Case Study

Case Study: Veterinary Clinic Client Automation

We built a connected set of automations for a companion-animal veterinary clinic: a new-client pipeline, preventive care reminders with post-op check-ins, an AI receptionist on the phone and website, new-client registration with records requests, and one queue for prescription refills. The front desk now works from a few clear lists instead of sticky notes and voicemail, and vets see each refill with the history already attached.

Clinic type
Companion-animal general practice
Team involved
Practice manager, front desk, nurses and technicians, veterinarians
Systems connected
PIMS, phone system, CRM, Google Business Profile, Twilio, n8n
Delivery
Scrum, 1-week sprints, about 9 weeks to full launch

The challenge

Where the practice started

The phones rang all day with routine questions, and owners with sick pets sometimes waited in the same queue as people asking about opening hours.

New-client enquiries from the website, Facebook and missed calls were not tracked anywhere, and nobody knew which ones booked.

Reminders went out once from the PIMS, with no follow-up, and the team worried about reminders reaching owners of pets who had died. Post-op calls depended on how busy the day was.

New clients filled in paper forms on arrival while staff phoned previous clinics for records, and refill requests arrived on notes, voicemail and email with no single place to see them.

Goals

What the project had to change

  • Routine questions are answered at any hour, and possible emergencies reach a person at once.
  • Every new-client enquiry lands in one pipeline with a clear next step.
  • Reminders check each pet's status before sending and follow up before handing over to a person.
  • New-client forms and previous records are in the PIMS before the first consult.
  • Every refill request reaches the right vet with history attached.

What we built

What we built, as one connected system.

01

AI receptionist

An assistant on the website and after-hours phone line that answers from the clinic's approved library, screens every message for possible emergencies first and collects booking and refill requests.

Service details
02

New-client pipeline

Web forms, chat, Facebook messages and missed calls feed one CRM pipeline with fast replies, desk tasks and a monthly source report, matched back to new PIMS clients.

Service details
03

Preventive reminders and post-op check-ins

Nightly reminder lists with status checks at send time, household grouping, two follow-ups, a lapsed-patient call list and next-day post-op messages that escalate to nurses.

Service details
04

New-client registration

Forms and records consent sent at booking, records requests to previous clinics with chasing, and everything attached to the PIMS with a short summary for the vet.

Service details
05

Refill queue

Requests from every channel matched to the patient, with last exam and current prescription attached, routed to the right vet, and owners updated after the decision.

Service details

Architecture

How the clinic's workflows connect

Phone and chat Owners Web and social Enquiries PIMS Patients, reminders n8n Five workflows AI steps Screen, summarise CRM pipeline New clients Texts and emails Twilio, email Desk and nurses Lists, queues Veterinarians Refills, clinical Log and reports Monthly summary
  • Input
  • Logic and services
  • AI step
  • Data
  • Output
  • People

How it flows

  1. 1 Calls and chats, web and social enquiries, and patient and reminder data from the PIMS feed one n8n instance.
  2. 2 Five workflows update the CRM, send messages, and use AI steps to screen conversations and summarise received records.
  3. 3 The desk and nurses work short lists and queues; veterinarians decide refills and anything clinical.
  4. 4 Every step is logged, and a monthly 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 owners see

  • Quick answers at any hour and emergency instructions at once when needed
  • A fast reply when they enquire as a new client
  • Reminders that never mention a pet they have lost
  • Forms to complete at home before the first visit
  • A message when their refill is ready or an exam is needed

What staff see

  • Emergency hand-offs first
  • One pipeline, one call list, one day-before list and one refill queue
  • Post-op replies that need a nurse, flagged at once

What the automation does

  • Screens, reminds, chases and routes on schedule
  • Applies consent, opt-outs and status checks across every workflow
  • Logs every step and alerts the practice manager if anything fails

Edge cases and fallbacks

An owner describes symptoms in a chat
No advice is given; emergency instructions are shown and staff are alerted.
A pet is marked deceased
Excluded from every workflow immediately.
An owner opts out in one workflow
One shared opt-out list stops messages from every workflow.
The PIMS is unreachable overnight
Runs are skipped and retried rather than built from stale data.
Twilio or n8n has an outage
Calls reach the normal phone queue, forms can still be completed at the desk, and the practice manager gets an alert.

Integrations

What we connected

All integrations

ezyVet

Practice management (PIMS)

Clients, patients, appointments and bookings for reminders, registration, refills and CRM matching.

ezyVet REST API with OAuth, with access enabled through IDEXX, confirmed per project.

PetDesk

Client communication

We design reminders and messaging around PetDesk when it is your platform, rather than duplicating it.

PetDesk syncs with a published list of PIMS; our connection method is confirmed per project.

HubSpot

CRM

New-client pipeline, tasks and reporting for clinics and groups.

HubSpot CRM REST API.

Twilio

SMS and voice

Reminders, replies, post-op check-ins and the AI phone line.

Twilio Programmable Messaging and Voice APIs.

Google Business Profile

Local search

Booking link, messages and new-review alerts.

Google Business Profile settings and APIs.

Slack and Microsoft Teams

Staff alerts

Emergency hand-offs, refill queue and failure alerts.

