5 ManyMoney AI prompts for every lifecycle stage

You got an AI tool. Your metrics didn’t move. Here’s why.

Most marketing teams now use AI to generate copy. More variants, faster. And yet — D7 retention looks the same. First purchase rate hasn’t budged. Re-engagement campaigns still underperform.

The copy wasn’t the problem.

The real advantage of AI in messaging isn’t producing more variants. It’s making better decisions faster: who gets this message, when, based on what signal, with what offer. That’s where the ROI actually is — and that’s what AI-driven lifecycle messaging does.

Five stages. Five prompts.

Each stage of the user lifecycle has a different problem — and requires a different decision, not just a different text. Here’s the full arc we’ll work with: from install to high-value customer.

Lifecycle stage	Problem we're solving	Key metric to target
Onboarding → Activation	User installed the app but never reached their first key action	D1 Retention, Activation Rate
Engagement → Habit formation	Completed onboarding but sessions are low — the habit isn't forming	D7 Retention, Session Frequency
Conversion → First purchase	Engaged but not paying. The first transaction is the most expensive moment in the funnel	CVR free→paid, First Purchase Rate
Retention → Churn prevention	Churn signals are there, but the team sees them too late	Churn Rate, Re-engagement CVR
Upsell & loyalty → Expand your best users	They're paying, but not enough. How to grow the high-value user cohort	ARPU, CLV

Lifecycle stage

1 / 5

Onboarding → Activation

Problem we're solving

User installed the app but never reached their first key action

Key metric to target

D1 Retention, Activation Rate

Lifecycle stage

2 / 5

Engagement → Habit formation

Problem we're solving

Completed onboarding but sessions are low — the habit isn't forming

Key metric to target

D7 Retention, Session Frequency

Lifecycle stage

3 / 5

Conversion → First purchase

Problem we're solving

Engaged but not paying. The first transaction is the most expensive moment in the funnel

Key metric to target

CVR free→paid, First Purchase Rate

Lifecycle stage

4 / 5

Retention → Churn prevention

Problem we're solving

Churn signals are there, but the team sees them too late

Key metric to target

Churn Rate, Re-engagement CVR

Lifecycle stage

5 / 5

Upsell & loyalty → Expand your best users

Problem we're solving

They're paying, but not enough. How to grow the high-value user cohort

Key metric to target

ARPU, CLV

Below: each stage, a ready-to-use prompt, and how ManyMoney — Pushwoosh’s AI marketing co-pilot — turns it into a live campaign.

See ManyMoney in action

Type your first prompt

Stage 1 💡 Onboarding → Activation

⚠️

Why are new users dropping off — and where exactly?

Goal: Increase activation rate and D1 retention by identifying the exact drop-off point between install and first key action — and launching targeted experiments to close it.

Analyze new users acquired in the last 30 days in my [my app name/category].
Identify where they drop off between install and first key action
[e.g., first deposit / first level completed / first article read].
Launch 3 targeted campaigns to bring them back to that moment —
with channel and timing recommendations per segment.

What ManyMoney does: Maps the onboarding funnel step by step, identifies the exact drop-off point, segments users by how far they got, and launches adaptive in-app and push campaigns timed to each user’s last active moment — not a generic 24h delay.

ManyMoney analyzed onboarding funnel and prepared 3 campaigns to launch

Result: Higher D1 retention and activation rate without rebuilding the onboarding flow.

How to adapt this prompt across industries:

For a fintech app — replace “key action” with “first transaction” or “first account top-up.”
For gaming — use “first completed level”.
For a subscription app — “first feature used” or “first subscription page visit.”
For an e-commerce app — “first product viewed” or “first item added to cart.”

Stage 2 🔄 Engagement → Habit formation

⚠️

Completed onboarding. Hasn’t come back.

Goal: Improve D7 Retention and session frequency — the two metrics that predict long-term CLV better than anything else.

Identify users of [my app name/category] who completed onboarding
but have low session frequency in their first 7 days (fewer than [X] sessions).
Analyze their Day 0 behavior and segment by feature usage.
Recommend personalized push and in-app campaigns per segment
to increase week-1 retention and habit formation.

What ManyMoney does: Finds the correlation between Day 0 behavior and D7 return probability — which features, which actions, which sequences predict retention. Splits the low-frequency segment into behavioral groups and builds a separate messaging sequence for each: different channel, different timing, different angle. The user who opened feature A gets a reminder about exactly that. The one who never reached it gets shown what they missed.

ManyMoney analysis tab: segment breakdown by Day 0 behavior with personalized campaign recommendations per group

Result: Improved D7 retention and session frequency — built on what actually works for your retained users, not best-practice guesses.

