Strategy ROAS Campaign Strategy for Mental Health App Using aida-pas-hybrid-linear-slack-system-7600-07600 — Conversion / Performance

# Strategy ROAS Campaign Strategy for Mental Health App Using aida-pas-hybrid-linear-slack-system-7600-07600 — Conversion / Performance **Category:** Claude Prompt → Strategy | **Audience:** Professionals or practitioners using AI for strategy tasks. | **Delivery:** User-specified channel or workflow **Job:** Improve the named business/performance outcome using a measurable, testable intervention Strategic lens: Conversion / Performance. Prioritize the stated conversion or revenue outcome. Identify the largest bottleneck, make one causal intervention, and define a measurable decision threshold. ## SOURCE INPUT Use this source brief as the authoritative task/scenario. Preserve its supplied numbers, constraints, assets, frameworks and requested deliverables. Separate facts from assumptions; never invent missing evidence. > Treat this as the authoritative source brief. Preserve useful specifics; do not invent facts or turn scenario values into verified claims. > > > Act as Senior Strategy Strategist for Claude Prompt (experienced, scaled Mental Health App to 8-figures, experienced technology/product background, generated substantial commercial experience with this system). CONTEXT: Business: Mental Health App - $12M ARR, team 35, targeting affluent homeowners, stage Series A Current: CAC $223, LTV $2148, churn 7%, traffic 47504/mo, conversion 4.8% Assets: Notion docs + SOPs Goal: achieve 4.8 ROAS in 60 days Constraint: Budget $15k/mo, team of 3 Tone: scientific McKinsey FRAMEWORK: AIDA+PAS Hybrid + structured 4-step. TASK: Complete Strategy system for Claude Prompt / Mental Health App. - common failure modes about strategy for Mental Health App - 5 Whys root cause for achieve 4.8 ROAS - Hidden cost of failure - Contrarian insight advanced practitioner insight ## LLM instruction variants > Variant A — DIRECT EXECUTION: Optimize for concise task completion and a precise output contract. > Variant B — LONG-CONTEXT SYNTHESIS: Optimize source organization, evidence handling, assumptions and synthesis. > Variant C — ANALYTICAL QA: Optimize structured evaluation, edge cases, verification and revision criteria. > Each variant must have a distinct reliability or reasoning objective. ## METHOD **Workflow:** Task → context → assumptions → staged execution → validation → output contract **Execution** - Diagnose the actual task before prescribing when diagnosis changes the answer. - Make the key strategic/technical/creative decision explicit. - Use concrete instructions, structures, examples, thresholds or implementation details. - Distinguish supplied facts, assumptions and validation needs. - Do not invent capabilities, results, claims or evidence. **Model / delivery** Target model(s): ChatGPT-4o, Claude 3.5, Gemini 1.5. Keep the core solution portable; adapt only relevant model behavior. Delivery context: User-specified channel or workflow; respect its real format, audience and constraints. **Output contract** Return the smallest complete deliverable that solves the job. Include the result, material assumptions, measurable/verifiable success criteria where relevant, and next decision/action when useful. **QA** - task is unambiguous - context is sufficient - assumptions are explicit - output contract is concrete - self-checks are relevant Also check for contradictions, generic recommendations, unusable outputs and constraint violations. ## CONTROLLED VARIANTS Use variants only as real experiments; never as paraphrases. **A — Direct execution:** concise complete execution. Preserve core identity/facts. Define the hypothesis, changed variable, expected effect and decision criterion. **B — Reasoned workflow:** staged analysis and checkpoints. Preserve core identity/facts. Define the hypothesis, changed variable, expected effect and decision criterion. **C — Structured QA:** schema, validation and edge cases. Preserve core identity/facts. Define the hypothesis, changed variable, expected effect and decision criterion. ## FINAL GATE Before answering, ask: Is this specific to the supplied scenario? Is every important instruction actionable? Are assumptions labeled? Is the output genuinely usable? Would a professional get a better result from this than from a generic prompt? If not, revise the weakest part before delivering.