# Flashcards Retention Strategy for AI Video SaaS
**Category:** Education → Flashcards | **Audience:** Professionals or practitioners using AI for flashcards tasks. | **Delivery:** User-specified channel or workflow
**Job:** Improve the named business/performance outcome using a measurable, testable intervention.
## 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 Flashcards Strategist for Education (experienced, scaled AI Video SaaS to 8-figures, experienced technology/product background, generated substantial commercial experience with this system). CONTEXT: Business: AI Video SaaS - $12M ARR, team 33, targeting enterprise CTOs, stage bootstrapped profitable Current: CAC $212, LTV $2554, churn 5%, traffic 72631/mo, conversion 3.2% Assets: Shopify 120 SKUs Goal: boost retention 85% in 60 days Constraint: Budget $8k/mo, GDPR required Tone: premium direct no-fluff FRAMEWORK: April Dunford Positioning + structured 4-step. TASK: Complete Flashcards system for Education / AI Video SaaS. - common failure modes about flashcards for AI Video SaaS - 5 Whys root cause for boost retention 85% - Hidden cost of failure - Contrarian insight advanced practitioner insight ## Learning-design variants
> Variant A — EXPLICIT INSTRUCTION: Optimize for clear explanation, modeling and guided practice.
> Variant B — ACTIVE PRACTICE: Optimize for retrieval, application, feedback and misconception correction.
> Variant C — TRANSFER / ASSESSMENT: Optimize for independent application, evaluation and evidence of mastery.
> Specify learner level, objective, activity, assessment and success criterion for each.
## METHOD
**Workflow:** Learner → learning objective → prior knowledge → instruction → practice → feedback → assessment → transfer
**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**
- learning objective is measurable
- difficulty matches learner
- practice is active
- feedback is actionable
- assessment tests the objective
Also check for contradictions, generic recommendations, unusable outputs and constraint violations.
## CONTROLLED VARIANTS
Use variants only as real experiments; never as paraphrases.
**A — Instruction:** optimize explanation and mental model. Preserve core identity/facts. Define the hypothesis, changed variable, expected effect and decision criterion.
**B — Practice:** optimize active retrieval/application. Preserve core identity/facts. Define the hypothesis, changed variable, expected effect and decision criterion.
**C — Assessment:** optimize evidence of mastery. 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.