Case Study

Case Study: Healthcare Clinic Referral & Intake Automation

We built a connected set of automations for a multi-specialty outpatient clinic: a healthcare CRM for new-patient enquiries and referrers, referral logging and intake, patient reminders with no-show follow-up, prior authorization tracking and an AI receptionist on the website. Coordinators now work from one set of queues, and clinicians see referrals and histories in time to prepare.

Clinic type
Multi-specialty outpatient clinic
Team involved
Practice manager, patient coordinators, billing staff, triaging clinicians, medical director
Systems connected
EHR (FHIR and vendor API), cloud fax, CRM, clearinghouse, Twilio, n8n
Delivery
Scrum, 1-week sprints, about 9 weeks to full launch

The challenge

Where the practice started

Referrals arrived by fax, email and e-referral into three inboxes. Some waited days for triage, and referring practices rarely heard back.

New-patient enquiries from the website and directories were tracked when someone had time, and nobody could say which referrers or channels brought patients who attended.

Reminders went out once from the EHR. Cancellations the night before left empty slots, and no-shows were noticed only at month end.

Prior authorizations were tracked on sticky notes and a shared spreadsheet, so missing auths sometimes surfaced after the visit. After hours, calls went to voicemail.

Goals

What the project had to change

  • Every referral is logged the day it arrives, triaged by a clinician and acknowledged to the referrer.
  • Every new-patient enquiry has an owner and a next step in one pipeline.
  • Freed slots are offered to the waitlist and every no-show reaches a coordinator.
  • No visit happens without the clinic knowing its authorization status.
  • Routine questions get answers after hours, with clinical questions handed to people.

What we built

What we built, as one connected system.

01

Referral log and intake

We connected the fax inbox, shared email and e-referral feed to one referral log with a clinician triage queue, intake forms by appointment type, a pre-visit gap list and draft referrer acknowledgements.

Service details
02

Healthcare CRM pipeline

Website forms, chat, directory enquiries and referrals flow into one pipeline with coordinator tasks and a weekly report by channel, referrer and service line.

Service details
03

Reminders and no-show follow-up

Reminders within the healthcare texting limits, confirm and reschedule replies, waitlist offers for freed slots and a daily no-show list with flags for clinically important visits.

Service details
04

Prior authorization tracker

Payer and service rules flag visits needing an auth, a tracker holds every pending request with its due date, and billing staff get reminders and a denial log.

Service details
05

AI receptionist

A website assistant answers from the clinic's approved wording, takes booking and records requests, discloses it is automated and sends anything clinical to coordinators.

Service details

Architecture

How the clinic's workflows connect

Referrals in Fax, email, portal Web enquiries Forms, chat EHR Schedule, records n8n Five workflows AI steps Fields, answers CRM pipeline Owners, tasks Texts and emails Twilio, email Coordinators Queues, billing Clinicians Triage, review Logs and reports Weekly summary
  • Input
  • Logic and services
  • AI step
  • Data
  • Output
  • People

How it flows

  1. 1 Referrals, web enquiries and the EHR schedule feed one n8n instance.
  2. 2 Five workflows update the CRM, send reminders and forms, track authorizations and run the website assistant.
  3. 3 Coordinators and billing staff work one set of queues; clinicians triage referrals and review histories.
  4. 4 Every step is logged and a weekly summary shows the measures the clinic agreed to track.

How it behaves

How the system behaves day to day

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

What patients see

  • A booking confirmation soon after their referral is triaged
  • Forms to complete before the first visit
  • Reminders with an easy way to reschedule
  • Answers to routine questions any time, and a person for anything clinical

What staff see

  • One referral log, one pipeline, one no-show list and one auth tracker
  • Urgent items flagged first
  • Weekly reports by channel and referrer

What the automation does

  • Logs, matches, sends, reminds and chases on schedule
  • Applies texting limits, opt-outs and consent across every workflow
  • Alerts the practice manager if anything fails

Edge cases and fallbacks

A referral is marked urgent
It jumps the queue to the triaging clinician; nothing clinical is decided automatically.
A patient opts out in one workflow
One shared opt-out list stops texts from every workflow.
A payer rule is unclear
The visit is marked needs review instead of being guessed.
The EHR API is unreachable
Runs are held and retried, never sent from stale data.
Twilio or n8n has an outage
Calls reach voicemail, referrals still arrive by fax, and the practice manager gets an alert.

Integrations

What we connected

All integrations

Epic

EHR

Appointments, patients and documents for reminders, intake and pipeline matching.

Epic on FHIR APIs (open.epic); app access set up with the health system, confirmed per project.

athenahealth (athenaOne)

EHR and practice management

Scheduling, patients and documents for reminders, intake and auth tracking.

athenahealth Developer Portal: certified FHIR APIs, plus athenaOne APIs through its Marketplace route.

HubSpot

CRM

Contacts, deals, pipeline stages and coordinator tasks.

HubSpot CRM REST API.

Twilio

SMS and voice

Reminders, text lines and the AI receptionist's phone line.

Twilio Messaging and Voice APIs, under Twilio's BAA for PHI.

Google Business Profile

Local search

Booking links and listing details.

Google Business Profile settings and APIs.

n8n

Automation platform

Runs the workflows, self-hosted or on n8n Cloud.

Your own n8n instance; we hand over every workflow.

How we delivered it

Week by week, one workflow at a time.

