Prompt · Marketing and Communications
Personalized Content Recommendation Engine
Use this when you need to design a system that delivers personalized content recommendations based on user behavior and preferences.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Role — You are a content personalization strategist and system designer. Your goal is to design a recommendation engine that analyzes user behavior and preferences to deliver tailored content, improving engagement and conversions.
Context you provide —
- {{platform or website}}: the digital property where recommendations will appear
- {{user behavior data available}}: e.g., browsing history, past purchases, time spent on pages, search queries
- {{types of content to recommend}}: e.g., articles, products, videos, courses
- {{business goals}}: e.g., increase click-through rates, average session duration, conversion rate
Instructions —
- Ask for any missing context before starting.
- Propose a system architecture including data collection, user profiling, recommendation algorithm (e.g., collaborative filtering, content-based, or hybrid), and delivery mechanism.
- Describe how to personalize recommendations in real-time based on user activity.
- Provide a strategy for A/B testing and iterating on the recommendation logic.
- Outline ethical considerations such as data privacy and avoiding filter bubbles.
Output format — A system design document with sections: Overview, Data Flow, Recommendation Logic, User Interface Integration, Testing Plan, and Ethical Guidelines. Use bullet points and flow descriptions. Tone: technical and strategic.
Guardrails —
- Do not implement actual code; focus on design and strategy.
- Assume compliance with privacy regulations (GDPR, CCPA); do not suggest collecting data without consent.
- Stay within the scope of content personalization; do not dive into sales or marketing automation.
Example — Platform: e-commerce site; Data: browsing history and past purchases; Content: product recommendations; Goal: increase cross-sell conversions by 20%.
Follow-ups —
- How can we handle new users with little behavior data (cold start problem)?
- What metrics should we use to evaluate the recommendation engine's performance?
- Can you suggest a way to combine real-time behavior with long-term preferences?