Skip to main content
Elizabeth Stein
Experiment LabOpen to workHomeWorkAboutContact

Case study

experimental2026

AI Spend Tracker

Track and analyze spending across OpenAI, Anthropic, and other AI providers. Budget alerts, usage breakdowns by project, and cost optimization recommendations.

Where wild ideas take flight and curiosity leads

Field notes

Role

Creator

Read order

Evidence first, then constraint → build → proof. Use the chapter rail to jump sections; orbit to adjacent work from the bottom of the case study.

The Experiment Lab·✦II-Class Star

Evidence

Interface & evidence

A real surface area—not a mock. Scroll the story below for constraint, build, and outcome.

Signature viewpreview
AI Spend Tracker application interface

Story arc

How this shipped

Where wild ideas take flight and curiosity leadsThree beats: what pressed against the work, how the stack answered, and what changed once it was live.

I · Constraint

The brief

AI API costs add up invisibly across multiple providers and projects. Developers get surprised by monthly bills.

II · Build

The craft

Built unified dashboard aggregating costs across providers. Budget alerts with Slack/email notifications. Per-project cost attribution and optimization suggestions.

III · Proof

What moved after launch

Single view of all AI spend. Budget alerts prevent overruns. Optimization tips reduce costs 20-40% for heavy users.

Inventory

Stack & signals

Next.jsTypeScript
← Project archive

Tell me what you're building

If you need someone who can own UI, systems, and AI integration without losing the plot—I'm listening. Contract, advisory, or full-time: we'll find the right shape.

Start a ConversationSee More Projects

Related work

Same clustersignal 3
Signal: Medium
Next.jsTypeScript

Competitor Stalker

Competitive analysis tool for tracking competitor websites, features, and market positioning.

Same clustersignal 3
Signal: Medium
Next.jsTypeScript

RunwayOS

AI-powered financial runway predictor for SaaS founders. Tracks MRR, churn, and burn rate to forecast exactly when money runs out — with scenario modelling for different growth trajectories. Dashboard UI with metric cards and predictive charts.

Nearby systemsignal 2
Signal: Low
TypeScriptNext.js

Coulson One

Enterprise-scale TypeScript/React application with 64,806 files. Led architecture decisions and core feature implementation for aviation resource management.

Keep exploring

Previous Project

App Idea Miner

AI-powered opportunity detection platform that collects, clusters, and analyzes "I wish there was an app..." posts. HDBSCAN clustering, sentiment analysis, and real-time monitoring.

Next Project

Coulson One

Enterprise-scale TypeScript/React application with 64,806 files. Led architecture decisions and core feature implementation for aviation resource management.

© 2026 Elizabeth Stein

·Contact·Privacy
Let's work together → GitHubLinkedIn

Built with Next.js, Three.js, and obsessive attention to detail.