Guide · Doctors & services KB

Doctors and services knowledge bases (not a chart)

Upload Departments, Doctors, Beds, and Services catalogs; the agent answers hours and names, not a diagnosis from those rows. Specialty match is a catalog lookup after the qualifier — not a clinical opinion wearing a PDF.

Four catalog types
Hours and names, not findings
Canonical job is specialty match

Start free Specialty match playbook

Definition

Healthcare knowledge bases are Project files and catalogs: Departments, Doctors, Beds, and Services. The conversation agent retrieves hours, names, locations, and package labels. They are not an EMR, not a lab chart, and not a license to diagnose.

Why pasted doctor bios become fake advice

A hospital dumps 40 CVs into one knowledge file. The bot quotes a paragraph that sounds like treatment. The qualifier never captured location. Beds catalog is unused. Families think the bot ‘knows’ the case.

Specialty match is the job: route to the right department or doctor from catalogs after four qualifier fields. Diagnostics ICPs feel this when test names collide with symptoms.

HowTo: load catalogs the agent may quote

Split Departments, Doctors, Beds, Services. Keep hours and sites current. Scope knowledge per Project if two hospitals share an Organization. Router so a billing bot does not read doctor bios.

Create four catalogs Agents → Studio → knowledge. Departments, Doctors, Beds, Services — not one mega-PDF of protocols.
Match after qualifier fields Service_need and location first. Then quote hours and names.
Refuse findings If the question is ‘what do I have,’ redirect: I can share services and slots; I cannot diagnose. Emergencies → emergency services.
Router Specialty bot vs billing vs reminder. Wrong router quotes the wrong catalog.
Keep HIS out of the story CoPulse is not HIS/EMR. Do not claim pharmacy or billing replacement.

How it runs on the platform

Knowledge is attached to conversation agents. Growth templates should not dump clinical PDFs as if they were catalogs. 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: diagnostics test menu

A diagnostics Project loads Services with fasting flags and hours, Doctors with reporting radiologists, Departments for collection centres. Agent answers ‘lipid profile, Koramangala, 7:00.’ It does not interpret last week’s values.

ICP: diagnostics. Qualifier: non-diagnostic qualifier.

What each catalog is for

Four catalogs. Zero diagnoses.

Catalog	Agent may say	Agent must not say	Typical ICP
Departments	Cardiology hours, floor	What your ECG means	Hospitals
Doctors	Name, days, language	A treatment plan	Clinics / hospitals
Beds	Availability language you maintain	Admit/discharge orders	Hospitals
Services	Test/package name, prep flag	Interpret a report	Diagnostics

Honest limitations

Stale catalogs hallucinate hours. There is no automatic HIS sync claimed here. Avoid-topics still apply.

Keep this Doctors & services KB 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: Specialty match 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.

Playbook: specialty match. Product: AI agents. Scripts: hospital vs clinic.

Frequently asked questions

Operators implementing this mechanic on a healthcare Project.

Can the agent diagnose from the Doctors catalog?

No. It answers hours and names, not a diagnosis from those rows.

Is this EMR?

No. CoPulse is not HIS/EMR.

One knowledge file for three hospitals?

Scope per Project or you will quote the wrong site.

Which playbook?

Specialty match.

Beds mean we manage occupancy?

Catalogs hold what you upload. We do not claim HIS bed management.

HIPAA?

Not a HIPAA claim. See opt-in/out for consent operations.

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

Load catalogs the bot is allowed to quote

Hours and names. Never a finding. Specialty match is the job.

Get started free