Agent-Ready Infrastructure

The Missing API for
Mortgage Guidelines

FHA, Fannie Mae, Freddie Mac, VA, and USDA underwriting handbooks — fully indexed, semantically searchable, and returned with structured citations. Built for AI agents and the humans who deploy them.

Chunks Indexed
5
Agencies Covered
100%
Cited Answers
<2s
Avg Response Time

Ask Any Guideline Question

Real queries against the live API. Filter by agency, get answers with full citations — agency, document, section, and page number.

Not connected
💬
No questions yet
Enter your API key above and ask a mortgage guideline question to see live results.

Five Agencies. One API.

Every major federal mortgage program, ingested from primary source PDFs and kept current via automated change detection.

🏠
FHA
Federal Housing Administration
HUD 4000.1 — Single Family Housing Policy Handbook
Chunks
Tokens
📋
Fannie Mae
Federal National Mortgage Association
Selling Guide — Originating & Underwriting
Chunks
Tokens
📑
Freddie Mac
Federal Home Loan Mortgage Corp
Single-Family Seller/Servicer Guide
Chunks
Tokens
VA
Department of Veterans Affairs
VA Lenders Handbook — VA Pamphlet 26-7
Chunks
Tokens
🌾
USDA
Dept. of Agriculture
Single Family Housing Guaranteed Loan Technical Handbook
Chunks
Tokens

From Question to Cited Answer

A four-stage pipeline transforms raw guideline PDFs into structured, citable knowledge — automatically updated when source documents change.

01

PDF Ingestion & Parsing

Source PDFs are downloaded from official agency sites, parsed for structure — headings, section IDs, page numbers — and stored with full provenance metadata.

02

Semantic Chunking

Documents are split into ~500-token chunks with 50-token overlap. Each chunk carries agency, document, version, section reference, and page range metadata.

03

Vector Embedding & Storage

Chunks are embedded with all-MiniLM-L6-v2 and stored in ChromaDB. Multi-agency queries are per-agency balanced to prevent source dominance.

04

Cited Answer Generation

Top-k chunks are retrieved, passed to Claude Haiku with a strict citation prompt, and returned as structured JSON — answer text plus a citations array with every source reference.

Built for Integration

REST JSON API with API key authentication. Every endpoint returns structured data with full citation metadata.

Endpoints

POST
/query
Natural language question → cited answer + source chunks
GET
/agencies
List guideline agencies with document and chunk counts
GET
/documents
All ingested documents with version and token stats
GET
/chunk/{id}
Retrieve raw chunk text and metadata by ID
GET
/health
Service status, vector DB health, chunk count
GET
/pipeline/status
Change-management pipeline status and run history

Authentication

All endpoints (except /health) require an X-API-Key header. Rate limit: 60 requests/minute per IP.

Citation Schema

Every /query response includes a citations array:

Citation Object
{
  "agency":        "FHA",
  "document":      "HUD 4000.1",
  "section_id":    "II.A.4.b",
  "section_title": "Credit Score...",
  "page":          153,
  "chunk_id":      "fha-hud4001-...",
  "similarity":   0.8724
}
cURL — Query Example
curl -X POST http://localhost:8000/query \
  -H "Content-Type: application/json" \
  -H "X-API-Key: YOUR_API_KEY" \
  -d '{
    "question": "What is the minimum credit score for an FHA loan?",
    "top_k": 5
  }'
Python — SDK Usage
import requests

BASE  = "http://localhost:8000"
HEADS = {
    "X-API-Key": "YOUR_API_KEY",
    "Content-Type": "application/json"
}

resp = requests.post(
    f"{BASE}/query",
    headers=HEADS,
    json={
        "question": "DTI limits for VA loans?",
        "top_k": 5
    }
)

data = resp.json()
print(data["answer"])

for c in data["citations"]:
    print(f"{c['agency']} | {c['document']} | §{c['section_id']} | p.{c['page']}")
JSON Response
{
  "question":    "Minimum credit score for FHA?",
  "answer":      "FHA requires a minimum FICO score of 580 for maximum financing (96.5% LTV) [FHA | HUD 4000.1 | II.A.4.b | p.153]. Borrowers with scores between 500–579 are limited to 90% LTV [FHA | HUD 4000.1 | II.A.4.b | p.153].",
  "citations":   [ ... ],
  "chunks_used": 5
}

Simple, Value-Based Pricing

Anchored to the value it replaces — hours of manual guideline lookup per underwriter, per day.

Starter
$0 / month
Try the API. Limited to FHA guidelines and 100 queries/month.
FHA guidelines only
100 queries / month
Cited JSON responses
/health & /documents endpoints
Get Access
Enterprise
Custom
On-premise deployment, custom integrations, priority support, and SLA.
Everything in Professional
On-premise / VPC deployment
Custom agency ingestion
Dedicated Slack support
SLA: 99.9% uptime
Contact Sales