JetAppointment stores bookings in custom tables like jet_apb_appointments and jet_apb_apt_meta, with services, providers, and locations exposed as JetEngine custom post types. Excluded dates and working hours live in their own settings. SleekAI's data sources map all of that into named variables so the chatbot can answer questions like "do you have a 45 minute haircut with Lisa on Thursday morning" with real slot data, not invented availability.

Display conditions scope each bot by post type, taxonomy term, user role, logged-in state, and URL pattern. That means the service-page bot sees only the current service plus its providers and free slots, the staff-page bot sees one provider's calendar, and a logged-in customer's bot can reference their own past bookings without exposing the rest of the schedule.

Every chat is logged inside WordPress with the model name, token usage, and origin page. Pair that with the JS API or PHP embed and the bot can be triggered from a custom Elementor button, the JetAppointment confirmation step, or a follow-up email link without rebuilding the booking flow.

Appointment sites live or die by how quickly a visitor can find a time that actually works. Most pre-booking chats are short and concrete: do you have anything Thursday afternoon, can I get the longer service back to back, what is the deposit, does my preferred stylist work Saturdays. A generic web chatbot does not know any of that.

It invents working hours, hallucinates providers, and quotes prices that do not match the booking page. The result is a confirmation step that contradicts the chat, which kills trust faster than no bot at all. JetAppointment already stores the schedule, the services, the providers, and the excluded dates inside WordPress in well-known custom tables and JetEngine CPTs.

SleekAI maps that data into the chatbot prompt with point and click data sources, so the chat agrees with the booking form on every detail. Per-bot display conditions then let you run a service-page bot, a provider-page bot, and a returning-client bot from the same install, each scoped exactly where the conversation makes sense, and each running on a key the studio owner controls.