Elizabeth Stein4/8 systems responding · 

Full-stack developer & designer

ElizabethStein.

I design and build software that’s actually running in production. Eighty-six things shipped — here are the eight that matter, live right now.

Open to contract workEnterprise · AI · Full-stack · Dev tools
Get in touch →Download résumé
4/8
Live systems responding
Checked in real time, right now
86
Projects shipped
Enterprise · AI · full-stack · dev tools
3
Organisations
Production code, three teams
3.98
GPA, Summa Cum Laude
B.S. Software Development, Capella
Selected work — 08 / 86click a row to open the case

The problem

Managed-service providers had no fast, credible way to measure a client’s cybersecurity readiness — assessments lived in spreadsheets and consultants’ heads.

What I built

A guided assessment on Dynamics 365 / Power Platform with a Next.js front end. Twelve phases from data model to scoring to reporting, shipped solo across the full stack.

Proof

Live in production and in use by a cybersecurity nonprofit. Sole developer — data model, business logic, front end, and deploys.

12
Phases shipped
1
Developer (me)
Prod
Status

Context

Agency work — a portfolio of client sites that each need to ship fast, stay maintainable, and share a design language without becoming copy-paste.

What I do

Build and maintain eleven Craft CMS sites in PHP and Twig, with reusable components and content models tuned for non-technical editors.

11
Live client sites
PHP
/ Twig / Craft

The idea

Enter any date from 1958 to 2020 and get the cultural snapshot — the #1 song, the movies, the prices, the news — synthesized into an era-aware narrative. Not “what was #1 in 1975” but what that day felt like.

How it works

A date is parsed, then four Algolia indices (Billboard, TMDB, FRED prices, Wikimedia events) are queried in parallel and an LLM synthesizes the results into one narrative, rendered in a shareable CRT/VHS aesthetic. Next.js 16 with Upstash rate-limiting and Langfuse LLM observability.

Why it matters

The one project here with an externally-verified outcome: it won the Algolia Agent Studio Challenge against a judged field of entries.

$750
Algolia Agent Studio win
420K
Records searched
4
Data sources fused
Try it live ↗Read the write-up ↗Full case study →

What it is

Point it at a repository and it narrates how the code fits together, exposing 14 Model-Context-Protocol tools so an AI agent can explore the codebase with structure instead of guesswork.

14
MCP tools
npm
Published, installable
View on npm ↗Full case study →

The idea

Most screenshot-to-code tools hallucinate components that don’t exist in your system. Trace grounds generation against a real catalogue, so what comes out is code you can actually merge.

★
DEV.to contest win
38
Tests
Live demo ↗GitHub ↗Full case study →

What it is

Feed it your sources and it answers documentation questions with RAG — a full product with subscription tiers, auth, and Stripe billing wired in, not a demo.

Live
SaaS with billing
RAG
+ Stripe / Next.js
Visit live ↗Full case study →

Why it exists

The most lived-in thing here: the command-line tool I built to run my own operation — one interface over ~90 repositories and 10 services. I use it every day, which is the real test.

216
Tests passing
~90
Repos managed
10
APIs wired

What it is

Practise interviews out loud with a voice agent on the OpenAI Realtime API, with FSRS-5 spaced repetition scheduling what you review next. A live SaaS.

Live
SaaS
150
Tests
Realtime
OpenAI voice
Visit live ↗Full case study →
+ 78 more, shipped.
Experiments, dev tools, and games — the lab where the eight above got their reps. Browse the full catalogue, or explore it as a galaxy.

B.S. Information Technology, Software Development— Capella University, Summa Cum Laude (3.98 GPA). Shipping production code across three organisations.

AboutWorkContactRésuméGitHubLinkedInEmail
Elizabeth Stein — 2026Enter the galaxy →