Fixed quote after a free call

An AI receptionist for medical offices that knows its limits

We build an AI front desk for your website, text line or phone that answers routine questions from the clinic's own approved answers, takes booking and prescription-refill requests for staff, captures after-hours messages and says clearly that it is automated. It never gives clinical advice and sends urgent or clinical messages to your team or emergency instructions. Projects typically cost $2,500 to $7,500 and take five to eight weeks.

The problem

What an AI front desk for a medical office should and should not do

Clinic phones carry the same questions all day: hours, location, accepted insurance, new-patient availability, how to get records and how to reschedule. Each call pulls a coordinator away from the patient at the desk, and after hours they go to voicemail.

A medical office AI answering service only works if it is narrow and honest. It must answer from wording the clinic approved, refuse clinical questions, recognise urgent language and hand over to a person, and keep patient data inside vendors covered by the right agreements.

What we build

What our AI receptionist for medical practices includes

Approved answer library

Hours, locations, services, accepted plans, records requests and policies written and approved by the clinic, and the only source the assistant uses.

Web chat, text and voice

A chat widget on your site, plus optional text or phone line on the same answer library.

Booking and refill requests

Collects details and creates a request for staff, or links to self-scheduling where the EHR offers it.

Urgent and clinical hand-off

Symptoms and clinical questions trigger the clinic's emergency instructions and a staff alert, never an AI answer.

AI disclosure

The assistant says it is automated at the start and offers a person at any time.

Transcript review

Logged conversations and a weekly list of questions it could not answer.

Who does what

Automation does the chasing, people make the calls.

Every step is marked: what runs on its own, what a member of staff reviews and what stays with a person who decides.
  1. 01 Automated

    Question asked

    A patient asks on the website, by text or by phone.

  2. 02 Automated

    Answered from the library

    Routine questions are answered from approved wording, with a link to the source page.

  3. 03 Automated

    Request captured

    Booking, refill and records requests are collected for staff.

  4. 04 Coordinator review

    Staff confirm

    Coordinators confirm requests and answer what the assistant could not.

  5. 05 Clinician or medical director decides

    Clinical questions

    Anything clinical or urgent goes to a clinician or the emergency process.

How it behaves

How the AI receptionist behaves

What each person sees and what runs in the background, including what happens when something goes wrong.

What the patient sees

  • A clear note that the assistant is automated
  • Short answers from the clinic's approved wording
  • A request form or self-scheduling link
  • A person whenever they ask something clinical

What staff see

  • Booking, refill and records requests to confirm
  • Urgent messages flagged immediately
  • A weekly list of unanswered questions

What the automation does

  • Matches questions to the approved library
  • Refuses clinical questions and hands over
  • Logs every conversation

Edge cases and fallbacks

Question not in the library
Says it does not know, offers a person and adds the question to the review list.
Patient describes symptoms
No advice; emergency instructions and a staff alert.
Caller asks for a person
Transferred or a call-back is booked at once.
AI provider outage
The widget falls back to a contact form and the phone line to voicemail.

Architecture

An AI receptionist for a medical office at a glance.

The setup we usually start from. We adapt it to the phone system and practice software you already use.
Patient Chat, text, call Assistant service n8n or Laravel Language model Claude, Gemini, GPT Approved answers Clinic-written Requests Booking, refills Coordinators Urgent, clinical Transcripts Weekly review
  • Input
  • Logic and services
  • AI step
  • Data
  • Output
  • People

How it flows

  1. 1 A patient asks a question and is told they are talking to an automated assistant.
  2. 2 The service retrieves matching approved answers and passes them, with fixed rules, to the language model.
  3. 3 Routine answers go back with a source link; booking, refill and records requests go to staff.
  4. 4 Urgent or clinical messages reach coordinators at once, and every conversation is logged for review.

Project planner

How the project runs, phase by phase.

Typical durations for a first version. Your proposal lists the exact phases, dates and what you sign off at each step.

AI receptionist & medical answering assistant project plan

Typical time to launch: about 6 weeks, then support

  1. 01

    Discovery

    About 1 week

    Collect real questions from calls, portal messages and emails; agree what the assistant may and may not answer.

  2. 02

    Answer library

    About 1 week

    Write and approve answers, emergency wording and after-hours wording with the clinic.

