All use cases

Retain / Save

Four-month drop-off re-engagement

Around month four a patient who was logging every day goes quiet — not angry, just deflated that the early momentum has faded — and that single window is where most of the program's churn happens.

Get aheadBehavioral triggerTime-based triggerPushIn-appChatEmailWhatsAppGLP-1 & PeptidesHealth & TelehealthSubscription

What it does

GLP-1 patients do not drift evenly. There is one named window, around the third-to-fourth month, where the first rush of results levels off, the novelty wears thin, and the patient quietly starts to disengage long before they would ever message to cancel. Programs commonly see patients stay only a few months when the clinically meaningful course runs much longer, and almost nobody raises their hand on the way out — they simply stop opening the app. The agent watches for the quiet signal inside this specific window, reaches out before the gap hardens into a lapse, names the deflation the patient is feeling, addresses the worries that cluster here, and re-opens the conversation with the next-best content or action — defending the single window where retention is won or lost.

How it works

  1. 1
    Trigger. the patient enters the month-three-to-four window and their engagement decays below their own baseline — fewer logs, fewer opens, a check-in gone quiet — rather than a fixed calendar date alone.
  2. 2
    Decision. the agent reads the patient's memory — start date, early wins, what they have told the coach, channel consent — and picks the move for this window: name the motivation dip, normalize the first subjective plateau, or surface a concrete next action. A judge reviews every unprompted message before it sends.
  3. 3
    Action. a short, personal touch lands on a channel the program keeps owning (push, in-app, chat, email, or WhatsApp), written to pull the patient back into the existing coach conversation rather than read like a campaign.
  4. 4
    Follow-through. replies continue inside the coach chat; clinical concerns escalate to the care team; if the patient re-engages on their own or cancels, queued touches are cancelled automatically; and retained months are measured against a holdout so the lift is proven, not assumed.
Example
AgentYou've hit the stretch right around month four — and your logging's tailed off these last couple of weeks, which is exactly the pattern we watch for here. This is where the fast early progress levels off and it can feel like the program's stopped working: a really common point, and not where it ends. Want to look at what's still moving, even if the scale's been stubborn?
PatientYeah, honestly the first two months felt great and now nothing. I've kind of stopped bothering.
AgentThat dip is exactly the moment most people quietly step back — and the ones who stay through it are the ones who reach their goal. Let's pick one small thing to focus on this week, and I'll check in with you on Friday.

Configuration

How the agent is wired for this use case.

Triggerthe patient enters the month-three-to-four drop-off window and engagement decays below their own baseline (fewer logs, fewer opens, a quiet check-in), sourced from the program app and engagement signals.
Tools & actions
  • Scheduling system · open the window touchpoint when the patient enters month three-to-four and queue the timed re-engagement touch
  • Patient record / CRM · read program start date, early wins, conversation history, and channel consent
  • Memory store · read coach-conversation history; write the re-engagement outcome back for the next touch
  • Messaging channel · send the judged window touch on a program-owned channel and pull the patient back into the coach chat
  • Clinical escalation path · route any clinical concern in the reply to the care team
Autonomywindow detection and the re-engagement touch run unattended, judge-gated on every unprompted message, using approved coaching content only under a never-new-medical-advice clinical policy; clinical concerns always route to a human, and sends are suppressed on cancellation or self-re-engagement.
Channelspush · in-app · chat · email · whatsapp
Escalationclinical concerns hand off to the care team; if the patient re-engages on their own or cancels, queued touches are cancelled automatically.

What you need

The inputs this use case runs on. Your channels stay yours; the agent supplies the judgment.

Signals

program-month position, engagement-decay detection against the patient's own baseline, gone-quiet detection, renewal date.

Data

program start date and course length, early-win and conversation history, coach-chat memory, channel consent state.

Guardrails

judge review on every unprompted message; clinical concerns always escalate to a human; approved coaching content only, never new medical advice; companion tone, never pressure; frequency caps; suppression on cancellation or self-re-engagement; holdout measurement of retained months.

Metrics it moves

  • churndown, by defending the single steepest drop-off window before the quiet turns into a lapse.
  • adherenceup, by re-opening the relationship in the exact weeks doses and logging tend to slip.
  • ltvup, as each patient carried past the four-month window compounds on already-paid high-CAC acquisition.

Related use cases

Retain / Save

Month-4 cliff companion coach (GLP-1)

the always-on companion relationship across the same cliff

Retain / Save

Drop-off-window cadence coach (GLP-1)

the full map of drop-off windows this one window sits inside

Retain / Save

Weight-stall plateau intervention coach

the save fired by an actual weight-stall signal rather than the calendar window

See it on your own customer journey

Bring one drop-off, one churn cliff, or one silent segment. We will show you what a proactive agent with memory and judgment does with it.

Book a demo