No, and the system prompt is configured to prevent it. Quoting a specific rate or sizing a loan against an assumed DSCR for an anonymous visitor is the kind of behaviour that creates regulatory exposure on the licensed-broker side and bad expectations on the borrower side. The bot describes program features and typical fee categories that already appear on your published pages, and routes every rate-quote or sizing question to a licensed CRE broker.

No. The bot can describe what SBA 7(a), SBA 504, Fannie DUS, Freddie SBL, bridge, CMBS, and conventional CRE products are at a general level and what categories of deal each one typically serves, but it does not recommend a specific program for a specific deal. Program selection depends on the deal's underwrite, sponsor profile, and execution timeline, so the bot routes that decision to a licensed CRE broker.

Yes. Map each broker on your team to the asset classes and program categories they cover in a custom post type or ACF field on the team page, and SleekAI ingests that mapping. When a multifamily prospect shows up, the bot routes the lead to the agency broker; when a hotel prospect shows up, it routes to the hospitality specialist. The routing logic lives in WordPress and updates without redeploying.

The bot is configured to identify itself as a non-licensed automated assistant and to surface the brokerage's NMLS ID and the assigned broker's NMLS ID when bookings are made. Your footer and broker pages already carry NMLS information per regulation, and SleekAI can be configured to surface the same identifiers in the chat handoff so the disclosure trail is intact end to end.

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 CRE brokerages run GPT-4o or Claude Sonnet because those models follow strict no-quote, no-recommendation system prompts more reliably than smaller models, which matters when the cost of a hallucinated rate or DSCR comment is reputational and regulatory.

Yes. SleekAI ships with 28+ display conditions so the brokerage can show the bot only on the program pages, hide it on the broker bios, or trigger different bots per asset class. A common setup runs a multifamily-focused bot on the agency page, an SBA-focused bot on the SBA page, and a generalist bot on the homepage that triages to the right broker after the first deal question.

Logs live in your WordPress database and you control retention. Most CRE 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 state regulators expect to see in a record-keeping review. Retention windows are aligned with the brokerage's existing communications policy.

SleekAI runs in WordPress and logs every conversation there. Most CRE brokerages push the transcript and contact details into HubSpot, Salesforce, or a CRE-specific CRM via Zapier or a webhook. The conversation summary plus the qualifying answers (asset class, loan purpose, deal size, location) end up as a fully shaped lead record so the broker sees the context before the deal call begins.