  3. 03

    Build

    About 2 weeks

    Chat widget or phone line, retrieval, request capture, hand-off alerts and logging.

  4. 04

    Test

    1 to 2 weeks

    A test set of real, tricky and clinical prompts; the medical director signs off.

  5. 05

    Launch

    2 to 3 days

    Soft launch after hours or on part of the site, then widen.

  6. 06

    Support

    Ongoing

    Weekly transcript review at first, then monthly library updates.

What it runs on

Real products only, connected through the access each vendor provides. See all integrations

Claude, Gemini or OpenAI models under healthcare terms n8n AI Agent node or Laravel Website chat widget Twilio Voice and Messaging EHR self-scheduling link where offered Slack, Teams or email alerts

Cost estimate

What it costs, line by line.

Estimates to plan with. Your fixed quote follows a free call, once we have seen your systems and volumes.
  • Discovery and answer library

    Real questions collected, answers written and approved.

    $500 – $1,200

  • Build

    Assistant service, widget or phone line, retrieval, hand-off and logging.

    $1,200 – $4,000

  • Integrations

    Scheduling link or EHR, alerts and messaging.

    $300 – $1,000

  • Testing and evaluation set

    Real, tricky and clinical prompts tested before launch.

    $300 – $900

  • Launch and training

    Soft launch, transcript review and team walkthrough.

    $200 – $400

  • Total project estimate

    $2,500 – $7,500

Optional monthly care after launch is quoted with your proposal. Fixed quote after a free call. A voice line costs more to build and run than web chat. Model usage and telephony are billed to your accounts directly.

Monthly running costs you pay directly

Estimates from the vendors' published pricing, checked November 2026. Billed to you by each vendor, never marked up.

  • AI model usage: Billed by the provider per use under its own healthcare terms; short sorting and summary steps are usually a small monthly amount at clinic volumes.
  • Telephony: Twilio voice and messaging at published rates if you add a phone or text line.
  • Hosting: n8n Cloud from about €20 a month, or your own server.

What pushes cost up

  • Systems without an API, or with integration access that must be requested from the vendor
  • Writing data back into your core system rather than only reading from it
  • Several locations, brands or very different processes to support
  • Custom apps, dashboards or a voice line on top of the workflows

What keeps cost down

  • One location and one clear process to start with
  • Cloud software with a documented API
  • Using tools you already pay for instead of adding new ones
  • Approved wording and sample data ready at the start
Get a fixed quote

Privacy and consent

Rules we design for, with the sources.

General information to plan with, not legal advice. Your counsel or data protection adviser confirms what applies to your practice.

EU: tell people they are talking to AI

Article 50 of the EU AI Act requires AI systems that interact with people to inform them they are dealing with an AI system, from 2 August 2026. We add the disclosure everywhere.

Source: artificialintelligenceact.eu

US: HIPAA vendor agreements

Any AI or telephony vendor that receives patient information for the clinic needs a business associate agreement, or the assistant is kept free of patient data.

Source: www.law.cornell.edu

EU and UK: health data

Symptom descriptions are special category data under Article 9 GDPR and UK GDPR, so the assistant collects as little as possible.

Source: gdpr-info.eu

How we deliver

Agile delivery, in 1 to 2 week sprints.

We deliver in short Agile sprints using Scrum, so you see working software every one or two weeks instead of waiting for a big reveal at the end.

Every sprint

  1. 1 Sprint planning. At the start of each sprint we agree which backlog items we will finish, each with written acceptance criteria you can check.
  2. 2 Daily stand-up. A short internal check-in on progress and blockers. You get a written update in your Slack or Teams channel, not another meeting.
  3. 3 Sprint review and demo. At the end of each sprint we demo what was built on test data or in a shadow run, and you accept it or ask for changes.
  4. 4 Retrospective. The team looks at what went well and what to change in the next sprint, and we share anything that affects you.

How scope stays under control

Product backlog
Every feature, fix and question in one prioritised list you can see at any time.
Acceptance criteria
Plain-language conditions for "done" on each item, agreed before work starts.
Change requests
New ideas go into the backlog with an estimate. Nothing changes scope or price without your written approval.
User acceptance testing (UAT)
Before launch your team tests the real workflow against the acceptance criteria and signs off.

