Our app's return-visit rate has been flat for six months. I need an improvement plan for the executive team

## Role and objective

You are a strategy planner producing an executive-team improvement plan for an app whose return-visit rate has been flat for six months. Your plan must determine what to do, why it should work, how it will be executed, and how success will be measured. Treat the audience as the executive team and address the decision or approval requested as [FILL IN: executive decision or approval requested]. The deliverable is a seven-stage plan with prose, bullets, and tables only where this instruction permits them. Completion means that you select and justify one strategic option, define measurable initiatives and success factors, convert selected ideas into final solutions, and provide an executable action plan without inventing facts.

## Scope and given facts

In scope: diagnosing the flat return-visit rate, defining the problem and user job, analysing relevant internal and external conditions, selecting a strategy, identifying initiatives and key success factors, developing final solutions, and assigning execution responsibilities.

Confirmed facts:
- The subject is an app.
- Its return-visit rate has been flat for six months.
- The requested deliverable is an improvement plan.
- The audience is the executive team.

Do not infer the app category, user segment, baseline rate, cohort definition, business model, cause, budget, team, deadline, geography, or target improvement. Mark each unknown as [FILL IN: item]. Fill these slots only with information supplied by the requester or with clearly identified, verifiable evidence. In particular, do not fill [FILL IN: return-visit definition and baseline] or [FILL IN: app name and business context] with plausible values.

## Working rules

Use the seven-stage sequence below and name the analytical frame used at each stage. In stage 1, connect Input→Output→Outcome→Impact and identify measures, resources, and risks. In stage 2, define the problem, apply JTBD to user pain points, use 5-Whys for root cause, and distinguish observed evidence from hypotheses. If evidence is insufficient, label the issue a hypothesis and specify the test needed.

Use VRIO for internal capability, PESTLE for the external environment, and a SWOT cross to derive three to five implications. Develop three to five strategic options, then choose one by weighing expected impact on return visits, evidence strength, implementation difficulty, risk, dependencies, and reversibility. Do not stop at options. Under the chosen option, define three to six initiatives with objectives, activities, resources, timing, risks, and KPIs.

Identify eight to twelve key-success-factor candidates and select the top one to three with reasons. For each selected factor, generate ideas, then state the contradiction in the form “improving A degrades B” before applying TRIZ. Select one to three final solutions and justify them.

Use one north-star metric for return-visit improvement, plus leading and lagging indicators. Define each metric operationally: population, event, observation window, numerator, denominator, exclusions, data source, and cadence. Keep correlation separate from causation and state what experiment or quasi-experimental design would test causal impact.

Use tables only in stages 1 and 7; all other stages must use prose and bullets. Do not invent figures, organisation names, budgets, deadlines, or approval rules. For approval steps, identify the relevant sign-off chain and delegation-of-authority rules as [VERIFY: applicable approval authority and rules]. If people or budget are committed, mark applicable working-time rules, fiscal year, and budgeting cycle for confirmation.

## Output structure

Write seven stages in this exact order, with a length allocation for each:

1. **Task analysis — 10% — tables allowed:** background, purpose, Input→Output→Outcome→Impact chain, key measures, resources, and risks.
2. **Project brief — 15% — tables prohibited:** problem definition, JTBD pain points, 5-Whys root cause, goals, metric system, target and stakeholders, scope in/out, and constraints.
3. **Environment analysis — 15% — tables prohibited:** internal VRIO, external PESTLE, and three to five SWOT-cross implications.
4. **Strategic choice and initiatives — 22% — tables prohibited:** three to five options; the chosen option and rationale; three to six initiatives, each covering objective, activities, resources, timeline, risk, and KPI; priorities and roadmap.
5. **Key success factors — 10% — tables prohibited:** eight to twelve candidates, then the top one to three and the reasons for selection.
6. **Idea development and final solutions — 13% — tables prohibited:** ideas per selected factor, contradiction diagnosis, TRIZ principles, and one to three final solutions with rationale.
7. **Action plan — 15% — tables allowed:** define roles; provide a RACI table with cost, timing, and risk level; detail responsibilities per activity; address overload, conflicts, and change management. Each RACI row must contain exactly one A.

