No. SleekAI is configured with explicit refusal language for every diagnostic, treatment, dosage, and symptom-interpretation question. The instruction includes a hard refusal clause: never diagnose, never recommend specific treatments, and route urgent concerns to 911 or the local emergency number. ENT symptoms can range from trivial to time-critical (severe facial trauma, sudden hearing loss, signs of epiglottitis), and the bot is configured to escalate every clinical question to a real clinician rather than guess.

Yes. ENT is unusually subspeciality-heavy for an outpatient practice, and routing matters. The bot reads each surgeon's subspecialty (rhinology, otology, laryngology, paediatric, sleep medicine, head and neck oncology) and routes accordingly. 'I'd like a sinus consult' goes to rhinology; 'I'm worried about my child's hearing' goes to paediatric ENT or audiology depending on your workflow. Misrouting is one of the biggest drivers of patient dissatisfaction in ENT, and a chatbot that gets it right pays for itself quickly.

Yes, if your scheduler exposes audiology as an appointment type, the bot can route hearing test requests to the audiologist's calendar rather than the surgeon's. Most ENT practices have a separate appointment type for audiology that the bot can pick up automatically from the scheduler's published list. Prep instructions (bring medication list, hearing aids if applicable, prior audiogram if available) are added to the confirmation.

The system prompt is configured to recognise ENT-specific urgency keywords (severe facial trauma, sudden onset hearing loss, severe nosebleed not controlled with pressure, difficulty breathing, severe throat pain with drooling) and immediately route the patient to call 911 or the local emergency number. The standard urgency routing applies to general red flags (chest pain, signs of stroke). A visible disclaimer in the widget header reinforces the channel's scope upfront.

Yes, plan-by-plan from your published policy page. The bot tells patients which insurance plans you accept, whether each plan requires a PCP referral for specialist visits, and what prior-authorisation steps exist for procedures like sinus surgery or tonsillectomy. It defers exact coverage decisions to insurance verification with the front desk, since plan tiers vary, but it cuts the routine plan-acceptance question to a single message.

Sleep apnea evaluations have a distinctive multi-step workflow (consult, home sleep study or in-lab polysomnography, follow-up with CPAP titration or other intervention discussion). The bot walks patients through your practice's specific process, books the consult, and explains what to expect at each stage from your published content. It does not interpret any sleep study data, that conversation stays with the sleep medicine physician at the follow-up appointment.

Yes, in your WordPress database. Retention is configurable. For PHI we recommend short retention windows (days, not years), encryption at rest on the database, role-restricted access on logs, and BAAs across your stack including the API vendor (OpenAI, Anthropic, Google, OpenRouter). Document the chat channel in your Notice of Privacy Practices and your records-retention policy.

Yes. Patients writing in any common language get responses in their language, with operational details translated cleanly and the clinical-refusal language translated faithfully. ENT practices often serve patients across age groups and linguistic backgrounds, and a multilingual chat front door raises access for families who otherwise navigate specialist care through phone interpreters or a bilingual family member.