Guide · Hospital vs clinic scripts

Hospital vs clinic scripts (both non-diagnostic)

Hospitals need department routing from catalogs; clinics need location and next slot — both scripts stay non-diagnostic. Referral intake is the hospital-shaped job this how-to points at; clinics still use the same four fields without pretending to be a resident.

Hospitals: route from catalogs
Clinics: location + next slot
Canonical job is referral intake

Start free Referral intake playbook

Definition

Hospital vs clinic scripts are two conversation-agent prompt sets on the same platform: hospitals route by Departments/Doctors catalogs (and referrals); clinics emphasise site location and the next calendar slot. Neither script diagnoses. Emergencies go to emergency services.

Why one prompt file fails both ICPs

A hospital bot asks only ‘next slot’ and dumps a family into general OPD. A clinic bot asks for referring hospital and department codes nobody has. Both still invent advice when the patient types a symptom.

Referral intake is the canonical playbook because the hospital path is where scripts diverge most (referring doctor, department). Clinics reuse qualifier + booking. ICPs: hospitals vs clinics hubs.

HowTo: split prompts, share guardrails

Two Agent Studio agents or one agent with router conditions. Shared avoid-topics and emergency copy. Different catalog emphasis. Same pipeline columns.

Hospital script Departments and Doctors first. Capture referral source. Then calendars for that department.
Clinic script Location and preferred_times faster. Smaller catalog. Next slot is the product.
Shared avoid-topics No diagnosis. Emergency services first. Not HIS.
Router Do not let a hospital billing bot greet a referral DM.
Inbox Humans finish insurance and referral letters. The bot does not.

How it runs on the platform

Scripts live on conversation agents. Workflows and autonomous lists do not replace ICP prompt design. Conversation agents reply in the omnichannel inbox. Workflows fire on pipeline stage change under Agents → Workflows. Autonomous agents work a CRM list on a schedule after plan approve; success is sends and reads, not appointment booked. Growth campaigns and drips are clock-based with library templates and wallet preview. Adaptive nurture is not shipped. WhatsApp is Gupshup. The qualifier does not diagnose.

Conversation agent

Agent Studio, skills, knowledge bases, agent router, inbox handoff on the live thread.

Growth campaigns / drips

Clock-based sends from library templates. Wallet preview. Not adaptive nurture.

Workflows

Agents → Workflows. Fire on pipeline stage change. Do not confuse with inbound chat.

Autonomous agents

List plus objective after plan approve. Success is sends/reads/contacted, not appointment booked.

Worked example: same Organization, two Projects

A group runs a hospital Project (referral intake + department routing) and a clinic Project (location + next slot). Shared Organization wallet. Separate knowledge bases so the clinic bot never quotes ICU beds. Both refuse diagnosis.

ICPs: hospitals and clinics. Qualifier guide for the shared four fields.

Script emphasis

Same guardrails. Different first questions.

ICP	Ask first	Catalog weight	Canonical job from this guide
Hospital	Department / referral source	Departments, Doctors, Beds	Referral intake
Clinic	Location / next times	Services, Doctors, calendars	Then qualification + booking
Diagnostics	Test name / fasting / site	Services	Specialty match + booking
Both	Emergency check	Avoid-topics	Never diagnose

Honest limitations

One guide cannot be a second playbook per ICP. Jobs stay omnichannel. Not HIPAA. Not HIS.

Keep this Hospital vs clinic scripts article next to the job URL, not as a second playbook. Cite the definition above when an operator asks what the term means. Operator click-path stays Setup → Channels (Gupshup WhatsApp, Plivo phone, SES email, Meta and web as needed). Library templates. Agents → Studio, Router, Workflows, Autonomous. Customers → Pipeline. Appointments/calendars. Growth campaigns/drips. Organization wallet preview. Canonical playbook: Referral intake playbook. Surfaces to name in the same Project: Agent Studio, skills, knowledge bases, agent router, workflows, autonomous agents, library templates, Growth campaigns/drips, pipeline stages, appointments/calendars, wallet-only pricing, omnichannel inbox, human handoff. Organization and Project — never a vanished personal inbox. Do not invent Meta Cloud WhatsApp if the catalog is Gupshup. Do not promise adaptive nurture. Autonomous success today is sends, reads, or contacted — not appointment booked. Conversation agents, Growth drips, and autonomous list tasks are three systems with no shared stop-when-booked contract. Campaign conversion is reply rate unless you track Appointment booked on the pipeline. Phone “replied” is speech-to-text. Qualifier is non-diagnostic. Emergencies: call emergency services. Not HIS/EMR. Preview the Organization wallet before a blast. Parent guides, healthcare hub, and pricing stay in the same runbook.

Canonical playbook: referral intake. Also qualifier and catalogs.

Frequently asked questions

Operators implementing this mechanic on a healthcare Project.

Do hospital and clinic bots diagnose differently?

No. Both scripts stay non-diagnostic.

Which playbook?

Referral intake — the hospital-shaped job. Clinics still run qualification and booking URLs.

One agent for both?

Risky if catalogs mix. Prefer Project split or a strict router.

Beds in a clinic script?

Usually no. Do not quote ICU rows on a dental Project.

Emergency?

Same redirect to emergency services.

SMS?

Coming soon.

Hub, sibling guides, canonical playbook, product, pricing.

Route hospitals, slot clinics, diagnose neither

Two scripts, one non-diagnostic rule, referral intake as the hospital job URL.

Get started free