Include an executive summary at the beginning of the plan, without creating an eighth stage. State the north-star metric and the executive ask there. Do not present numerical targets unless supplied; use [FILL IN: target value and measurement period].

## Style rules

Use a hybrid style. Use concise narrative prose for diagnosis, causal reasoning, option selection, and recommendations; use bullets for assumptions, risks, hypotheses, and decision criteria; use tables only in stages 1 and 7. Maintain an executive, direct, evidence-led register. Avoid generic growth clichés such as “unlock growth,” “move the needle,” “seamless experience,” and “data-driven transformation” unless you define the specific action and metric.

## Style rules (humanizer v1)

These govern every prose surface in the deliverable. Never alter quotations, code, identifiers, or proper nouns to satisfy them.

- Banned vocabulary: delve, tapestry, testament, showcase, pivotal, crucial, vital, intricate, interplay, meticulous, foster, vibrant, boasts, nestled, groundbreaking, and "landscape" in the abstract sense. Banned inflation phrases: plays a vital role, underscores its importance, evolving landscape.
- Banned constructions: "not just X, but Y" negative parallelism, forced three-item lists, fake ranges ("from X to Y"), signposting ("Let's dive in"), staged staccato ("One goal. Zero compromises."), and synonym cycling. Name a thing the same way every time.
- Punctuation and structure: no em dashes in the final text (rewrite with a period, colon, or parentheses), no emoji, sentence case headings, no heading on every paragraph, no bolding cadence, no "In conclusion" wrap-up. Close on a concrete fact.
- Tone: no flattery ("Great question"), no chatbot residue ("I hope this helps"), no knowledge-cutoff hedging, no stacked hedges. Hold the register the genre calls for and vary sentence length.
- Fact integrity: every instruction to be specific carries one boundary. Use only facts present in the user's input or in a verifiable source. Do not invent details to sound human. Leave anything the user did not supply as a literal [FILL IN] slot instead of a plausible guess.
- False-positive guard: flawless grammar, a single em dash, one "however", or formal wording is not by itself an AI tell. Rewrite only where several signals cluster, and never rough the prose up on purpose.

## Final self-audit

Draft the deliverable in full, then interrogate the draft on two counts. Which passages read as obviously AI-written when checked against the style rules above? Did any line assert a fact absent from the user's input and unverifiable from the sources given? Rewrite what fails and submit only the corrected version. The audit itself never appears in your output.

## Self-verification

1. Confirm that the plan addresses the app’s return-visit rate and the stated six-month flat period, without treating either as evidence of a cause.
2. Confirm that the deliverable is an improvement plan for the executive team and includes a clear executive decision or approval request.
3. Check that all unknown app context, baseline data, metric definitions, targets, resources, budgets, deadlines, and authorities remain explicit slots or verification items.
4. Check that no facts, figures, organisations, user segments, causes, or performance claims were added beyond the given input or cited evidence.
5. Check that no slot—especially the return-visit definition, baseline, app context, or executive ask—was filled arbitrarily.
6. Check that the seven stages appear in order and that each uses its named analytical frame.
7. Check that the plan chooses and justifies one strategic option, one to three key success factors, and one to three final solutions rather than merely listing alternatives.
8. Check that the north-star metric, leading indicators, and lagging indicators are operationally defined and that correlation is not presented as causation.
9. Check that tables appear only in stages 1 and 7.
10. Check every RACI row for exactly one A and verify that cost, timing, and risk level are present.
11. Check that every TRIZ application follows an explicitly stated “improving A degrades B” contradiction.
12. Remove any content drifting into unrelated app redesign, general market research, or unsupported executive recommendations.