Skip to content
MG
Work

Case studies, not screenshots

Each of these covers the same ground: what the problem actually was, how the system is shaped, the decisions I would defend in a review, and the failures worth writing down.

ProductMay 2026 — Present
Active

PROM

An AI-native operating system for product development

Six deployables, 274,000 lines, a company of two. PROM takes a team from raw idea to shipped product inside a single workflow engine, where every artefact — personas, decisions, specs, tasks, launches — lands in a knowledge graph the AI reasons over. I co-founded it and own the technical side: the NestJS core API, the Python inference service, the Postgres/pgvector graph, billing and entitlements, the customer web app, an internal staff console, and a CLI that puts the whole thing inside your editor over MCP.

274k

lines of code

6

deployables

337

REST endpoints

69

Prisma models

NestJSPythonpgvectorMulti-tenantLLM tooling
Read the case study
Competition2024
Prototype

Porsche Customer Relations Hub

Winning entry — Porsche Digital Campus Challenge

An AI-powered customer relations platform for Porsche: a multi-modal assistant that resolves owner issues in the My Porsche app using semantic retrieval over Porsche's own knowledge sources, paired with an agent console that gives human CR staff the full session context the moment a case escalates. Our team took first place in the Customer Relations track.

AI agentRAGMulti-modalAWS
Read the case study
Platform2024 — 2025
Prototype

SociaLink

A unified operational data store for social presence

SociaLink pulls a person's activity across social platforms into one operational data store and makes it answerable in plain language. Built as a polyglot-persistence exercise that turned into a real system: layered ingestion pipelines, hybrid full-text and vector retrieval, and an assistant with awareness of the whole store rather than a single document.

DjangoPolyglot persistenceHybrid searchDocker
Read the case study
Open source2026
Shipped

prom CLI & MCP bridge

Live product context inside a coding agent

A published npm package that links a customer's repository to a PROM product, keeps an ambient context block in sync inside their agent instructions file, and proxies PROM's MCP server over stdio — so a coding agent can ask what to build next, read acceptance criteria, and report work back, without a human relaying any of it.

MCPCLIDeveloper toolingTypeScript
Read the case study