Incoming webhooks and APIs.

n8n

Automation platform

Runs every workflow, 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 the front desk and nurses, mapped calls, enquiries, reminders, registration and refills, agreed emergency wording and data flows, and confirmed PIMS API access with the vendor.

  2. 02

    Design and access

    Week 2

    Approved message templates, pipeline stages, reminder status rules, refill policy flags, Twilio number and A2P 10DLC registration.

  3. 03

    Sprint 1: reminders

    Week 3

    Built status-checked reminders and post-op check-ins; staff checked every daily list before anything was sent.

  4. 04

    Sprint 2: refills

    Week 4

    Reminders went live for one type. Built the refill queue with PIMS history and vet routing.

  5. 05

    Sprint 3: new-client pipeline

    Week 5

    Refills went live. Connected enquiry sources to the CRM with replies and desk tasks.

  6. 06

    Sprint 4: registration

    Week 6

    The pipeline went live. Built forms, records requests, PIMS attachment and the day-before list.

  7. 07

    Sprint 5: AI receptionist

    Week 7

    Registration went live for new clients. Built the answer library, emergency screen and request capture.

  8. 08

    Receptionist testing

    Week 8

    Ran real, emergency and toxin prompts; a veterinarian signed off the screen and hand-offs.

  9. 09

    UAT and handover

    Week 9

    The team ran acceptance tests, the assistant went live on web chat and after hours, and we handed over run books.

  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

  • Answers routine questions and screens for possible emergencies
  • Captures new-client enquiries and replies with booking information
  • Builds status-checked reminder lists every night
  • Sends forms and records requests and chases what is missing
  • Collects refill requests and attaches PIMS history

The team does

  • Handle emergency hand-offs and call back owners
  • Call lapsed patients and follow up new-client enquiries
  • Check forms, records and vaccination proof
  • Prepare refill requests for the vet
  • Respond to post-op replies that need a nurse

Veterinarian decides

  • Decides every refill and prescription
  • Sets vaccine protocols and reminder intervals
  • Reviews received records and post-op concerns
  • Approves emergency wording and health content

Compliance handled

Privacy, consent and safety, built in.

No medical advice by chat or phone

Possible emergencies trigger the clinic's emergency instructions and a staff alert; nothing clinical is answered automatically.

Prescribing stays with the vet

Refills are prepared, never approved, by automation, in line with the VCPR definition and RCVS under-care guidance.

Source: www.law.cornell.edu

Texting consent

Reminder texts follow the general TCPA consent rules rather than the healthcare exemption.

Source: www.law.cornell.edu

Records with consent

Records requests are sent only with the owner's consent, in line with state veterinary confidentiality laws.

Source: www.hipaajournal.com

AI disclosure

The assistant says it is automated, matching Article 50 of the EU AI Act.

Source: artificialintelligenceact.eu

Outcomes

What changed for the practice

  • Routine questions are answered at any hour, and possible emergencies reach staff at once.
  • Every new-client enquiry lands in one pipeline with a next step and an owner.
  • Reminders check each pet's status before sending, and lapsed patients reach a person.
  • Post-op check-ins happen every time, with worrying replies going straight to nurses.
  • Most new clients arrive with forms done and previous records already in the PIMS.
  • Vets see every refill request in one queue with the history attached.

What we track

The measures the practice watches.

Emergency hand-off time

Time from a flagged message to a staff response.

New-client conversion

Enquiries by source, first visits booked and clients registered.

Reminder compliance

Reminders due, sent and booked by reminder type.

Registration readiness

Share of first visits with forms and records in the PIMS beforehand.

Refill turnaround

Time from request to vet decision and owner chase calls.

Assistant quality

Conversations resolved without hand-off and questions added to 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 services.

    $1,000 – $2,000

  • AI receptionist module

    Answer library, emergency screen, channels and request capture.

    $2,500 – $5,000

  • CRM pipeline module

    Source capture, replies, tasks and reporting.

    $700 – $1,500

  • Reminders module

    Status-checked reminders, follow-ups, call list and post-op check-ins.

    $700 – $1,500

  • Registration module

    Forms, records requests, PIMS attachment and the day-before list.

    $700 – $1,500

  • Refill module

    Queue, PIMS history, flags, routing and owner updates.

    $600 – $1,300

  • Integrations

    PIMS, reminder platform, CRM, Google and Twilio connections.

    $300 – $700

  • Testing, UAT and launch

    QA, acceptance testing, launch and training.

    $500 – $1,500

  • Total project estimate

    $7,000 – $15,000

Optional monthly care after launch is quoted with your proposal. Typical range for a project of this scope: four workflows plus an AI receptionist. 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 (US): About $0.0083 per SMS segment each way plus carrier fees, and about $1.15 a month per local number (Twilio's published US pricing), plus A2P 10DLC registration fees and voice usage.
  • n8n: Free self-hosted Community edition, or n8n Cloud from about €20 a month (Starter) or €50 (Pro), billed annually.
  • PIMS, CRM and reminder platform: Each vendor's own plan.
  • AI usage: Pay-per-use model fees, usually small at single-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 veterinary & pet care?

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