No, and the system prompt is configured to prevent it. Quoting a specific rate or predicting approval for an anonymous buyer is the kind of behaviour that creates regulatory exposure for a mortgage brokerage. The bot describes FHA program features (credit-score floor, MIP structure, county loan limits, 3.5% down) at a general level and routes every rate-quote or approval-prediction question to a licensed MLO with the chat context attached.

The bot describes the FHA loan-limit framework (floor, ceiling, high-cost-area bands) and links to HUD's published lookup tool for current county-specific limits. It can surface the lookup link automatically when a prospect mentions a specific county or city, and it acknowledges that limits update annually rather than caching potentially stale numbers in its system prompt.

Yes. When a prospect mentions a fixer-upper, a property needing repairs, or a home with rehab budget, the bot recognises this as a 203(k) candidate and describes the standard 203(k) versus limited 203(k) differences at a general level. It then routes the lead to your 203(k)-trained MLO with the property condition captured in the chat summary so the MLO call starts already aimed at the right product.

The bot can describe the streamline refi process at a general level (no appraisal in most cases, reduced documentation, current FHA loan required) and capture the prospect's current loan details (rate, balance, term remaining) before routing to an MLO. It does not quote new rates or claim the prospect will save a specific amount; that calculation routes to the licensed loan officer with the borrower's current loan information attached.

Yes. Add the fee categories that already appear on your published disclosures (origination, lender credits, MIP at closing, third-party services) as a page, custom post type, or ACF fields. SleekAI reads them through your WordPress structure and passes them into the prompt as context. The bot describes general fee categories without quoting a specific dollar figure or rate for a specific borrower.

Bring your own key for OpenAI, Anthropic, Google Gemini, or OpenRouter, plus any OpenAI-compatible endpoint such as Azure or self-hosted models behind a compatible proxy. Most FHA-focused brokerages run GPT-4o or Claude Sonnet because those models follow strict no-quote, no-prediction system prompts more reliably than smaller models, which matters when the cost of a hallucinated rate or approval claim is regulatory.

Yes. SleekAI ships with 28+ display conditions so the brokerage can show the bot only on the FHA program pages, hide it on the loan-officer bios, or trigger different bots per loan type. A common setup runs an FHA-focused bot on the FHA page, a separate 203(k) bot on the renovation page, and a generalist bot on the homepage that triages to the right MLO after the first qualifying question.

Logs live in your WordPress database and you control retention. Most FHA-focused brokerages export them to their CRM or compliance archive on a recurring schedule via webhook. That keeps chat transcripts inside the same archival workflow as other regulated communications, which is what CFPB and state-regulator examiners expect to see. Retention windows are aligned with the brokerage's existing communications and HUD record-keeping policies.