All use cases

Upsell & Cross-sell

Free-to-paid nudge in the care chat

A free user asks the care chat a question that really needs a doctor — the agent helps first, then points to the paid consult without breaking trust.

Next best thingBehavioral triggerChatWhatsAppHealth & Telehealth

What it does

Telehealth providers run free care surfaces that quietly absorb questions worth paying for. Unpaid users get a helpful answer and leave; the paid doctor-consult product sits one step away, unmentioned, and the free surface stays a pure cost center. The agent recognizes when a free user's question crosses into territory the paid product genuinely serves, answers what it can, and adds a warm, non-pushy nudge toward the consult — monetizing the free surface without ever turning care into a sales pitch.

How it works

  1. 1
    Trigger. a free-tier user's message in the care chat or WhatsApp thread shows intent the paid product serves — a symptom question that needs a clinician's judgment, a request beyond the free scope.
  2. 2
    Decision. clinical red-flag detection runs first — anything urgent escalates instead of upsells. Then the agent checks the user's memory (what they have asked before, whether they have already declined the offer) and a judge gates the nudge for tone: warm and optional, never pressuring.
  3. 3
    Action. the agent answers fully within the free scope, then offers the paid consult as the genuinely better next step, in the same thread the user is already in.
  4. 4
    Follow-through. a decline is written to memory and sets a cool-down so the user is not nudged again on the next question; conversion is measured against a holdout group. Payment for the consult completes in the provider's own hosted payment step — the agent hands off, it never takes the payment itself.
Example
CustomerI've had this rash for a while and the cream from the pharmacy isn't helping. What else can I try?
AgentIf it's not improving with over-the-counter care, that's worth a doctor's look rather than another guess. I can share general skin-care guidance here — but our doctor consult would get you a personal review: you describe it once, add a photo, and a doctor replies with a treatment plan. Would that be helpful?
CustomerHow does it work?
AgentYou answer a few questions in this same chat, and a licensed doctor reviews and responds with a plan. If you'd like to go ahead, I'll hand you to the secure checkout and we'll pick this thread right back up.

Configuration

How the agent is wired for this use case.

Triggera free-tier user's message in the care chat or WhatsApp thread shows intent the paid product serves — a symptom question needing a clinician's judgment, or a request beyond the free scope.
Tools & actions
  • Messaging channel (care chat and WhatsApp) · reads the inbound message, answers within the free scope, and adds the consult nudge in the same thread
  • Billing platform · reads user tier and entitlement state to confirm the user is free and the consult applies
  • Knowledge base · sources the general guidance the agent shares within the free scope
  • Hosted payment step (provider-owned) · receives the handoff to take the consult payment; the agent never takes payment itself
Autonomyanswering and nudge composition run unattended, judge-gated for warm, optional tone on every nudge, but only after clinical red-flag detection clears; a care-first policy means the free answer is never withheld to force the upgrade, and the money-moving consult payment always routes to the provider's hosted step.
Channelschat · whatsapp
Escalationanything clinically urgent escalates instead of upselling; payment for the consult hands off to the provider's hosted checkout, and a decline sets a cool-down before the next nudge.

What you need

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

Signals

care-chat messages from free-tier users, intent classification against the paid product's scope, scope-boundary events from the free flow

Data

user tier and entitlement state, consent state, memory of prior questions and declined nudges, paid-product catalog

Guardrails

clinical red-flag detection runs before any commercial nudge; judge gating for tone on every nudge; decline cool-downs and frequency caps; care-first policy — the free answer is never withheld to force the upgrade

Metrics it moves

  • conversion-rateup on free-to-paid, because the offer arrives exactly when the user's question already justifies it
  • revenue-per-conversationup, as the free care surface starts producing consult purchases instead of only cost
  • csatheld or up, because the nudge is gated to moments where the paid product is genuinely the better answer

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