Skip to content
View ethan-haas's full-sized avatar

Block or report ethan-haas

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
ethan-haas/README.md

Ethan Haas

AI & Document-Automation Engineer — I turn messy documents into clean, validated, structured data, and build the AI systems and SaaS around them. Output that's verifiable, not just plausible.

🔗 ethanhaas.dev · LinkedIn · ethanzhaas@gmail.com · Open to contract or full-time work

What I build

  • Document extraction & validation — PDFs → structured data, with tie-out checks and golden-file tests. The model never does the math; tested code does.
  • AI systems that stay honest — multi-agent, RAG, and LLM pipelines built behind verification (sealed holdouts, fresh-context critics) so improvements are earned, not hallucinated.
  • Full-stack SaaS — production B2B products end to end: auth, multi-tenant data, billing, audit trails, dashboards.

Featured work

🟢 OBBBA Tracker — a live, paid B2B SaaS I build and operate. Tip & overtime tax-compliance for tipped-industry employers: automatic TTOC codes, FLSA overtime, W-2 Box 14 exports (ADP/Gusto/QuickBooks), multi-tenant access, billing.

self-improving-agent-harness — an autonomous multi-agent system that improves its own code behind a 7-tier verification gauntlet (incl. a sealed holdout). Inner research loop ported from Udit Goenka's autoresearch (MIT, based on Karpathy's work); the meta-improvement architecture and verification stack are my own.

financial-statement-extractor — government audit PDF → validated JSON, re-deriving every total (foot / crossfoot / articulate) with a golden-file test. 25 checks, 0 exceptions on a published report — and it catches an injected wrong figure.

grantledger — B2B SaaS that auto-categorizes nonprofit grant spending into 2 CFR 200 budget categories and generates audit-ready compliance reports. Next.js · Supabase · Stripe · OpenAI.

pacman-cpp — native C++20 + SDL2 Pac-Man built from scratch: co-op multiplayer, four ghost AIs, procedural audio, cross-compiled to an ARM handheld, with sanitizer/coverage/strict build presets and tests.

Stack

Python · C#/.NET · TypeScript / React · FastAPI · Next.js · pdfplumber / PyMuPDF · OCR · RAG / vector search · Claude / Gemini / OpenAI · Docker

Background

B.B.A., Finance — University of Cincinnati (Cum Laude) · CFI FMVA & BIDA. I work where financial and regulated documents meet engineering, and I make the output provably correct.

Open to contract or full-time AI / automation / document-intelligence roles — say hello.

Pinned Loading

  1. financial-statement-extractor financial-statement-extractor Public

    Government audit PDFs → validated structured JSON. Deterministic extraction + foot/crossfoot/articulate tie-out + golden-file test. Tested code does the math, not the model.

    Python

  2. grantledger grantledger Public

    B2B SaaS automating federal grant compliance for nonprofits — AI expense categorization into 2 CFR 200, budget-to-actual tracking, audit-ready reports.

    TypeScript

  3. pacman-cpp pacman-cpp Public

    Native C++20 + SDL2 Pac-Man from scratch — co-op multiplayer, four ghost AIs, procedural audio, cross-compiled to ARM, sanitizer/coverage/strict builds + tests.

    C++

  4. self-improving-agent-harness self-improving-agent-harness Public

    Autonomous multi-agent system that improves its own code behind a 7-tier verification gauntlet (sealed holdout + fresh-context critic) — improvements earned, not hallucinated.

    PowerShell