickups, and let customers track orders the way they track a
package — less spreadsheet chaos, clearer handoffs.
Build
Cross-platform mobile and web clients on a shared API, with role-aware workflows
for scientists, drivers, and customers.
What it demonstrates
Multi-persona operations software: prioritization, machine/staff load balancing,
driver navigation/scheduling, and a customer-facing tracking experience.
Flutter
React
FastAPI
Python
PostgreSQL
AWS
Event Operations
Tournament desk for directors running live bowling events
Replace paper stacks with one desk for registration, lanes, scoring, standings,
brackets, and side pots — built for weekend directors and centers that need
software that keeps up when the lanes are full.
Build
React director desk and public results surfaces on a FastAPI/PostgreSQL backend
with payments, background jobs, and an embedded in-app coaching pack for complex
director flows.
What it demonstrates
Domain-heavy SaaS: tournament → event → round → squad → game modeling, batch and
match-play scoring, lane assignment boards, Stripe-backed commerce, and guided
UX for power users.
React
TypeScript
FastAPI
Python
PostgreSQL
Redis
Celery
Stripe
AWS Aurora
Legal Technology
Matter research desk with grounded answers for law firms
A local-first research workspace for matter documents — ask questions with cited
sources, run multi-user research sessions across assigned libraries, and keep an
always-on faithfulness gate before anything is emitted. Built for firm control of
data, ethical walls, and audit — not a generic chat wrapper over the open web.
Build
Rust API and workspace with local indexing, Ask and Research modes, firm installer,
Docker options, and a dark Live Desk UI for chat, stages, and source panes.
What it demonstrates
Grounded legal retrieval with a faithfulness council before emit, privilege and
ethical-wall enforcement, matter-scoped libraries, and operator tooling for
install, backup, and DMS connectors.
Rust
Cargo workspace
Local LLMs
Ollama
Docker
Playwright
TypeScript
Accessibility Software
Hands-free Windows control with gaze and gestures
Webcam-based cursor control for people who need an alternative to mouse and trackpad —
look to move, gesture to click and scroll, with guided calibration and a lightweight
control panel so profiles stay personal and recoverable.
Build
Windows desktop app with gaze tracking, MediaPipe hand landmarks, accessibility-tree
UI snapping, Alpine.js + pywebview control panel, system tray, and a single-file
release executable.
What it demonstrates
OS-level assistive input: eye-driven pointing, V-sign / pinch click, thumb scroll,
per-profile calibration persistence, and packaging for real Windows 10/11 machines.
Python
eyeGestures
MediaPipe
pywebview
Alpine.js
PyInstaller
Playwright
Product Enablement
In-app coach that teaches complex software in plain language
Drop guidance into any React product so customers can ask “how do I…?” and get
walked to the right button — fewer support tickets, faster onboarding, without
building a one-off chatbot for every screen. Training to improve answers stays
offline and separate from the sealed runtime customers ship.
Build
TypeScript monorepo: deterministic NLU packs at runtime, React host SDK, optional
ONNX ranker, plus a separate offline training pipeline that turns real “miss”
logs into better intents and aliases without rewriting production clients.
What it demonstrates
UI-actions-only coaching (spotlight/click guide IDs, never posting into product
APIs), pack-based domain extracts, and a runtime-vs-training split for auditable
product UX improvement.
TypeScript
React
Vite
ONNX
Playwright
Node.js
AI Infrastructure
Local capability broker so AI tools share one secure toolkit
Install once on a machine and give every assistant or IDE a controlled way to use
models, files, sandboxes, memory, and research — without each tool inventing its
own integrations, and with data staying local by default.
Build
Rust MCP server (stdio + HTTP) with a catalog → bind → invoke flow, SQLite-first
persistence, optional Postgres, Wasm module marketplace, and multi-language client
SDKs.
What it demonstrates
Harness-agnostic Model Context Protocol integration: one local broker many AI
clients can call, with safer Wasm-first extensions instead of arbitrary native
plugins.
Rust
MCP
Tokio
SQLite
Wasm
TypeScript SDK
Python SDK
AI-Assisted Delivery
Governed workspace for agent-assisted software changes
A local-first platform where AI agents propose small, testable slices of work —
and only proceed when gates and reviews pass. Built for teams that want agent help
with an audit trail, not a black-box SaaS rewriting the whole codebase overnight.
Build
Python/FastAPI orchestrator with event-sourced runs, Maker and Admin surfaces,
desktop launcher, and capability calls delegated to a local MCP broker for
models, sandboxes, and memory.
What it demonstrates
Adversarial, slice-based agent workflows with unanimous gates, projections over
an append-only store, and dual MCP bridges (IDE orchestration vs capability
broker).
Python
FastAPI
PostgreSQL
Alpine.js
Preact
MCP
Poetry
Research Tooling
Automated analysis for research datasets
Help academic and research teams stop hand-running the same stats over and over —
load a dataset, map findings to hypotheses, and get comprehensive coverage without
babysitting every test.
Build
Packaged Python desktop app (single-file distribution) with an embedded web UI
for interactive analysis.
What it demonstrates
Domain automation for non-engineering users: scikit-learn driven analyses,
PyInstaller packaging, and python-webview desktop chrome.
Python
Scikit-Learn
PyInstaller
python-webview
Engineering Productivity
Ask natural-language questions about any codebase
Turn a repository into something your team can interrogate in plain English —
useful for onboarding, audits, and documentation without sending the whole tree to
a third-party black box if you prefer local models.
Build
Desktop RAG pipeline with FAISS indexing, incremental updates, and optional
GPU-accelerated local LLM inference behind a FastAPI service.
What it demonstrates
Retrieval-augmented generation over source trees: index → retrieve → answer with
repository visualization and self-hosted model options.
FastAPI
Python
RAG
FAISS
Self-hosted LLM
Collaboration Demo
Shared whiteboard rooms for remote brainstorming
Spin up a room, invite collaborators, and draw together with chat — a lightweight
prototype you can try instantly to see how we approach real-time collaboration
products.
Build
Single HTML file with canvas drawing, host controls, and chat (emoji/images) —
no backend bill for the demo itself.
What it demonstrates
PeerJS / WebRTC peer-to-peer connectivity: rooms sync strokes and chat without a
custom signaling stack of our own, proving browser P2P collaboration end-to-end.
HTML5 Canvas
JavaScript
PeerJS
WebRTC
ML Operations
No-code path from trained models to production APIs
Let data scientists publish models as monitored API endpoints with controlled
inputs and outputs — closing the gap between notebooks and something operations
can actually run.
Build
FastAPI control plane with BentoML-style model serving patterns and AWS-hosted
deployment targets.
What it demonstrates
MLOps productization: packaging, versioned endpoints, input/output contracts, and
production monitoring hooks for DS teams.
FastAPI
Python
BentoML
AWS