Each workflow went live on its own after a shadow run and a sprint demo, so the team got used to one change before the next.

Delivery timeline

Typical time to launch: about 9 weeks, then support

  1. 01

    Discovery

    Week 1

    We shadowed coordinators and billing staff, mapped referral, enquiry, reminder and auth steps, agreed urgent wording and data flows, and the clinic signed vendor agreements.

  2. 02

    Design and access

    Week 2

    Templates approved by the medical director, referral statuses, payer rules, consent and opt-out rules, EHR API access, Twilio number and A2P 10DLC registration.

  3. 03

    Sprint 1: referrals

    Week 3

    Built and shadow-ran the referral log and triage queue; demo and sign-off.

  4. 04

    Sprint 2: CRM pipeline

    Week 4

    Referrals went live. Connected enquiry sources to the CRM and set up coordinator tasks.

  5. 05

    Sprint 3: reminders

    Week 5

    The pipeline went live. Built reminders, reply handling, waitlist offers and the no-show list.

  6. 06

    Sprint 4: prior auth

    Week 6

    Reminders went live for one service line. Built payer rules, the auth tracker and the denial log.

  7. 07

    Sprint 5: AI receptionist

    Week 7

    The tracker went live. Built the answer library and the website assistant.

  8. 08

    Assistant testing

    Week 8

    Ran real, tricky and clinical prompts against the assistant; the medical director signed off.

  9. 09

    UAT and handover

    Week 9

    Staff ran acceptance tests on every workflow, then we switched everything on, handed over the run book and trained the team.

  10. 10

    Support

    Ongoing

    Weekly check-ins during stabilisation, then monthly care.

Who does what

What the team does, and what automation does.

Automation does

  • Logs and matches referrals from every inbox
  • Captures enquiries into the CRM and creates tasks
  • Sends reminders, forms and waitlist offers
  • Flags visits that need an authorization and tracks due dates
  • Answers routine questions from approved wording

The team does

  • Match unclear referrals and fix intake gaps
  • Call new patients and no-shows
  • Verify eligibility, submit auths and work denials
  • Confirm booking and records requests from the assistant

Clinician or medical director decides

  • Triages every referral and sets priority
  • Reviews intake histories and decides what they mean
  • Writes medical necessity documentation
  • Answers anything clinical, including urgent messages

Compliance handled

Privacy, consent and safety, built in.

No clinical advice by text or chat

Nothing clinical is answered automatically; urgent language triggers the clinic's emergency instructions and a staff alert.

Texting rules in the US

Reminders stay within the FCC healthcare exemption limits and carry no billing content.

Source: www.law.cornell.edu

Vendor agreements first

Every vendor that touches patient data signed a BAA or processor contract before go-live; Twilio's BAA requires its Security or Enterprise Edition.

Source: www.twilio.com

Prior auth timeframes

The tracker uses the CMS decision timeframes for impacted payers to flag overdue requests.

Source: www.cms.gov

AI disclosure

The assistant says it is automated at the start of every conversation.

Source: artificialintelligenceact.eu

Outcomes

What changed for the practice

  • Referrals are logged the day they arrive and referrers hear back once the patient is booked.
  • Every new-patient enquiry has an owner and a next step.
  • Freed slots are offered to the waitlist automatically and no-shows reach a person the same day.
  • Authorization status is known before visits, not after.
  • Routine questions get answered after hours, and clinical questions reach people.

What we track

The measures the practice watches.

Referral to triage

Days from referral received to clinician triage and to first visit.

Pipeline conversion

Enquiries by source and referrer, first visits booked and attended.

Slots refilled

Cancellations with notice and slots filled from the waitlist.

Auth coverage

Visits seen with a required authorization confirmed beforehand.

Assistant hand-offs

Conversations resolved without hand-off and questions missing from the library.

Cost estimate

What a project like this costs

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

    Process mapping, data flows, wording and the backlog for all five modules.

    $1,000 – $2,000

  • Referral and intake module

    Referral log, triage queue, forms and gap list.

    $800 – $2,000

  • CRM pipeline module

    Source capture, stages, tasks and the weekly report.

    $700 – $1,600

  • Reminders module

    Reminders, replies, waitlist offers and no-show list.

    $700 – $1,700

  • Prior auth module

    Payer rules, tracker, reminders and denial log.

    $700 – $1,700

  • AI receptionist

    Answer library, assistant, hand-off and testing.

    $1,500 – $3,200

  • Integrations

    EHR, CRM, fax, Twilio and clearinghouse connections.

    $300 – $800

  • Testing, UAT and launch

    QA, acceptance testing, launch and training.

    $300 – $1,000

  • Total project estimate

    $6,000 – $14,000

Optional monthly care after launch is quoted with your proposal. Typical range for this scope: four workflows plus an AI receptionist at our fixed ranges. Every clinic gets its own fixed quote after a free call.

Monthly running costs you pay directly

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

  • Twilio SMS (US): About $0.0083 per message segment each way plus carrier fees (Twilio's published US pricing). A BAA needs Twilio's Security or Enterprise Edition if patient information is in the messages.
  • n8n: Free self-hosted Community edition on your own server, or n8n Cloud from about €20 a month (Starter) or €50 (Pro), billed annually.
  • CRM: The CRM vendor's own plan.
  • AI usage and form tool: Pay-per-use model fees and the form provider's plan, usually small at clinic volumes.

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

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.

Free 20-minute call

Want this built 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