Substrate ARC: Agentic Booking
When a patient's AI assistant is ready to book, it should book with you.
Patients now ask ChatGPT, Claude and Gemini which doctor to see. Today those assistants can't confirm your network or reach your schedule, so the patient leaves with a phone number, often for someone else. Substrate lets the assistant ask your triage questions, verify insurance and book a real slot at your hospital, inside the chat.
Why health systems are moving now

The first conversation about care is moving into the AI assistant.

The front door moved
Patients ask the assistant first
Health system CIOs report thousands of patients linking their records to ChatGPT, and agents from the frontier labs already reaching scheduling systems (healthsystemCIO, Oct 2026; Becker's Hospital Review, Nov 2026).
The booking breaks
The patient leaves with a phone number
Ask an assistant for an in-network knee surgeon and it lists names, says it can't confirm coverage for the plan and can't book. The first names it offers are often independent groups.
Marketplaces are moving in
Booked somewhere else
Booking marketplaces now expose their inventory to AI assistants directly (Zocdoc, Oct 28, 2026). If your schedule can't be reached, the agent books whoever can be, and you pay per patient for demand your brand created.
One patient, two outcomes

A 58-year-old with a torn meniscus asks an AI assistant for a knee surgeon.

On the left is what a leading assistant said on November 16, 2026. On the right is the same request when the hospital has agentic booking turned on. The doctor and times on the right are made up.

Today: real transcript
AI assistant
I'm 58 and my right knee has hurt for about 3 months. An MRI showed a torn meniscus. Who's the best orthopedic knee surgeon near me that takes UnitedHealthcare Medicare Advantage?
1. Dr. [Name], independent orthopedic group
2. Dr. [Name], independent orthopedic group
3. Dr. [Name], [Hospital] Orthopedics

On insurance: I can't confirm in-network status for your specific plan, and this is worth verifying carefully.

Can you just book it for me with the first available one?

I can't book it for you. I don't have access to [Hospital]'s scheduling system, so the appointment has to come from you by phone or online. Phone: [number].

The hospital's own surgeon is listed third, coverage is never confirmed, and the patient leaves with a phone number.

With Substrate agentic booking
AI assistant

[Hospital]'s knee team can likely help. A few quick questions so I match you with the right doctor: Does your knee lock, catch or give way? Have you done physical therapy, and for how long? Can I share your MRI report and insurance details with [Hospital]?

It catches. I did 6 weeks of PT in person and it didn't help. Yes, share.

Dr. Maya Ellison, knee and sports medicine surgeon, [Hospital] Orthopedics, 1.2 miles

UnitedHealthcare plan in networkNo referral needed
Thu 9:40 AMFri 2:15 PMMon 8:00 AM
Booked: Thursday, 9:40 AM with Dr. Ellison. I've sent your MRI report and PT notes ahead. Bring your insurance card.

The assistant asks what a scheduler would ask, insurance is confirmed, and the slot is real. No phone call.

[Hospital] · Patient triageNew request from AI assistant

New patient · 58 · right knee · UHC Medicare Advantage. Checked against payer criteria for knee arthroscopy with partial meniscectomy.

CheckResultEvidence
Significant knee painMetPatient: 3 months, worse on stairs
Catching or lockingMetPatient: "it catches"
MRI confirms meniscus tearMetMRI report: medial meniscus tear
Arthritis no worse than mildMetMRI report: mild cartilage wear
6+ weeks of physical therapy, no reliefMetPT notes: 6 weeks in person, pain unchanged
Plan in networkMetEligibility check
Fits your prioritiesYesOrthopedics, knee: accepting new patients
Route
Knee and sports medicine surgeon
Flag
Surgery will likely need prior authorization. Records on file already cover the usual criteria.

Every check shows its evidence, so your team can see why each patient was routed. A patient with two weeks of knee pain and no MRI is booked with a non-surgical sports medicine doctor at your hospital instead, who can refer within your system later.

Today vs. with Substrate

Five steps between a patient's question and your schedule.

Every booking an AI assistant attempts runs through the same five steps your schedulers and nurses handle on the phone. Today the assistant fails at most of them. Substrate gives it a way to finish each one under your rules.