How to adapt this prompt across industries:

Gaming — low session frequency in Week 1 predicts permanent churn faster than in any other vertical. Focus the prompt on users who completed the tutorial but haven’t returned to their second session.
Fintech — habit formation here means logging in to check balance or track spending. Users who don’t develop this behavior in Week 1 rarely make their first transaction.
Subscription media — target users who read one piece of content and didn’t return. The prompt should surface which content category drove the first visit — and recommend more of it.
E-commerce / Delivery — focus on users who browsed but didn’t add to cart. Habit here is browse frequency, not purchase — so messaging should drive return visits, not immediate conversion.

Stage 3 🤑 Conversion → First purchase

⚠️

Catch high-intent users before they convert somewhere else

Goal: Increase CVR free→paid and first purchase rate by identifying engaged non-payers showing purchase intent signals — and reaching them at the right moment with the right offer.

Identify engaged users of [my app name/category] who haven't made their
first purchase. Analyze behavioral signals that predicted first purchase
among users who did convert — including [e.g., pricing screen views /
feature usage / session frequency / time in app].
Build a real-time intent score and launch a personalized campaign
for the top intent segment now.

What ManyMoney does: Continuously scans behavioral events, identifies high-intent micro-signals, scores users by conversion probability, and autonomously launches a campaign — personalized timing, deep link to the exact conversion moment, offer calibrated to intent level.

ManyMoney identified high-intent segments and created a ready-to-launch campaign

Result: Conversion rates on high-intent segments up to 5x higher than broad campaigns — on a fraction of the audience.

How to adapt this prompt across industries:

Gaming — near-payers who visited the IAP store 3+ times without purchasing are the highest-ROI segment in mobile games. Add “IAP store visits” as the primary intent signal.
Fintech — replace purchase with “first transaction” or “first loan application.”
Subscription media — target users who hit the paywall 2+ times.
E-commerce — use cart abandonment, wishlist additions, and repeat product views as intent signals. The prompt works as a smarter version of cart recovery.

Stage 4 🚨 Retention → Churn prevention

⚠️

Stop churn before it happens — not after.

Goal: Reduce churn rate and improve re-engagement CVR by detecting at-risk users early.

Detect users of [my app name/category] showing early churn signals
in the last 14 days: [your churn signal: declining session frequency, no purchases,
notification open rate dropping below [X]%].
Generate personalized re-engagement flows segmented by risk level —
with recommended timing, channel mix, and incentive strategy
for each tier.

What ManyMoney does: Scores churn risk across the entire user base in real time using each user’s personal behavioral baseline — not a fixed segment rule. Builds tiered at-risk segments and launches a multi-touch journey: lighter nudge for medium-risk users, stronger incentive for high-risk, across push, email, and in-app.

ManyMoney churn scoring and re-engagement journey

ManyMoney churn scoring + re-engagement journey

Result: Churn caught 7–14 days earlier than manual review cycles, with incentive spend matched to actual risk level, not wasted on users who would have returned anyway.

How to adapt this prompt across industries:

Gaming — target users who stopped logging in after a specific level or event ended.
Fintech — declining login frequency and no transaction activity are the primary signals.
Subscription — declining feature usage frequency before renewal date is the highest-value signal.
E-commerce / Delivery — no order in the last 30 days for a previously weekly buyer is the trigger. Focus the incentive on re-establishing the ordering habit, not just offering a discount.

Stage 5 💎 Upsell & loyalty → Expand your best users

⚠️

Your top 20% are a blueprint. Use them to grow revenue.

Goal: Increase ARPU and CLV by identifying the behavioral profile of your highest-value users — and using it to expand the cohort and maximize monetization within it.

Segment the top 20% most active and highest-revenue users
of [my app name/category]. Identify the behavioral traits:
[feature usage patterns, e.g., high engagement, top spenders]
that distinguish them from the rest of the user base.
Propose strategies to expand this cohort — including lookalike
segments, premium feature nudges, and upsell campaigns —
and launch the highest-priority one.

What ManyMoney does: Builds the power-user segment, extracts shared behavioral fingerprints — category preferences, session timing, response to past offers — identifies near-tier lookalikes, and drafts a campaign sequence with upsell logic and loyalty mechanics across push, in-app, and email.

ManyMoney power-user segmentation and upsell campaign

ManyMoney power-user segmentation + upsell campaign

Result: Higher ARPU from both existing power users and the next cohort being accelerated toward that tier, without a data analyst or a separate growth sprint.

How to adapt this prompt across industries:

Mobile game — top spenders on IAP; find users close to that behavior pattern and nudge them with exclusive content or limited offers.
Fintech app — users with the highest product adoption; expand into adjacent products like premium accounts or investment features.
Subscription app — annual plan upsell to monthly subscribers showing high engagement patterns.
E-commerce — power users are repeat buyers with high AOV. Upsell is a loyalty program or subscription delivery. Trigger after their third purchase in a category.