Skip to main content
Elizabeth Stein
AI FrontierOpen to workHomeWorkAboutContact

Case study

ai2024-2026

AutomaDocs

Production SaaS AI documentation platform. Automatically generates and maintains comprehensive code docs with RAG-powered chat, Tree-sitter parsing, and GitHub webhooks. Stripe-integrated with Pro ($35/mo), Team ($95/mo), and Business ($239/mo) tiers.

Exploring the boundaries of artificial intelligence

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 AI Frontier·✦Ω-Class Supergiant
●LIVE💰$$$★FEATURED
View on GitHub
View Live SiteSource Code

Evidence

Interface & evidence

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

Signature viewautomadocs.com
AutomaDocs application interface
Open Live Site
automadocs.com

Story arc

How this shipped

Exploring the boundaries of artificial intelligenceThree beats: what pressed against the work, how the stack answered, and what changed once it was live.

I · Constraint

The brief

Documentation becomes outdated instantly. Manual maintenance is tedious and skipped. Need auto-sync on every git push plus intelligent Q&A.

II · Build

The craft

Built AI pipeline with Claude for documentation generation, Tree-sitter for code parsing, RAG (Pinecone + BM25) for intelligent chat, GitHub webhooks for auto-sync, and full Stripe billing with 3 pricing tiers. Multi-language code sample generation.

III · Proof

What moved after launch

Live production SaaS with Stripe billing ($35-239/mo). Documentation auto-updates on git push via GitHub webhooks. RAG chat (Pinecone + BM25) answers questions about the codebase directly.

Signals

◆Signals & scale

0$35–239/mo
Pricing
Claude + RAG
Stack
Live SaaS
Status
Auto on Push
Sync

Engine room

At a glance

Inventory

Stack & signals

AIClaude SonnetTree-sitterRAGStripePostgreSQLRedis
← 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
AIRedis

StanceStream

Enterprise-grade AI policy debate platform built for the Redis AI Challenge 2025. GPT-4 agents with persistent personalities, emotional states, and coalition analysis. All 4 Redis data models (JSON/Streams/TimeSeries/Vector), Redis Vector-powered semantic caching, multi-source fact-checking, and business intelligence dashboard with ROI tracking.

Same clustersignal 3
Signal: Medium
AIRAG

CodeCompass

AI-powered codebase onboarding platform with interactive architecture diagrams and RAG-based Q&A.

Same clustersignal 2
Signal: Low
AI

Finance Quest

Advanced financial literacy platform with 17 chapters, 30+ professional calculators, spaced-repetition learning (SM-2 algorithm), AI coaching, and WCAG 2.1 AA compliance. Major refactor removed 43K lines of dead code for a lean, maintainable codebase.

Keep exploring

Previous Project

TubeDigest

AI-powered YouTube video summarization with Claude Sonnet 4.5, topic extraction, full-text search, mind map visualization, and GitHub sync.

Next Project

MCP Server Studio

Visual builder for Model Context Protocol servers. Design tools, resources, and prompts on a drag-and-drop React Flow canvas. Built-in test simulator with parameter validation and batch schema testing. Exports production-ready TypeScript with Docker and Railway deployment bundles. 466 passing tests.

© 2026 Elizabeth Stein

·Contact·Privacy
Let's work together → GitHubLinkedIn

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