8
Products shipped
AI for complex, legacy systems.
№8
The hardest data in the world is public — and almost unusable. We rebuild it, record by record, into software anyone can actually use.
NYSGPT builds domain-specific AI applications for the systems ordinary software won't touch — impenetrable government databases, statutory regimes, and industrial records. Eight shipped products, one architecture.
350k+
Records navigable
5
Live in production
1
Founder · full-stack
The most consequential systems run on the worst software.
Legislative records, customs rulings, energy filings, licensing registries, nuclear references — the data is public, authoritative, and locked behind portals built two decades ago for nobody in particular.
The most consequential systems run on the worst software. The information exists; it simply can't be reached by the people who need it.
NYSGPT exists to close that gap. We don't bolt a chatbot onto a problem. We ingest the primary record, ground every answer in a verifiable source, and rebuild the interface from the data up.
So a stressed parent, an importer, a researcher, or a regulator gets a real answer — not a 40-page PDF. Each entry in the contents is the same architecture, set for a different domain.
We don't bolt a chatbot onto a problem. We rebuild the interface from the record up.
i.
Grounded, not generated.Every claim traces to a primary source. Fluency without traceability is a liability.ii.
The data is the product.We rebuild the interface from the record up — search, structure, and AI as one surface.iii.
Ship to production.Live products with real users, not decks. Five of eight are running right now.The Contents
01LIVE
AI Governance
44B
A public registry, research library, and incident record for AI — the compliance portal for NY's Article 44-B. "SERFF, for AI."
32k papers · 2,561 incidents indexed
02LIVE
Trade & Customs
TariffsGPT
A self-serve refund engine for importers who paid IEEPA tariffs the Supreme Court invalidated — a real number before any phone call.
220k+ customs rulings · live schedule
03LIVE
Social Services
ChildcareGPT
NY childcare intelligence — every OCFS facility, county costs, and an AI-assisted subsidy form.
16,800 facilities
04LIVE
Energy & Grid
SolarGPT
Clean-energy intelligence for every U.S. county, state, and grid region.
3,000+ counties · EIA pipelines
05SHIPPED
Gov · Legislative
PolicyGPT
NY legislative & financial intelligence — bills, budgets, lobbying, with an advocacy layer.
Full NYS record
06SHIPPED
Scientific Reference
NSRgpt
Semantic search & RAG over the Nuclear Science References database.
88,000+ records · pgvector
07SHIPPED
Insurance · Reg.
InsuranceGPT
Auto-insurance quotes grounded in filed carrier data, Stripe checkout, agent console.
Grounded rates
08SHIPPED
Sports · Public
SportsGPT
High-school sports intelligence for Section XI — team and player stats, standings, choropleth maps, and AI-generated game highlights.
Section XI · AI highlights
How we build. Three movements, every issue.
i.
Tame the primary record
We crawl, dedupe, and structure the authoritative source — even when there's no bulk export, no API, or a pagination wall — into clean, queryable Postgres. The hard part nobody else does.
ii.
Make the AI accountable
Retrieval over the real corpus, structured output, and a visible chain back to the source. The model reasons over primary data, and every answer can be checked.
iii.
Rebuild the interface
Search, structured exploration, maps, and AI on one surface — designed for the human who actually needs the answer, and pushed to production with real users.
Have a system that's too complex for ordinary software?
That's exactly what we build for. Book a working session and we'll pressure-test what an AI-first rebuild looks like for your data — or send a short brief and we'll come back with a concrete read.