Yes. The system prompt can ingest a jurisdiction page (UBE states with cut scores, plus California, Louisiana, Puerto Rico, and any jurisdiction-specific track) and recommend a study path accordingly. UBE applicants get a unified MBE/MEE/MPT plan; California applicants get a different track that includes Performance Tests and California-specific essay topics. The bot routes correctly without giving legal advice on jurisdiction choice.

The bot doesn't grade essays itself, and that's intentional. Bar essay grading requires a trained reviewer who has read hundreds of model answers and your service's grading rubric. The bot captures the essay text, applies per-essay or package pricing, queues the submission to your reviewer roster by topic, and confirms turnaround. Most services use the bot as the intake point and email-handoff layer, not a grader.

Yes. If your tutor profiles list MBE subjects, MEE topics, and MPT specialty, the bot reads those fields and matches accordingly. A repeater whose MBE is at 132 gets routed to MBE-focused tutors; a JD with a strong MBE but weak MEE writing gets a different tutor. The bot also handles compound needs: a 60-hour package with split MBE/MEE coverage routes to a primary tutor plus a secondary reviewer.

If your hour-bundle and essay-grading pricing is on the pricing page, yes. The bot surfaces trial-session discounts in context and explains when a 60-hour package is cheaper than singles plus separate essay-grading fees. It won't invent discounts; if you want a specific code honoured, add the rule to the prompt. Otherwise it quotes only what's published.

Yes. The 28+ display conditions let you run a repeater bot on /repeaters/ pages with different tone and tutor roster, and a first-timer bot on /first-time-takers/ pages with a fuller content-review plan. Conversation logs stay separate so you can review repeater enquiries without scrolling past first-timer threads. Most services find the repeater bot needs warmer, more direct framing.

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 because bar applicants share sensitive details: prior attempt scores, char-and-fit history, MPRE results, jurisdictional history. You control retention and redaction, and the plugin doesn't add a new vendor between you and the model.

No. The system prompt should explicitly forbid giving legal advice, opinions on character-and-fitness disclosures, or recommendations on jurisdiction strategy. The bot describes your prep service: tutoring, essay grading, packages. For any character-and-fitness or admissions-strategy question, it routes to a 'consult call with a senior tutor or a bar admissions attorney' rather than guessing in chat.

The bot handles accommodation enquiries with care. It explains your service's accommodation-aware practice (extended time, reading aloud, separate room) and how that affects scheduling and pacing, then routes to a consult call rather than recommending a specific accommodation. For jurisdiction-specific accommodation paperwork (NCBE, state-specific filings), the bot references the relevant board and recommends the official process, never invented filings.