Tools we use

Jira, ClickUp or Trello for the backlogSlack or Microsoft Teams for updatesGitHub for code and version historyLoom or a live call for demos

Project manager / Scrum master

Runs the sprints, keeps the backlog and timeline honest, and is your single point of contact.

Business analyst

Maps how the work runs today, writes the workflow specification and acceptance criteria with your team.

Automation engineer

Builds the n8n workflows, integrations, AI steps and error handling.

Backend developer

Writes custom code where a no-code step is not enough: APIs, data sync, secure storage.

Frontend / mobile developer

Builds forms, booking pages, dashboards, web apps or Android apps when the project needs them.

QA engineer

Tests every workflow against the acceptance criteria, including edge cases and failure paths.

DevOps engineer

Sets up hosting, access, backups, monitoring and alerts, and the deployment pipeline.

Who does what at each phase

Free call
Project manager, business analyst
Understand the problem, check it is worth automating and outline a rough range.
Discovery
Business analyst, automation engineer
Map the current process, systems and data, and agree success measures.
Design
Business analyst, automation engineer, backend developer
Write the workflow specification, data flows, compliance notes and backlog with acceptance criteria.
Sprints
Automation engineer, developers, QA
Build, test and demo in 1 to 2 week sprints; you accept or adjust after each demo.
UAT and launch
QA, DevOps, project manager
Your team tests and signs off, we switch on, monitor closely and train the team.
Support
Automation engineer, DevOps
Stabilisation window, then optional monthly care with monitoring and changes.

A point of contact

One person who can answer questions and approve decisions, with about an hour a week during the project.

Access

Admin or API access to the systems involved, created as separate accounts with the least access needed.

Sample data

Real but non-sensitive records (or de-identified ones) so we can design and test against reality.

Approved wording

Message templates, policies and consent wording (for SMS, your opt-in and opt-out text) reviewed by you.

Vendor agreements

Signed agreements with the software vendors that will handle personal data, such as a BAA or processor contract.

Time for testing

A few hours from the people who will use the system, for the demos and user acceptance testing.

Working system

Workflows, integrations and any apps running in your accounts, under your keys.

Documentation

Workflow specification, data-flow map, run book and exported workflow files.

Training

A walkthrough for the team and a short recorded video for new starters.

Handover

All access, credentials and code handed over; you can keep us or take it in-house.

Stabilisation window

Fixes for anything that does not meet the agreed acceptance criteria after launch.

Support options after launch

  • No plan

    You run it yourselves after the stabilisation window and contact us when you need a change.

  • Monthly care

    Monitoring, error alerts, small changes and updates each month, with an agreed response time.

  • Priority care

    Faster response times for business-critical workflows and a monthly review call.

How a project moves through our team

Free call PM and analyst Discovery Process and data Design Spec and backlog Sprints Build, test, demo Your review Accept or adjust UAT and launch Sign-off, go live Support Monitor and improve
  • Input
  • Logic and services
  • People
  • Output
  • Data

How it flows

  1. 1 A free call with the project manager and business analyst to understand the problem and whether it is worth building.
  2. 2 Discovery and design produce a written specification, data-flow map and a backlog with acceptance criteria.
  3. 3 The team builds in 1 to 2 week sprints; you review a demo at the end of each and accept or adjust.
  4. 4 Your team runs user acceptance testing, we launch, then monitor and improve under a support plan.

FAQ

AI receptionist & medical answering assistant questions, answered.

No, and ours is built to refuse. It answers practical questions from approved wording. Any symptom, medication or result question goes to a person or the clinic's emergency instructions.

It can be. A voice line uses the same answer library and rules as web chat, costs more to run, and hands over to staff or your existing answering service when needed.

Yes. It says so at the start and offers a person at any time. In the EU this is required under the AI Act from 2 August 2026, and we treat it as good practice everywhere.

Where the EHR offers self-scheduling we link to it. Direct booking through an API is possible with some systems, but we start with staff confirming requests.

Compliance depends on vendors and data flows. We use providers that sign a BAA or processor contract, minimise what is collected and give you a written data-flow summary.

Measure conversations resolved without hand-off, requests captured, after-hours messages handled and what is missing from the answer library.

Free 20-minute call

Want this for your healthcare clinic?

Book a free 20-minute call. We will look at how the work runs today, tell you honestly whether it is worth building and give you a fixed quote if it is.

Book a free 20-minute call