If your tutor profiles include topic tags (logarithms, polynomial factoring, integration techniques) the bot reads them and matches accurately. If the profiles only say 'Algebra 2 specialist', topic-level matching is weaker but grade-level matching still works. Most services that care about topic matching add a short topics list to each tutor's profile post or to a taxonomy. The bot then routes the question to the tutor who covers it.

Yes. The bot recognises 'AP in May', 'SAT in March', 'finals next week', and similar signals, then recommends frequency accordingly. It uses real availability from your roster rather than promising slots that don't exist. For a 10-day test prep window, it might suggest two sessions; for a 5-month AP runway, it might suggest weekly. The recommendations are grounded in what your tutors actually offer.

Yes, if those rates are on the pricing page. The bot can also explain when a 4-pack saves money over single sessions and when the trial discount applies. It will not invent discounts; if you want it to honour a specific promo code, add the rule to the prompt. Otherwise it quotes only what is published, which is usually what you want for accuracy and refund clarity.

Yes. Hand off to TutorBird, Calendly, Acuity, or any tool with a public booking URL via deep link or webhook. The bot collects preferred slot, topic, and grade in conversation, then either passes the family to your booking link with the slot pre-selected or fires a webhook that creates the appointment server-side. Most services use deep links because they are easier to support.

The system prompt sets tone. Most services use 'professional and warm' for parent-facing pages and 'friendly and direct' for student-facing pages. The bot can also pick up signals in the first message (a parent worried about a grade versus a student stuck on a problem set) and shift register inside one conversation if you allow it in the prompt.

Homework help is a separate use case from tutor matching, and most services route it differently. You can configure the prompt to either work through a problem with a student (educational, not just an answer) or redirect to a booked session. Many services do both: short homework nudges in chat, longer prep packaged as paid sessions. Logs help you tune that line over time.

Logs stay in your WordPress database. Bring-your-own-key sends prompts directly to OpenAI, Anthropic, or Google with no third-party processor in between. That matters when minors are part of the conversation: you control retention and redaction, and the plugin does not add a new vendor between you and the model. Apply your existing WordPress security to the logs.

Yes. If your pre-session diagnostic, baseline assessment, or trial format is documented on a WordPress page, the bot reads and explains it. Many services add a paragraph on what the trial looks like (45-min Zoom, problem walkthrough, written feedback) so parents know what they are paying for, and the bot quotes that paragraph back when asked.