Team CORE

TEAM CORE

Michigan's Commercial Real Estate Advisors

Document Type: Compliance & Security Brief
Phase: Phase 0 — Foundation Layer
Date: March 24, 2026

Bringing the "Team" approach to the commercial market  ·  team-core.com

Powered by Beyond AI

01 Why Compliance Matters

Connecting AI to your AppFolio Property Manager and Google Workspace means giving a system access to lease data, financial records, tenant information, and internal communications. Before we write a single line of code, we need to understand what data we're touching, what regulations apply, and what controls must be in place.

This brief identifies the full compliance landscape for Team CORE's AI deployment. It maps every regulation that applies to your operations, classifies every data type by sensitivity, and defines the security controls that will be embedded into every agent we build — not bolted on afterward.

The goal is simple: zero surprises. Your team, your clients, and your data are protected from day one.

02 Regulatory Landscape for CRE + AI

Eight regulations and platform policies govern how Team CORE can deploy AI agents. Each one has been assessed for applicability, priority, and specific requirements.

Regulation / Policy Requirements Priority Team CORE Application
Anthropic Claude API /
AWS Bedrock
Zero Data Retention (ZDR) mode available and must be enabled. Data sent to Claude API is not stored or used for training. AWS Bedrock provides additional data isolation layer. BAA available if needed. Critical Foundation of all AI processing. ZDR ensures no tenant, financial, or lease data is ever retained by the AI model.
AppFolio Terms of Service / API Usage Policy Must comply with AppFolio's acceptable use of their Database API. Data accessed via API subject to AppFolio's data handling requirements. Rate limits, access controls, and audit requirements per AppFolio's terms. Critical Primary data source for leases, tenants, properties, financials, and work orders. API tier determines read vs. read/write access.
Michigan Identity Theft Protection Act
MCL 445.61-445.77
Requires safeguarding personal identifying information. Breach notification within 30 days. Written security policy required. High Applies to tenant PII, employee data, and any investor data encountered. AI agents must never expose or store PII outside controlled systems.
Fair Housing Act AI must not discriminate in tenant screening, communications, or lease decisions. No algorithmic bias in any tenant-facing AI output. High Any AI-generated tenant communications, renewal letters, or lease analysis must be reviewed for discriminatory language or bias.
Google Workspace Data Processing Agreement Google's DPA governs how data in Google Drive and Gmail is accessed programmatically. AI agent must use OAuth 2.0 with minimum necessary scopes. Must comply with Google API Services User Data Policy. High AI agents accessing Google Drive documents, calendar, or email must request only the scopes needed and maintain audit trail of all access.
GLBA
Gramm-Leach-Bliley Act
If Team CORE handles financial data for clients, GLBA safeguards may apply. Requires written information security program. Medium Applies if financial data is shared with or from banking/institutional clients. Investment analysis reports and rent roll data may fall under this.
CAN-SPAM Act AI-generated marketing emails must comply with federal email marketing law. Opt-out mechanism required. Physical address in email. No deceptive subject lines. Medium Applies to marketing drip campaigns and client outreach generated by AI. Sam's marketing workflows must include compliant footers and opt-out links.
SOC 2 Type II
Best Practice
Not legally required but increasingly expected by institutional clients. Demonstrates security controls, availability, and confidentiality. Medium Applies to AI infrastructure hosted on AWS. Institutional clients (Rehmann, etc.) may ask about SOC 2 compliance during due diligence.
03 Data Classification

Every data type Team CORE handles has been classified by sensitivity level, AI access permission, and required controls. This classification drives every architecture decision.

Data Type Examples Sensitivity AI Access Controls Required
Lease Data Terms, rent amounts, expiration dates, renewal options, TI allowances Medium Yes — Core Function Encryption, access control, audit trail
Tenant Business Info Company name, suite, contact person, lease terms Medium Yes — Required Encryption, role-based access
Tenant PII SSN, EIN, personal addresses (if stored in AppFolio) High Limited — Redact Sanitization before AI processing, encryption, access control
Financial Data (Property) P&L statements, budgets, rent rolls, AR/AP Medium-High Yes — Budgeting Encryption, role-based access, audit trail
Investor Data Tax IDs, SSNs, bank accounts, distribution records Critical NO — Isolated No AI connection. AppFolio Investment Manager stays completely separate.
Work Orders Maintenance requests, vendor info, property issues Low-Medium Yes — Maintenance Basic access control
Employee Data Payroll, personal info, performance records High NO — Not in Scope Not connected to AI pipeline
Market Data (CoStar) Comps, market trends, property research data Low Future Phase Third-party ToS compliance, read-only access
Communications Emails, chat messages, calendar events Medium Limited — Consent OAuth scopes, user consent, audit trail
04 Required Security Controls

Six security controls will be embedded into every AI agent built for Team CORE. Each one addresses a specific compliance requirement identified in the regulatory landscape above.

4.1
Encryption

At rest: AES-256 via AWS KMS with customer-managed keys. All stored outputs, logs, and cached data encrypted.

In transit: TLS 1.2+ for all API calls — AppFolio, Google Workspace, and AWS Bedrock.

Google Drive: Already encrypted by Google; our agent adds an additional access control layer.

4.2
Authentication & Access Control

Two-factor authentication required for all AI access (matching Team CORE's existing Google Auth + SMS setup).

Role-based access: Admin (Matt/Kevin) — full config + all data. Manager (Amanda/Zach) — property management. Broker (Phil/Sam) — transactions/leases. Maintenance — work orders only.

OAuth 2.0 for Google Workspace; API key management for AppFolio Database API.

4.3
Zero Data Retention (AI Processing)

All AI processing via AWS Bedrock with Claude (ZDR enabled). No data stored by the AI model. No data used for model training.

Prompts and responses are ephemeral — not persisted outside our controlled environment. When the request completes, the data is gone.

4.4
Data Sanitization

Tenant SSNs and EINs redacted before AI processing (if encountered in AppFolio data).

Investor data never enters the AI pipeline. Investment Manager data is completely isolated.

Financial amounts preserved (needed for analysis) but access-controlled per role. Email addresses and phone numbers handled per role permissions.

4.5
Audit Trail

Every AI action logged: who requested, what data was accessed, what output was generated, timestamp.

Logs stored encrypted, retained for minimum 3 years. Available for review by leadership at any time.

4.6
Human-in-the-Loop Review

All AI-generated external communications (renewal letters, tenant notices, marketing emails) held for human review before sending.

AI generates draft → team member reviews → approves or edits → then sends. No autonomous external communication without human approval.

05 AppFolio-Specific Considerations

AppFolio Property Manager is the backbone of Team CORE's operations. Connecting an AI agent to it requires careful attention to API tier, data scope, and rate limits.

API Tier
Plus (Read-Only) or Max (Read/Write)
API access level determines whether the AI agent can only read data or also write back to AppFolio. Confirmation needed from Team CORE on current tier and desired access level for the AI agent.
Data Accessed via AI
Leases, Tenants, Properties, Financials, Work Orders
These five data categories represent the core data the AI agent will read from AppFolio. Each is subject to role-based access controls and audit logging.
Rate Limits
Respect AppFolio's API Rate Limiting
AI agent must implement graceful throttling to avoid service disruption. Queued requests processed within limits. No bulk data dumps — targeted queries only.
Data Freshness
Real-Time API Data — No Stale Cache
AppFolio's API provides real-time data, eliminating stale cache issues. AI agent queries live data on each request for accurate, up-to-the-minute reporting.
Data NOT Accessed via AI
Investment Manager data is completely off-limits. Investor PII, tax documents, distribution records, and bank account information will never be connected to the AI pipeline. AppFolio Investment Manager stays fully isolated.
AppFolio's Own AI (Realm-X)
We position our AI as complementary, not competing. Our agents handle what Realm-X cannot: PDF lease extraction with custom abstracts, multi-year budget generation from historical P&L data, portfolio-wide visualization dashboards, and custom investment analysis reports.
06 Risk Assessment Matrix

Every identified risk has been assessed for likelihood and impact, with specific mitigations defined. Residual risk — the risk remaining after controls are in place — is the metric that matters.

Risk Likelihood Impact Mitigation Residual Risk
Tenant PII exposure via AI Low High Data sanitization + role-based access + ZDR Very Low
AI hallucination in tenant communication Medium Medium Human-in-the-loop review + multi-agent validation Low
Unauthorized access to AI agent Low High 2FA + role-based access + audit trail Very Low
AppFolio API rate limiting / downtime Low Medium Graceful degradation + cached essential data Low
Investor data leakage Very Low Critical Complete isolation — no AI connection to Investment Manager Negligible
AI-generated bias in tenant communications Low High Fair Housing compliance review + prohibited language scanning Very Low
Data breach of stored outputs Low High AES-256 encryption at rest + access control Very Low
07 Compliance Checklist

Every item below will be implemented before the AI agents go live. This checklist serves as both a build requirement and a verification document.

  • Zero Data Retention enabled on all AI API calls
  • Two-factor authentication for all AI access
  • Role-based access control configured per team member
  • Data sanitization pipeline for PII redaction
  • AppFolio Investment Manager completely isolated from AI
  • Human review required for all external communications
  • Audit trail logging for every AI action
  • Encryption at rest (AES-256) and in transit (TLS 1.2+)
  • Fair Housing compliance review for tenant-facing outputs
  • CAN-SPAM compliance for marketing emails
  • OAuth 2.0 scopes minimized for Google Workspace
  • AppFolio API access limited to required data only
  • Breach notification procedure documented
  • Annual compliance review scheduled
08 Next Steps
1
Confirm AppFolio Tier
Verify whether Team CORE is on Plus (read-only) or Max (read/write) API access level.
2
Review & Approve Framework
Leadership reviews this compliance brief and approves the security framework before build begins.
3
Begin Phase 1 Build
Start building agents with all security controls embedded from day one — not added after.
4
Generate Compliance Report
Post-build: produce full AI Compliance & Security Report as a certification document.

Security isn't an afterthought — it's the foundation.
Every agent we build for Team CORE will have these controls baked in from the start.

Team CORE LLC  ·  691 N. Squirrel Road Suite 290, Auburn Hills, MI 48326  ·  team-core.com

Prepared by Beyond AI  ·  Confidential