AI Compliance & Risk · Residential Real Estate

Correctness over checkboxes.

MHRealtyAI reads the agreements, disclosures, listings, and agent messages your brokerage already produces — and reviews the actual language against state-specific rules. Not just "is it signed," but "is it right."

Decision-support, not legal advice — a licensed human always makes the final call.

Launching across Texas·Florida·New York
SCROLL

Why now

The rules just changed — and they keep changing.

Three regulatory shifts created durable, recurring compliance demand. The exposure is real, it's language-level, and it varies by state.

$418M
NAR antitrust settlement that made a written buyer agreement mandatory before touring.
NAR / MLS policy, eff. Aug 17 2024
$26,262
Minimum HUD penalty for a first Fair Housing violation. Private suits carry no cap.
2025 HUD penalty schedule
~3M
Licensed U.S. agents producing reviewable agreements, listings & messages every day.
NAR membership data
50
States of diverging rules, phasing in through 2025–2026 — monitored by plaintiffs' attorneys.
State patchwork, post-settlement

The gap

Existing tools check the checkbox. Nobody checks the language.

Transaction platforms confirm a document is present, signed, and filed. Almost none review whether a clause actually meets the legal standard for the state. That semantic gap is exactly where the liability — and the budget — concentrates.

Moving rules

Post-settlement buyer-agreement and compensation-disclosure requirements vary by state and MLS, and phase in through 2026. A human reviewer can't keep current.

Casual risk

The costliest Fair Housing failures aren't in polished listings — they're in the hurried text, the showing remark, the email. And everyone screenshots.

The bottleneck

Managing brokers review every file page-by-page against state rules — slow, inconsistent, and personally on the hook for what they miss.

Free Compliance Check

Paste an agreement. See what's wrong in seconds.

A live taste of Modules A & B. Every finding cites the exact offending text, the rule it implicates, the authority, and a suggested compliant rewrite — the same grounded output that drives the full platform.

mhrealtyai · compliance-check.live

Custom text detected — this live demo flags a curated set of example patterns, not the full state rule set. The complete platform reviews every rule.

Try editing the text — remove "TBD" or "St. Mary's Church" and re-run to watch findings clear.

The platform

One correctness-and-audit layer for the whole transaction.

Not another transaction platform, and not just a Fair Housing scanner — the integrated layer that reviews the actual language, end to end, and proves your process.

MODULE A · the wedge

Buyer-Rep & Compensation Compliance

Clause-level review against post-settlement, state-specific rules. Detects open-ended compensation (ranges, "TBD," "whatever the seller offers"), missing "fees are negotiable" statements, wrong or outdated form versions, and inconsistent signatures or dates.

MODULE B

Fair Housing Language Review

Scans listing copy and agent emails & texts for coded, discriminatory, steering and proxy language — where the costliest violations actually happen — and suggests compliant rewrites, accounting for state-specific protected classes.

MODULE C

Deal-File QA

Splits and classifies a whole closing file, then checks completeness and correctness — required docs present, correct versions, fields consistent across documents.

MODULE D · the artifact

Risk Report & Audit Trail

Per-file report (text, rule, authority, fix) plus an immutable, timestamped, rule-version-stamped log. The defensible record you show a regulator or plaintiff's attorney. PDF export.

MODULE E

Broker Dashboard

Portfolio queue with statuses and open-risk counts, filters by agent / state / type, plus recurring-issue and per-agent views — for coaching, not punishment.

How it works

Grounded findings only. No source span, no flag.

A hybrid pipeline: deterministic rules handle anything mechanically checkable; an LLM is used only for genuine semantic judgment — always with the source text and the retrieved rule in context. The system cannot assert a finding it can't ground.

01

Ingest

Upload or forward to a per-brokerage email address.

02

Parse & classify

OCR + layout; label each document type; split packets.

03

Rule evaluation

Deterministic checks in code + semantic checks over the rule engine.

04

Findings + fixes

Quoted text, rule, authority, confidence, suggested rewrite.

