The thesis

Affordable housing finance is a domain where AI assistance can compress hours of statutory research into minutes — if the AI is grounded in primary sources, cites its work, and knows when to defer to human judgment. We're building tools that do exactly that.

This page collects what we offer now and what's coming.

Available now: The Affordable Housing AI Toolkit ($99)

The Affordable Housing AI Toolkit turns ChatGPT, Claude, Gemini, or any major LLM into an affordable housing finance assistant. It bundles:

  • Platform setup files — system prompts and configurations packaged for Claude.ai (Project), ChatGPT (Custom GPT), and Gemini (Gem). Pick the AI you already pay for.
  • 50+ tested prompts — for LIHTC underwriting, QAP scoring, 4% vs 9% comparisons, OZ deal review, HUD compliance, and capital stack assembly. Platform-agnostic.
  • Statutory reference pack — curated PDFs of Section 42, key IRS Revenue Procedures, OBBBA provisions, sample state QAPs, HUD CPD notices, and FHLB AHP guidance. Upload to any AI that accepts file context for instant retrieval.
  • Setup walkthrough videos — one for each supported platform
  • Lifetime updates — new regulations, AMI tables, and QAP revisions delivered to your purchase email

You bring your own paid AI subscription (Claude, ChatGPT, Gemini, or any major LLM — sold separately by the respective providers). The Toolkit is a one-time $99 purchase, no recurring fees.

Learn more about the AI Toolkit

Available now (MVP): Pro AI Q&A platform

Our hosted Pro AI Q&A is in active development. Unlike the AI Toolkit (which runs in your own AI account), Pro AI Q&A runs on housingsubsidybrief.com using our content library and Anthropic's Claude API on the backend. Key planned features:

  • Conversational interface — ask deal questions in natural language
  • Grounded responses — answers cite primary sources (Section 42, 24 CFR, HUD notices, OBBBA, IRS Revenue Procedures)
  • Knows when to defer — trained to flag situations requiring qualified counsel or CPA review rather than over-confidently answering
  • Daily limits by tier — 0 questions/day for Reader, 10/day for Brief, 30/day for Pro, 100/day per seat for Enterprise
  • Conversation history — saved chats for Pro members
  • Privacy preserved — your questions are not used to train AI models. Anthropic processes the queries on the backend but does not retain them for training under our enterprise terms.

What's live today

Sixteen calculators and tools are live on the platform — AMI & rent limit calculator, capital stack builder, QAP scoring estimator, OZ calculator, Year-15 exit modeler, bond financed-by calculator, basis boost calculator, adjuster calculator, QAP comparison, deadline tracker, HOME match calculator, equity pricing tracker, LP IRR calculator, income averaging calculator, and the Pro AI Q&A. The full list is in the Federal Programs hub and tools dropdown.

In active development

Coming soon

OBBBA Impact Analyzer

Side-by-side analyzer showing pre-OBBBA vs post-OBBBA deal economics for hypothetical projects. Particularly useful for sponsors evaluating whether to accelerate or delay specific deal structures given the new statutory environment.

Coming soon

State QAP Scoring Expansion

The QAP Scoring Estimator currently covers the 5 largest state QAPs. We're expanding to the next 10 most-active states based on subscriber demand — with full scoring categories, set-aside breakdowns, and historical-round benchmarks.

Coming soon

Multi-source Layering Compliance Checker

Walks a deal stack through HOME/HTF/CDBG/AHP layering compatibility flags, basis treatment for each source, and the post-OBBBA bond financed-by interaction with 4% LIHTC. Flags conflicts before they show up in compliance review.

Our approach to AI

We're not building AI for AI's sake. The tools we ship have to make practitioner work materially faster and more accurate than what's possible without them. That means:

  • Grounded in primary sources — not generic language model output
  • Citation by default — every claim traces back to a primary source you can verify
  • Refuses to over-extend — trained to flag situations requiring human professional judgment rather than fabricate answers
  • Privacy-respecting — your queries don't train AI models
  • Transparent limitations — we publish what the AI can and cannot do reliably

Important caveats

AI-generated responses are not legal, tax, financial, or investment advice and should be verified against primary sources before any decision or transaction. Always consult qualified counsel, your CPA, and other appropriate professional advisors before relying on any AI output. See our Disclaimer for full details.

We're confident in the quality of what we're building, but the underlying technology has known limitations — hallucinations, outdated information, edge-case failures — that we work to mitigate but cannot eliminate. Use AI as a productivity tool, not as a substitute for professional review.

Get notified when new tools launch

The fastest way to know when a tool goes live is the weekly newsletter.

Subscribe to the newsletter Get the AI Toolkit now
Tell us what to build

If there's a specific AI tool that would materially speed up your affordable housing work, tell us. Email support@housingsubsidybrief.com with what you'd want and how you'd use it. Practitioner input directly shapes our roadmap.

Claude™, ChatGPT™, and Gemini™ are products of Anthropic, OpenAI, and Google respectively. The Housing Subsidy Brief is not affiliated with any of them. References to these services describe how those products work; the Affordable Housing AI Toolkit packages prompts, references, and configuration files designed to work inside the AI platform of your choice, and the Pro AI Q&A uses Anthropic's APIs on our backend under our commercial terms with Anthropic.

Sixteen tools currently live

The full toolset shipped on the platform — free where flagged, Brief or Pro for the rest: