How Ace AI Protects Your Follow Up Boss Data

A note on the URL: this article originally referenced a certification framework. Follow Up Ace is not certified under, and is not pursuing, any third-party security attestation — the controls below are what we actually run, documented plainly.

By the Follow Up Ace team· Last updated
Quick answer

Follow Up Ace protects your FUB data by tokenizing contact emails and phone numbers in the Ace chat before the model sees them, AES-256-GCM encryption at rest and in transit, code-enforced Fair Housing compliance scanning, a deletion request actioned within 30 days, and FUB Marketplace certification. We hold no third-party security certification and are not pursuing one. No public model is trained on your data; Ace's own scoring models learn from de-identified, pooled outcome patterns.

This is the technical security deep-dive. For the plain-English safety overview — auto-send, data handling, and legitimacy in one page — read is Follow Up Ace safe?

Secure data visualization showing encryption shield protecting real estate CRM contact data in Follow Up Boss

Why data security is a different question for real estate AI

Real estate agents and teams handle unusually sensitive data in their CRM. Follow Up Boss contacts include names, phone numbers, email addresses, home addresses, financial situation signals, and personal details shared during the buying or selling process. This is not generic business contact data — it's information that carries real privacy risk if mishandled.

When you add an AI layer to that CRM, you're doing something new: you're asking an AI model to read, analyze, and act on that contact data. The question "is this AI safe?" becomes a concrete technical question with specific answers. Here's what we actually do. (For the short version across all of safety, privacy, and compliance, see is Follow Up Ace safe?)

What happens to your FUB data before it reaches an AI model?

The most critical security boundary in an AI-connected CRM is the point where your data crosses into a large language model. LLMs are external services — they receive whatever text is sent to them as input. The question is: what form is that text in when it arrives?

Email and phone tokenization in the Ace chat

In the embedded Ace chat, Follow Up Ace tokenizes email addresses and phone numbers before they reach the language model (verified: chat-app/utils/piiAnonymizer.js). Those values are replaced with consistent placeholder tokens — for example, an email like [email protected] becomes [EMAIL_a3f8b2c1] before being sent to the model. The mapping between the token and the real value is maintained server-side and is never sent to the LLM.

This means: if the LLM provider's logs captured the input, they would see tokens, not your clients' real emails and phone numbers. The model responds using the tokens, the server deanonymizes the response, and only your interface sees the real values.

The scope is deliberate, and we state it plainly: names are not tokenized, and this applies to the embedded Ace chat only. Voice, automated drafting, typed classification (TypeSafe) and anything you ask Claude or ChatGPT through the connector receive the CRM text that task needs. Every vendor that processes CRM text is named on our Sub-processor page.

No public model is trained on your data

Your FUB contacts, conversation history, call notes, and pipeline data do not train the language models behind Ace. Our contracts with OpenAI, Anthropic, Google and ElevenLabs exclude your data from training their models, and OpenAI's API operates under API terms that do not use API inputs for model training by default — a published policy separate from the consumer ChatGPT product. TypeSafe, which classifies notes and replies, is listed on our Sub-processor page with the status of its data-processing terms (written terms are still being documented).

Ace's own scoring models do learn from outcomes: de-identified patterns pooled across accounts (stage history, response times, whether a lead closed), never names, contact details or message content. We use your data at inference time to generate responses for you, not to train a public model.

Encryption: what's protected and how

Encryption at rest

Sensitive fields stored in Firestore and related databases are encrypted at rest using AES-256-GCM (verified: chat-app/utils/encryption.js). AES-256-GCM is an authenticated encryption scheme — it provides both confidentiality (the data is scrambled without the key) and integrity (any tampering with the ciphertext is detectable). The authentication tag prevents silent corruption or modification of encrypted data.

Encryption keys are derived from environment secrets and are required in production — the code explicitly refuses to store plaintext sensitive values if no key is configured.

Encryption in transit

All communication between your browser, the Follow Up Ace servers, Follow Up Boss, Firestore, and LLM providers happens over TLS (HTTPS). This covers the entire data path: FUB API calls, webhook events, AI model requests, and the embedded interface in your browser. The compliance page summarizes this as "256-bit at rest and in transit across all FUB / Firestore / LLM paths" (verified: chat-app/public/compliance/index.html).

Fair Housing compliance: code-enforced, not policy-only

A critical but often overlooked security and legal dimension for real estate AI is Fair Housing compliance. AI models can — and without safeguards, will — generate text that makes illegal distinctions based on protected characteristics including race, color, national origin, religion, sex, familial status, and disability.

Follow Up Ace includes a code-level compliance scan function, scanForComplianceViolations(), that Ace runs on the drafts it writes and on Automation and Autopilot sends before they go out (verified: chat-app/utils/complianceGuard.js). This function checks against Fair Housing rules and licensing boundary rules.

The compliance layer is also injected into the LLM system prompt — the model receives an explicit compliance directive at session initialization that instructs it to refuse, rephrase, or flag responses that would violate Fair Housing or professional licensing boundaries.

This is two layers of protection: a system prompt directive that reduces the likelihood of a violation at generation time, and a code-level scan that catches violations before the output goes out. Learn more on the compliance overview page.

Security certifications: where we are, honestly

We don't hold — and are not pursuing — a third-party security certification, and we won't imply otherwise. A formal audit report (SOC 2 is the one most vendor questionnaires ask for) evaluates a company's controls around security, availability, processing integrity, confidentiality, and privacy over a period of time. We have not been through one.

What we do instead is publish what we actually do. Our controls are designed in line with recognized security frameworks: encryption in transit and at rest, least-privilege access, HMAC-verified requests, and audit logging. The technical controls described in this article are the real ones, and the compliance page states the same posture.

If a certification is a hard requirement for your brokerage's vendor approval process, the honest answer is that we can walk your team through our real controls, but we can't hand you an attestation.

Privacy law and deleting your data

Follow Up Ace serves the US and Canada and is built to the Texas TDPSA, California CCPA/CPRA and other US state law, and Canada's PIPEDA and Quebec Law 25, aligned to GDPR principles. Specifically:

Your client data in Follow Up Boss itself remains in Follow Up Boss — it's owned by your FUB account, not by Follow Up Ace. When you disconnect or cancel, our access to it ends.

FUB Marketplace certification

Follow Up Ace is listed in the official Follow Up Boss integration marketplace. FUB Marketplace certification requires that an integration meet Follow Up Boss's standards for API usage, security practices, and integration quality. This is an active listing that can be revoked — it's not a one-time badge.

You can verify this listing directly in your Follow Up Boss account settings under Integrations.

Authentication: how Ace verifies it's talking to you

The embedded Follow Up Ace assistant authenticates through your Follow Up Boss session context. When the embed loads inside FUB, it receives a base64-encoded, HMAC-signed context payload from Follow Up Boss that contains your identity and account information. The server validates the HMAC signature on every request — requests without a valid signature are rejected.

Admin users authenticate separately through Firebase Auth with email and password. Admin sessions are scoped to the admin interface and do not share session state with the agent-facing embed.

What about the AI models themselves — are they secure?

The AI models used by Follow Up Ace are accessed through provider APIs (OpenAI). The security of those providers is subject to their own security programs. OpenAI maintains its own security posture documentation at openai.com/security. We use API access, not consumer products, which carry different data handling terms.

The tokenization described above means that, in the Ace chat, a provider-side security issue would expose tokens rather than your clients' real emails and phone numbers. It does not cover names or the other CRM text the model needs to answer, which is why the provider contracts and the Sub-processor page matter too.

The security posture: honest summary

Control Status Verified source
Email and phone tokenization in the Ace chat Active utils/piiAnonymizer.js
AES-256-GCM encryption at rest Active utils/encryption.js
TLS encryption in transit Active compliance page
Fair Housing compliance scan Active (code-level) utils/complianceGuard.js
No public model trained on your data Active (provider contracts; TypeSafe terms being documented) compliance page + Sub-processor page
Deletion on request Verified request actioned within 30 days compliance page
FUB Marketplace certified Active compliance page
Third-party security certification Not held and not being pursued compliance page

For the complete compliance picture including the full Fair Housing compliance framework, see the compliance overview. For questions about your specific security requirements, contact us before signing up — we'd rather answer your questions honestly upfront than have them surface after you're onboarded.

Try Follow Up Ace in your Follow Up Boss

Free to start, no sales call. Connect Follow Up Boss in one click and Ace works inside your CRM.

Get Started Free