Finds why appointments are missed, and the capacity nobody recorded as lost
Every clinic loses a significant share of its capacity to appointments nobody attends, and the standard responses — charging, overbooking, more reminders — all treat it as patient behaviour, and all make access worse for the people least able to attend.
The patterns say something different. Non-attendance concentrates: in appointments booked far ahead, in the first slot of the day, in slots that are hard to reach, in cohorts whose letters arrive after the appointment. Those are scheduling and communication facts, and every one is inside the clinic's control.
The second thing in the same data is capacity that was never lost to a patient at all: slots cancelled with enough notice to refill and never refilled, clinics finishing early while a waiting list exists, rooms booked for sessions that did not happen. Nobody records that as lost, because nobody failed to arrive.
This agent reports both, with the scheduling change that would recover each and what it is worth in appointments. It works on operational patterns only. It makes no clinical judgement, never profiles or scores an individual patient, and never recommends anything that would deprioritise a person.
Most of it is already there and unused.
The fixes are scheduling, not penalties.
Because refillable slots actually get refilled.
Non-attendance rises steeply with how far ahead an appointment was booked. It is the strongest lever and it is entirely yours.
First slot of the day, or one that needs two buses. A scheduling fact, not a patient failing.
Cancellations with notice that were never refilled, and clinics finishing early against a waiting list.
A cohort whose communication lands after the date. Invisible, and completely fixable.
What the fix recovers, so it competes against the alternatives properly.
It produces no individual risk score and recommends nothing that would deprioritise anyone. Patterns only.
Why Healthcare in particular. Non-attendance concentrates in things the clinic controls — booking lead time, the first slot of the day, letters arriving late. And capacity lost to unfilled cancellations is never recorded as lost, because no patient failed to arrive.
Runs unattended
Started by you or by an event, and it finishes on its own. Nothing waits for someone to be at a desk.
The same standard every time
The two-hundredth item is held to the bar the first one was. Consistency is the part people cannot sustain.
It cannot act on its own
Clinic Access Analyst has no path to sending, spending or committing. That limit is why its output is safe to act on.
This agent runs server-side through the PROMIVO runtime. Each run is logged step by step and every tool call is permission-checked before it executes.
Read-only by design. This agent has no path to sending, spending, publishing or committing anything. Where that limit is the product, removing it would remove the reason to trust the output.
Demo dataIllustrative sample output, abridged.
{
"period": "H1 2026",
"appointments": [],
"suppressionThreshold": 10
}{
"escalate": true,
"disclaimer": "An operational analysis of appointment records. No clinical judgement has been made, no individual patient has been scored, profiled or identified, nothing recommends deprioritising or charging any patient, no appointment has been changed, and cohorts below ten are suppressed.",
"slotPatterns": [
"The 08:00 slot is missed at 2.4x the clinic average. The first bus arriving at that site is 07:52."
],
"cohortPatterns": [
"One cohort's non-attendance is 2.1x the average. The communication timing finding below appears to account for most of it, which makes it a fixable operational cause rather than a patient one."
],
"leadTimePattern": [
{
"leadTime": "0–7 days",
"appointments": 2100,
"nonAttendanceRate": 4.1
},
{
"leadTime": "8–28 days",
"appointments": 4800,
"nonAttendanceRate": 9.8
},
{
"leadTime": "29–84 days",
"appointments": 3900,
"nonAttendanceRate": 19.4
},
{
"leadTime": "85+ days",
"appointments": 1400,
"nonAttendanceRate": 31.2
}
],
"escalationReason": "Non-attendance differs materially between cohorts and appears linked to communication arriving late, which is an equity of access finding; and 610 refillable cancellations went unfilled against a waiting list of 1,900.",
"cohortsSuppressed": 4,
"fixesWithATradeOff": [
"Overbooking the 08:00 slot would recover roughly 120 appointments and would transfer waiting time to patients who did attend. Listed last for that reason."
],
"communicationTiming": [
"For 340 appointments, the letter was sent fewer than 3 days before the date. Those show a 27% non-attendance rate against 9.8% for the same lead time band overall."
],
"suppressionThresholdUsed": 10,
"fixesWithNoCostToPatients": [
{
"change": "Cap routine booking lead time at 28 days with a partial booking model",
"appointmentsRecovered": 740
},
{
"change": "Refill cancellations with more than 48 hours notice from the waiting list",
"appointmentsRecovered": 610
},
{
"change": "Send communication at least 7 days ahead for every appointment",
"appointmentsRecovered": 90
}
],
"capacityLostWithoutAPatient": [
{
"note": "A waiting list of 1,900 existed throughout. Nobody failed to attend these — they were simply never offered to anyone.",
"cause": "Cancellations with more than 48 hours notice, never refilled",
"appointmentsLost": 610
},
{
"note": "",
"cause": "Sessions finishing early against booked capacity",
"appointmentsLost": 180
}
]
}No integrations required.
Where capacity actually goes.
Which pattern is driving it.
Whether existing capacity is being used first.
Whether attendance differs by cohort, and what scheduling explains it.
$349/month
Billed monthly through your PROMIVO subscription. Cancel at any time.
Runs consume your plan allowance for agent executions and tokens. See plan limits.
No, and it refuses to. Individual non-attendance prediction leads to deprioritising the people who most need care. It reports operational patterns only.
Never. It makes no clinical judgement of any kind, does not assess urgency, and never suggests changing anyone's clinical priority.
Only where the data supports refill rather than double-booking, and it says plainly that overbooking transfers the cost to patients who did attend. It leads with the changes that create no such cost.
It analyses appointment records and reports aggregate patterns. It reproduces no patient identifier and suppresses cohorts below the size you set.
No reviews yet. Reviews open once customers have run this agent.
Tell us what to change and our team will scope a customised version for your business.
Customize this agent