Trade · practices

A full book today.A quiet one in March.

Practices are chosen on reputation and kept on recall, and both are front-desk jobs that lose to whoever is standing at the counter. An agent team does not get interrupted.

Three days on site · three days of analysis · the report is yours either way
12

Open source projects

Public on github.com/JIGGAI

4

AI plugins

Published on npm, free to install

65.4K

AI plugin installs

65,377 to date, per npm

2.8K

AI monthly plugin installs

2,811 in August 2026, per npm

Sound familiar

What we hear in the first hour.

Not a generic list. These are the ones that come up in businesses shaped like yours.

01Reviews

One unhappy patient wrote a paragraph and it is the first thing anyone reads.

A considered reply moves the reader more than the review does. It has to arrive before the next person looks.

02Recall

Recall happens when reception has a quiet afternoon.

It never has a quiet afternoon. Recall is the most reliable revenue in the practice and the first thing to slip.

03Social

Our socials are three months out of date.

Nobody minds a quiet feed, but an abandoned one is read as an abandoned practice.

04Reviews

We ask for reviews at the desk and it is awkward for everyone.

It is. The part worth automating is answering and escalating, not badgering people at checkout.

05Escalation

The practice manager finds out about complaints last.

Escalation by text, within minutes, to whoever can actually ring the patient — that is the whole feature.

The rule

A patient forgives the problem. They do not forgive being ignored in public.

Which is why the reviews team escalates first and drafts second: the reply matters, but reaching the right person while it is fixable matters more.

What we expect to find

The software already in the building.

We do not arrive with a platform to sell you. We arrive expecting these, and the work is usually in the gaps between them.

01

Practice management

Dentrix, Open Dental, Cliniko, ezyVet. Where appointments, recalls and clinical records live.

02

Google Business Profile

Where most new patients form their first opinion, and where the reply is public.

03

Patient messaging

Whatever sends reminders today, and whatever record exists of consent to send them.

04

The front desk phone

Where the enquiries that matter most still arrive, and where nothing is logged automatically.

05

Social accounts

Usually run by whoever is most comfortable with a phone, in gaps between patients.

06

Review platforms beyond Google

Sector directories and health-specific sites, each with their own reply mechanics.

A worked example

Escalating a bad review before the next patient reads it.

Roughly what one entry in your report looks like — a real shape, with the numbers changed.

What we saw
Negative reviews discovered late, usually by a clinician rather than the practice manager, and replied to inconsistently or not at all. No record of who had seen what.
What it costs today
On a profile most new patients read before booking, an unanswered complaint sitting at the top costs you enquiries you never hear about — and nobody in the building could say how long it had been there.
What we would build
Monitoring across the profile and sector directories, an immediate text and email to the practice manager on anything negative, a drafted reply awaiting approval, and a weekly summary of everything that arrived.
How you would know it worked
Time from review posted to the manager knowing, time to reply published, and share of reviews answered. The first of those is the one that matters clinically.
And what we would not automate

Anything about the patient’s care, and any reply that acknowledges a clinical detail. Confidentiality makes a generated public reply a genuine risk, so the draft stays deliberately non-specific and a person decides what can be said.

The arithmetic

What coordination work costs you.

Three numbers you already half-know. Move them until they look like your business.

12

re-keying, chasing status, producing the same document again

6h

on that work specifically, not their whole job

$65

salary, tax, benefits, desk

Coordination work, per year
3,312hours
Plausibly retired by agentic automation
2,484hours

A 75% capture rate. The other twenty-five per cent is judgement, exceptions, and not wanting to look greedy.

1.4
FTE equivalent
$161,460
Per year

This is arithmetic, not a finding. It rests on three numbers you guessed. The assessment replaces all three with numbers we observed — and tells you which of those hours are actually worth automating.

See what a real finding looks like →
What happens

What the six days look like.

The most common question we get is not about AI. It is what these people will actually do in my building.

Assessment · 3 days on site · 3 days analysisNo prep required
  1. Day 1Walk the floorWhoever is on shift

    We start where the work happens, not in a meeting room. Nobody prepares anything, and the first day is mostly watching.

  2. Day 2Sit with the people doing itOps, admin, finance

    Conversations with the roles that touch the work most, and a real task followed end to end — including the parts that happen in a group chat.

  3. Day 3Systems, then a read-backWhoever holds the logins

    What you run, what talks to what, and where a person is currently the integration. We tell you what we saw before we leave, while it is still cheap to correct.

  4. Days 4–6Research and discoveryOur desks, not yours

    Away from your building. We cost the work we watched, model the alternatives, and test the shortlist against your own numbers rather than a framework.

  5. +1 weekOne recommendationPresented in person

    The single change worth making first, specified precisely enough to build — with the ranked analysis behind it and the list of what we would not automate.

Before you ask

The questions this raises.

Can it reply to a review that mentions treatment?

It drafts something deliberately non-specific and flags it for a person, because acknowledging clinical detail in public is a confidentiality problem before it is a marketing one. The draft never gets posted automatically.

Does this touch patient records?

No. It reads reviews and, if you take the messaging team, the consent and contact fields needed to send a reminder. It does not need clinical data and we do not ask for it.

Our recall runs out of the practice system already.

Then the messaging team may be redundant and we will tell you. It is usually the reviews team that earns its keep in a practice — the recall feature you already pay for often just needs switching on.

Who gets the alert?

Whoever you nominate, by text and email, and you can have more than one. In most practices it is the manager rather than the principal, because the point is reaching someone who can ring the patient today.

Start with half an hour.

We'll tell you whether an assessment would pay for itself in an operation like yours. Sometimes the answer is no.