05

Human review

Reviewer resolves / accepts / overrides each flag with a note.

06

Audit log

Append-only, rule-version stamped, reproducible months later.

The moat

A versioned, citation-backed rule engine.

The reason a generic LLM wrapper can't replace us. Every rule is a structured object tied to its legal authority, carries an effective date and version, and is regression-tested before release. When a rule changes, old reports stay reproducible.

deterministic semantic hybrid authority-backed versioned
// a rule is a structured, versioned object
{
  "id": "MHR-NAR-COMP-001",
  "jurisdiction": "US-FEDERAL",
  "docType": "buyer_rep_agreement",
  "description": "Compensation must be objectively
     ascertainable and not open-ended",
  "authority": "NAR settlement (2024-08-17)",
  "severity": "high",
  "method": "hybrid",
  "version": "2026.04",
  "effectiveDate": "2024-08-17"
}

Honest differentiation

What no single competitor bundles for the brokerage.

Capability Checklist / TMS
SkySlope, dotloop
Fair Housing scanners
FairSentry, B.Claw
MHRealtyAI
Clause-level correctness reviewCompleteness onlyYes
Fair Housing across agent comms, not just listingsListings / marketingYes
Whole deal-file QA (complete + correct)Checklist completenessYes
Immutable, rule-versioned audit trailPartialPer-asset logsYes

Strategy: integrate, don't fight for the system of record. We sit on top of where files already live as the system of intelligence.

Trust & posture

Built for a regulated buyer who is personally on the hook.

Decision-support, not legal advice

We flag, explain, suggest, and log. A licensed human makes the final call. Suggested rewrites are drafts — UPL-aware by design.

No hallucinated findings

Every flag cites the exact span and the rule. Retrieval over recall; confidence + abstention. A finding with no source span is suppressed.

Defensible audit trail

Append-only, tamper-evident, rule-version stamped. Reproduce any past report and show exactly which rule and human action produced each finding.

Security first

Encryption in transit & at rest, strict multi-tenant isolation, RBAC, limited-retention LLM terms, and controls designed toward SOC 2.

Who it's for

Independent & mid-size brokerages, 10–150 agents.

Big enough to feel real liability and hold budget; small enough to buy without enterprise procurement. The broker buys and configures; agents and coordinators are the volume users whose work is reviewed.

Economic buyer

Managing broker

Personally and supervisorily liable. "Make sure nothing in my agents' files creates a fine, lawsuit, or license problem — without me reading every page."

Primary user

Compliance officer

"Catch every error before close, faster — and prove I did." Cares about accuracy, throughput, clear flags, audit logs.

Secondary user

Transaction coordinator

"Submit clean files the first time." Cares about pre-submission checks and fewer rejections.

Content source

Agent

"Don't accidentally write something non-compliant." Wants fast feedback — and not to get in trouble.

Pricing

Defensive spend, priced against a single avoided exposure.

A 50-agent brokerage runs roughly $750–2,000/month — trivially justified against one avoided Fair Housing penalty or one defended deal.

Free Check
Trial / single user
$0
  • Single-document analyzer
  • Paste or upload, no login
  • No audit trail
Try it
Solo / Small
≤ 10 agents
$99–199/mo
  • All modules, 1 state
  • Basic audit trail
  • Email + upload intake
Start
Brokerage
10–150 agents
$15–40/agent/mo
  • All modules, multi-state
  • Full audit trail + dashboard
  • Monthly floor; coaching views
Book a demo ↗
Enterprise
150+ / franchises & networks
Custom
  • dotloop / SkySlope integrations
  • SSO, SOC 2 documentation
  • Priority rule requests
Contact sales

Plus a per-transaction add-on (~$10–25/file) for variable-volume buyers and coordinators. Indicative pricing — validated with design partners.

Get started

Stop reading every page. Start proving your process.

Join 5–10 design-partner brokerages shaping V1 across Texas, Florida, and New York.