No. SleekAI's system prompt is configured to share general planning concepts and your firm's services without recommending specific securities, projecting retirement income, or making personalised tax recommendations. When a prospect asks something advice-shaped, the bot frames the response as general information and defers the specific modelling to a CFP at your firm in the discovery meeting.

Yes. Add ADV Part 2A, ADV Part 2B, and Form CRS as PDFs or pages on your site, and SleekAI will link them automatically when prospects ask about fees, conflicts of interest, or how your firm operates. Many firms also configure the bot to surface the disclosures proactively at the end of any fee discussion, which mirrors the disclosure flow a human intake coordinator would follow.

SleekAI hands off to whichever scheduler you embed on the page - Calendly, HubSpot, Acuity, or your CRM-native scheduler. The bot collects email and the qualifying context, then either redirects the prospect into your existing booking flow or sends a calendar invite via webhook. The conversation summary travels with the booking so the advisor sees the context before the meeting.

Logs are stored in your WordPress database and you control retention. Most advisors export them to their CRM or a dedicated compliance archive (often Smarsh, Global Relay, or an internal system) on a recurring schedule via webhook. That keeps the chat transcripts inside the same archival workflow as your email and other written communications, which is what compliance reviewers expect to see.

Yes. Run a retirement-planning bot on retirement pages, a 401(k)-rollover bot on rollover pages, and a separate bot for business-owner clients on the business-planning section using the multibot feature and 28+ display conditions. Each bot has its own system prompt, knowledge sources, and disclosures, so the framing matches the topic and the conversation stays tight.

Claude Sonnet and GPT-4o both perform well for compliance-sensitive copy - they follow the 'no specific recommendation' system prompt reliably and produce consistent disclosure language. Smaller or older models are more prone to drift into advice-shaped statements under pressure, which is exactly the failure mode you cannot afford on an advisor site. Bring your own key for whichever provider you prefer.

Yes. The system prompt can encode any ideal-client profile - 'pre-retirees aged 55+ with concentrated equity positions', 'business owners contemplating sale', 'multigenerational families' - and the bot uses that profile to gauge fit during the conversation. Prospects who clearly do not match get redirected to self-serve resources or a referral, while prospects who match get fast-tracked into the discovery flow.

It explains what those products are at a general-education level and describes whether your firm includes them in planning engagements, but it does not recommend specific products or carriers. If a prospect wants product-specific advice, the bot routes to an advisor; if you do not offer a particular product, the bot says so directly rather than improvising. That keeps the conversation aligned with what your firm actually does.