Easy Appointments stores services, workers, and locations as configuration rows, slot rules in the ea_connections table, and confirmed bookings in ea_appointments. Each booking row links a customer to a service, a worker, a location, and a time slot, with a status the admin can confirm or cancel. SleekAI can be wired to all of those, so the system message exposes the customer's upcoming bookings, the catalog of services and workers, and the relevant slot rules as named variables.

That means the bot can confirm a customer's next booking with service, worker, location, and time, answer availability questions on a specific service by reading the connection rules that define which workers and locations serve it, and quote the practice's cancellation policy on the exact service in question. None of those answers come from training data. They are direct reads on the Easy Appointments configuration the form already uses.

Display conditions scope the widget by page, role, or login state. Multibot keeps a public sales bot on service pages separate from a private support bot on the My Bookings page. Every conversation is logged inside WordPress with model and token usage so support leads can audit accuracy and refine the prompt over time.

Easy Appointments has a quiet reputation among small service businesses because its connection rules let an operator model real-world constraints with surprising precision. Worker A does balayage on Tuesdays at Downtown. Worker B does balayage on Thursdays at Riverside.

The form will refuse a Wednesday slot, and rightly so. A generic chatbot bolted onto an Easy Appointments site has no idea those rules exist. It will offer slots the form will then reject, suggest a worker at a location they do not cover, or quote a price that has not been current for six months.

The customer ends up confused, the staff fields three emails to fix it, and trust in the booking flow takes a hit. SleekAI flips the model. The bot reads the same connection table and the same bookings table Easy Appointments reads, so its suggestions line up with what the form will accept.

Per-page display conditions let a sales bot live on service pages with pricing and availability while a separate support bot lives on the customer dashboard with confirmed bookings, no leakage between them. The conversation log doubles as a quiet feedback loop on the service descriptions themselves, surfacing the rules customers misread again and again and helping operators fix the copy before the next round.