Step
AI assistant today
With Substrate
What your team sees
Finding a doctor
Ranks names it found on the web; your specialists may not appear, or appear third
Reads your doctors, locations, specialties and accepted plans from AI-readable pages and a public hospital MCP
Which questions, service lines and plans brought patients in
Insurance
"I can't confirm in-network status for your specific plan"
Runs a real-time eligibility check (270/271, payer APIs and portals across 3,500+ payers) before a slot is offered
Plan, network status and referral requirement on the request
Triage
None; the patient picks a name from a list
Asks the questions your schedulers ask and, with the patient's consent, receives the imaging report and therapy notes
Each criterion marked met or not met, with the evidence behind it
Fit
Any open slot with any doctor, or none at all
Matches each patient to a doctor's preferred patient profile and the payer's criteria; lower-fit patients get the right first visit at your hospital
The route chosen and why, plus prior authorization flags
Booking
"I can't book it for you" and a phone number to call
Books a real slot inside the chat, sends records ahead, or triggers a callback within minutes if the patient wants a person
A booked appointment with the intake packet attached

The "today" column comes from a real AI assistant transcript (Nov 16, 2026; hospital, doctor and phone details hidden). Triage criteria shown on this page are typical of published payer policies for knee arthroscopy.

How it works

Four layers, each useful on its own.

01

Get found and cited correctly

Your doctors, locations, specialties, accepted plans and access rules are published as structured pages that ChatGPT, Claude, Gemini and Perplexity can read and cite. We track which assistants send patients to you and which send them elsewhere.

02

Open a hospital MCP

A read-only, unauthenticated endpoint lets any assistant search your doctors, plans and open appointment windows. It carries no patient data. It uses the same model as our public payer MCP, which assistants already query at mcp.substrateai.com/payers.

03

Triage and verify before the visit

When the patient agrees to share, their assistant hands over symptoms, imaging, therapy notes and insurance. Substrate checks them against payer criteria and each doctor's fit rules, verifies eligibility, and shows every check with its evidence.

04

Book, or call back in minutes

The appointment is written to your scheduling system with the packet attached. If the patient would rather talk to a person, your front desk gets the request and calls back while the patient is still interested. Your team sees new patients found, triaged and booked by service line each week.

“Deploying the Substrate Claim Status AI agent enabled us to handle 4x the volume with the same team.”

Lance Merkley, VP RCMS Technical Services, NextGen RCM Services

Read the NextGen story
Read the NextGen story
FAQ

Agentic booking questions

What is agentic booking?

It is when a patient's AI assistant finds a doctor, checks coverage and books the appointment for them. Substrate is the hospital side of that exchange: it gives assistants accurate data about your doctors and plans, asks your triage questions, verifies insurance and books into your schedule under rules your team sets.

Which AI assistants does it work with?

Any assistant that can read the web or call an MCP server. Your data is published as structured pages and as an MCP endpoint, and booking runs on standard scheduling resources (FHIR R4 Slot and Appointment) so no single assistant or EHR is required.

How is patient data protected?

The public layer carries no patient data. Clinical and insurance details move only after the patient agrees to share them in their assistant, travel over an authenticated handoff, and are processed under a BAA with HIPAA and SOC 2 controls and a full audit trail.

Will this send us patients we can't treat or who aren't covered?

Insurance is checked before a slot is offered, and each doctor's fit rules decide who books with whom. A patient who isn't ready for a surgeon gets the right first visit instead, such as non-surgical sports medicine, so they still start their care with you.

How is this different from a booking marketplace or a patient portal assistant?

A marketplace books the patient into its own inventory and charges per booking, and the relationship sits with the marketplace. A portal assistant helps once the patient is already logged in to your portal. Substrate opens your own schedule to assistants outside your walls, on your rules, so the patient stays yours.

Where do we start?

With one service line. We need read access to your provider directory and scheduling templates, plus the questions your schedulers already ask for that service line. We start by showing you what ChatGPT, Claude and Gemini say about you today.

See where AI assistants send your patients today.

Book 30 minutes. Pick one service line and we'll run the questions your patients ask in ChatGPT, Claude and Gemini, show you who they get sent to, and walk through what triage, insurance checks and booking would look like on your schedule.

Security first, from the ground-up
End-to-end encryption protects sensitive data in transit and at rest, ensuring complete confidentiality.
Zero-trust architecture verifies every request, reducing attack surfaces and preventing unauthorized access.
Regular security audits and compliance checks keep our infrastructure resilient against evolving threats.
Granular access controls allow precise permission management, securing data at every level of the system.