Yes. If your tutor profiles list Discipline specialties (BAR, ISC, TCP), the bot reads those fields and matches accordingly. A candidate targeting corporate tax routes to TCP-focused tutors; an IT-audit candidate routes to ISC. The bot can also handle Discipline indecision: if a candidate hasn't chosen, the bot describes the trade-offs from your published guidance and routes to a consult call rather than picking for them.

If your WordPress pages reference the post-2024 format (three Core, three Discipline choices, 18-month rolling window), the bot reads and uses that framing. The system prompt should note 'CPA Evolution format only, not legacy BEC/AUD/FAR/REG' so the bot doesn't drift into BEC content that no longer exists. Most services update their content once, and the bot reflects it on the next conversation.

The bot doesn't grade Simulations itself, and that's intentional. CPA Simulation grading requires a CPA or experienced reviewer who has trained on the AICPA blueprint. The bot captures the Simulation response, applies per-Simulation or package pricing, queues the submission to your reviewer roster by topic, and confirms turnaround. Most services use the bot as the intake and email-handoff layer, not the grader.

If your section-package pricing is on the pricing page, yes. The bot surfaces trial-session discounts in context and explains when a Core + Discipline package is cheaper than singles plus separate Simulation-review 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, plus a reminder that state examination fees are paid separately.

Yes. The 28+ display conditions let you run a working-professional bot on /working-pros/ pages with evening-and-weekend tone and a Slack-support emphasis, and a full-time bot on /full-time-prep/ pages with a faster cadence. Conversation logs stay separate so you can review working-pro enquiries without scrolling past full-time threads. The Discipline-choice rationale often differs too.

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 CPA candidates share sensitive details: prior attempt scores, employer, state board status, education-credit 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 accounting, tax, or audit advice, plus opinions on licensure strategy or state board interpretation. The bot describes your prep service: tutoring, Simulation review, packages. For any state-board licensure or specific accounting question, it routes to 'a consult call with a senior CPA tutor or your state board' rather than guessing in chat. This applies to 150-hour rule interpretations too.

The bot handles transition cases explicitly. Candidates who passed legacy BEC, AUD, FAR, or REG before the Evolution conversion get a customised path: which Evolution sections their credits transfer to, which they still need to sit, and what the rolling-window reset looks like. The bot reads your transition-mapping page and quotes it, never invents the credit-transfer rules, and routes any ambiguity to your senior tutor or state board.