Appointment booking
Live availability across providers and locations, with new-patient and established-patient paths handled differently.
02 · Communication
AI Web Chat Agent
Most practice websites convert a fraction of the people who visit them. The Web Agent answers the question that brought them there and books the appointment in the same conversation.
Agent at a glance
- StatusIn development
- CategoryCommunication
- Deployment2–4 weeks, shadow mode first
- Review modelHuman approval per action, configurable
- Headline metric2–4× Booked visit lift
- EvidenceFull action log, exportable any time
2–4×
More booked visits
Typical lift versus a static contact form.
< 5 sec
First response
Visitors never wait for a callback that may not come.
60%+
Questions resolved
Answered without a staff member ever seeing the chat.
What it does
Everything in this agent, in writing.
Practice knowledge answers
Built from your site, your intake packet and your staff — so answers about insurance, referrals and prep instructions match your actual policy.
New-patient capture
Name, contact, insurance and reason for visit collected in-flow, with consent recorded, before anything is written to the EMR.
Bilingual conversations
Spanish-first and other languages handled natively, with clinical escalations routed to a qualified human.
Warm handoff
A visitor who asks for a human gets a scheduled callback or a transfer, with the transcript already in the chart.
Conversion analytics
Which pages, which questions and which drop-off points cost you bookings, reported monthly.
Deployment
Live in weeks, not quarters.
01
Content and intent build
We index your public information and interview staff to close the gaps that generate most questions.
02
Shadow and tune
The agent drafts replies to real traffic for review before it responds to visitors.
03
Live on the highest-traffic pages
Homepage, location pages and service pages first.
04
Expand and optimise
Monthly review of the questions that were not answered well, with fixes to the knowledge base.
Guardrails
What it will never do.
These limits hold regardless of configuration. They exist so that you can put an agent in front of patients without putting your licence next to it.
- Answers only from your approved knowledge base — no improvisation on clinical or billing specifics
- No symptom assessment or triage; anything clinical routes to staff
- Accessibility: keyboard navigable, screen-reader labelled, and never blocks page content
- Consent language shown before any personal detail is collected, and logged
- Refuses to discuss another patient, a balance dispute or a medical record through the widget
Human in the loop, by your choice
Every action can require approval before it commits. Start with all of web agent queued to your staff or to ours, watch the accuracy numbers, then widen autonomy workflow by workflow — or leave it queued forever. Both are supported.
Escalations land with certified people
Our review queue is staffed by the same certified coders, billers and credentialing specialists who run our managed services. Not a support desk, and not a chatbot watching a chatbot.
Full evidence trail
Input, decision, action, confidence, model version, reviewer and timestamp — retained and exportable as CSV or JSON, including after you leave us.
What we report against
Operational targets for this agent. They are internal commitments measured on your own data, reported monthly — including the misses.
2–4×
Booked visit lift
< 5 sec
First response
60%+
Self-resolved
24/7
Availability
Works with your systems
Your EMR, your numbers, your data.
- Your website (any platform)
- Athena
- eClinicalWorks
- NextGen
- Tebra
- Google Business Profile
We integrate through FHIR and HL7 where the vendor supports it, and through secure automation or structured document intake where it does not. No API required, no vendor commission taken.
FAQ
Common questions.
Does it work with our current website?
Yes. We add one script tag or an iframe to any platform — WordPress, Squarespace, Wix, Webflow or a custom build. No redesign required.
Will it make up answers?
It answers from your approved knowledge base and says 'let me have someone follow up' when the answer is not there. That refusal behaviour is the point, not a limitation.
Can it take payments or check balances?
It can take a copay through your existing processor where you want that, and it will not discuss balances without identity verification. Most practices start with booking only.
How is this different from a chatbot plugin?
A plugin answers questions. This books in your EMR, writes to the chart, follows your scheduling rules and escalates to named staff — with the same audit log as every other agent.
Related agents
Usually deployed together.
03
In development
AI SMS Agent
Two-way text that confirms, reminds and refills the schedule. Handles replies like 'can I move it to Thursday', keeps a TCPA-compliant opt-out record, and fills cancellations from your recall list.
- Confirms and reschedules by text, automatically
- Fills cancellations from your waitlist in minutes
- TCPA-compliant consent, opt-out and quiet hours
04
In development
AI Email Agent
Triages the practice inbox: sorts patient questions, payer notices, vendor noise and referrals, drafts replies for staff approval, and files what belongs in the chart.
- Inbox triaged by intent, not by sender
- Drafts replies for one-click staff approval
- Referrals and payer notices routed to the right queue
05
In development
AI Document & Referral Agent
Reads inbound faxes, scans, portal messages and referrals, identifies the document type, matches the patient, files it in the right chart and turns orders into tasks.
- Faxes and referrals classified and filed to the chart
- Patient matched by name, DOB and MRN — with exceptions queued
- Orders, labs and abnormal findings routed to a clinician
See it run on your own workflow.
A 30-minute demo using your scenarios, your payer mix and your systems. We will show you the guardrails and the audit log, not just the happy path.
A 30-minute call with an operations lead. No obligation, no sales sequence, and we will say so if you do not need us.