Yes. The system prompt can ingest target law-school tiers from a WordPress page (T14, T20, regional ABA) and recommend a section emphasis and target score range accordingly. A T14-bound applicant gets a 170+ framing; a regional applicant gets a 158 framing. Update the tier page and the bot reflects the new framing on the next conversation, no retraining required.

If your WordPress pages reference the current format (two scored LR sections, one scored RC section, one unscored experimental section, plus the separate Argumentative Writing task), the bot reads and uses that framing. The system prompt should note the current section count so the bot doesn't drift into Logic Games references that no longer apply to administrations after August 2024.

It can describe your blind-review process and explain why it works: students re-do every flagged question untimed, write up the reasoning, then meet with a tutor to discuss the gaps. The bot itself doesn't grade blind-review write-ups; that's the tutor's job. Most prep services use the bot to capture which PrepTests a student has completed and queue the next BR session.

If your hour-bundle pricing is on the pricing page, yes. The bot surfaces trial-session discounts in context and explains when the 30-hour package is cheaper than singles plus separate PrepTest 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 an LSAT bot on /lsat/ pages and an admissions consulting bot on the consulting pages, each with their own tone and tutor roster. Conversation logs stay separate so you can review LSAT enquiries without scrolling past consulting threads. Most prep services run two to three bots: LSAT, admissions, and a third for combined or pre-law advising.

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 law-school applicants share sensitive details: undergraduate GPA, prior LSAT scores, target schools, addenda topics. You control retention and redaction, and the plugin doesn't add a new vendor between you and the model.

The system prompt should forbid promising specific point gains (no 'we guarantee +10'). The bot describes typical practices: 100-150 hours for a 10-point climb, 25-30 timed PrepTests, weekly blind-review sessions. It quotes realistic floors and ceilings for the time remaining and routes to a consult call for any guarantee terms or unusual starting-point cases.

The bot handles retakes explicitly. It collects the prior attempt's score, score-cancellation status, and gap analysis (LR vs RC), then recommends a focused cadence on the dragging section. For applicants near a T14 floor (167-169), the bot routes to a high-yield LR question-type plan and your senior tutor roster rather than a generic 'study more' prescription.