90-Day Lifecycle Marketing Diagnostic and Experiment Roadmap for Onboarding and Retention

Diagnoses drop-off across the customer lifecycle from your funnel data and produces a prioritized 90-day plan of messages, triggers, and experiments with metrics so teams can decide where to invest first.

You get: A strategy you can act on

More like this

The prompt

90-day-lifecycle-marketing-diagnostic-and-experiment-roadmap-for-onboarding-and-retention.md
ROLE: You are a lifecycle marketing lead with experience in email, in-app messaging, and CRM programs for {business_model} companies. CONTEXT: {brand} wants to improve {lifecycle_goal} such as activation, repeat purchase, renewal, or reactivation for {customer_segment}. The job-to-be-done is to decide which lifecycle stage to fix first and which experiments to run in the next 90 days. TASK: Diagnose the stage-by-stage funnel using the supplied data, identify the biggest leverage points, and create a prioritized program and test roadmap. CONSTRAINTS: Use only the supplied metrics and label every assumption. Do not promise lift or revenue outcomes; give hypotheses and decision rules instead. Respect consent, privacy, and regional email rules mentioned in the inputs, and do not request personal customer data. Keep recommendations feasible for the team size and tools provided. TOOL INSTRUCTIONS FOR CHATGPT: Begin by confirming the inputs in a short table and asking for any missing required metric before analysis. If the user pastes a CSV or table, restate column meanings and the time period before calculating. Show any calculation steps in plain language so they can be checked. Use markdown tables for the roadmap and keep message copy in separate labeled blocks. If data is insufficient, say which analysis cannot be done instead of estimating. Inputs: 1) Lifecycle stages and conversion or retention rate at each stage with time period: {funnel_metrics}. 2) Current programs and channels such as welcome series, abandoned cart, in-app tips, newsletters, or win-back: {current_programs}. 3) Segment definitions and available behavioral data fields: {segments_and_data}. 4) Team size, tools, and weekly capacity: {team_and_tools}. 5) Product or offer constraints, margin limits, and discount policy: {offer_constraints}. 6) Target metric and deadline: {target_metric}. 7) Compliance or brand rules: {compliance_rules}. Workflow: Step 1, Data readiness check: list available metrics, missing metrics, and data quality risks such as small samples or short windows. Step 2, Stage diagnosis: build a table with stage, current metric, estimated size of drop-off in users or revenue where computable, likely causes, and evidence strength. Step 3, Leverage ranking: rank the top 3 stages by potential impact, effort, and confidence, and explain why the first one comes first. Step 4, Program map: for the top stage, define trigger, audience, message goal, channel, timing, and exit condition for each touchpoint. Step 5, Message drafts: write a brief for each touchpoint with subject line options, key message, call to action, and personalization fields that need no sensitive data. Step 6, Experiment backlog: write 6 experiments, each with hypothesis, variable changed, primary metric, guardrail metric, minimum run time, and decision rule for ship, iterate, or stop. Step 7, 90-day roadmap: sequence work in three 30-day phases with owner roles and dependencies. Step 8, Measurement plan: define the dashboard metrics, cadence of review, and how results will be attributed or caveated. Output format: Use these headings: Data Readiness Check, Stage Diagnosis Table, Leverage Ranking, Program Map, Message Briefs, Experiment Backlog Table, 90-Day Roadmap Table, Measurement Plan, Risks and Missing Information, Next 5 Actions. Acceptance criteria: The first priority stage is justified with supplied data. Each experiment has a single primary metric, a guardrail metric, and a stop rule. The roadmap fits the stated team capacity. No outcome is guaranteed and all assumptions are labeled. Messages are consistent with the offer and compliance constraints. Quality checks: Verify that calculations can be reproduced from the inputs, that no experiment changes more than one main variable, that discounts do not violate the stated policy, that sample size or run-time limitations are flagged, and that every recommendation maps to a stage in the diagnosis. Finish with a short list of the three biggest unknowns and how to resolve each.

Example output

AI-written example

Data Readiness Check

Window: last 90 days, 12,400 trial signups (EU/US, running-app, Pacely). Team: 1 lifecycle marketer + 0.5 analyst, Braze, ~15 hrs/week. Missing: channel-level opt-in rates (assumption: ~60% push opt-in). Risk: the retention cohort is only 90 days old.

Stage Diagnosis Table

StageRateUsers lostLikely causeEvidence
Signup → first workout (7d)48%6,448No clear first stepMedium
→ 3 workouts by day 1452%2,857Habit not formedLow
→ Paid38%1,919Value unclear at day 12Low
Month-3 retention71%341UnknownLow

Calc: 12,400 × 48% = 5,952 activated; 12,400 − 5,952 = 6,448.

Leverage Ranking

  1. Signup → first workout: largest absolute loss, and every later stage depends on it. Low effort (messaging only), medium confidence.
  2. Day 3–14 habit building.
  3. Trial-to-paid conversion.

Program Map

TouchTriggerChannelTimingExit
1 WelcomeSignupEmailImmediatelyFirst workout logged
2 Starter planNo workout after 24hPush (if opted in), else emailDay 1Workout logged
3 NudgeNo workout after 72hEmailDay 3Workout logged

Message Briefs

Touch 2

  • Subject options: "Your first 15-minute run is ready" / "{first_name}, start easy today"
  • Key message: a beginner plan takes 15 minutes.
  • CTA: "Start my first run"
  • Fields: first_name, chosen_goal

Experiment Backlog Table

#Hypothesis (variable)Primary / GuardrailMin runDecision rule
1Goal-based welcome subject raises first workout (subject line)7d first workout / unsubscribe rate14dShip if lift holds and unsubscribes don't rise; stop if flat
2Push beats email at 24h (channel
Generated from this prompt by AI. Your results will vary.

Tips and common edits

Include at least 8 to 12 weeks of stage-level metrics when possible. If volumes are low, ask the model to favor qualitative tests and larger changes. Have your legal or privacy owner review any consent-related decisions.

Questions about this prompt

More in AI Marketing

Onboarding Email Sequence Audit and Rewrite Around One Activation Event

Audits an existing or planned onboarding email flow, then rewrites it around a single activation event with segmentation, timing, copy, and a measurement plan.

Customer Review Mining: Personas, Jobs-to-Be-Done, Objections and Verbatim Copy Phrases

Turns pasted customer reviews into evidence-based personas, jobs-to-be-done, objections and a bank of exact customer phrases ready to reuse in copy.

Five-Angle Meta and Google Ad Copy Generator with Character Counts and A/B Test Plan

Produces Meta and Google ad copy across five distinct angles within platform character limits, plus a simple test plan with decision rules.

One-Page Brand Voice Brief Builder from Copy Samples for ChatGPT, Claude and Gemini

Analyzes your brand copy samples and builds a reusable one-page voice brief with tone rules, banned words, example rewrites and a paste-ready instruction block.

Positioning and Messaging Hierarchy Builder from Competitor and Customer Evidence

Turns your product facts, customer evidence, and competitor notes into a tested positioning statement, messaging hierarchy, and proof-gap list so a marketing team can decide what to say and what to validate first.

Turns pasted links and notes into a newsletter issue with a hooking intro, three takeaway sections, and one call to action.

Process Transcript to Standard Operating Procedure

Converts a pasted process description or transcript into an SOP with purpose, roles, numbered steps, checklists and common mistakes.

Audience Research Source Discovery and Evidence Synthesis for Segment Prioritization

Guides you to plan source discovery, review the evidence you collect, build a citation table, and synthesize findings into a segment prioritization decision, without pretending the model browsed the web.

Codebase Tour for a Specific Task

Explores a repo through the lens of your task and explains the architecture, key files and data flow, then says where to start.

Trending

Developmental Edit Memo for an Essay Draft With Revise-or-Cut Decisions

Gives a draft essay a structured developmental edit: thesis check, paragraph-by-paragraph audit, and a prioritized revision plan so you can decide what to keep, rewrite, or cut before line editing.

30-Minute Moderated Usability Test Script with Tasks and Notes Template

Produces a timed 30-minute moderated usability script with task scenarios, neutral follow-up questions and a ready-to-use notes template.

4-Week Small Business Launch Plan: $0 and Small-Budget Versions

Builds a 4-week launch plan for a product or service in a specific market, with channels and weekly tasks in a $0 version and a small-budget version.