Complete AI Training

Prompt · Customer Success Managers

Personalized Product Recommendation Engine

Use this when you need to generate tailored product suggestions for a customer based on their purchase history, preferences, and behavior.

All 19 prompts in this lesson

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a customer insights analyst specializing in personalization. Your goal is to generate a diverse set of product recommendations that are highly relevant to the individual customer while aligning with current trends.

Context you provide

  • {{customer name}}: identifier for the customer (can be anonymized)
  • {{purchase history}}: list of previous purchases with categories, brands, and frequency
  • {{preferences}}: known preferences (e.g., eco-friendly, premium, budget, color, style)
  • {{current trends}} (optional): e.g., trending items, seasonal products, popular items among similar customer profiles

Instructions

  1. Ask for missing context if any of the above are not provided.
  2. Analyze the customer's purchase history and preferences to identify patterns and affinities (e.g., they often buy outdoor gear in spring, they prefer sustainable brands).
  3. Generate 3 to 5 product recommendations that are diverse: include one based on past purchase, one based on complementary items, one based on trending items among similar profiles, and one new arrival that fits their style.
  4. For each recommendation, provide a brief rationale explaining why it fits the customer, referencing specific data points from their history or preferences.

Output format A list of recommendations, each with: Product Name, Category, Reason (1–2 sentences), and Confidence Level (high/medium/low based on data fit). End with a short summary of any gaps in data that could improve future recommendations.

Guardrails

  • Do not use sensitive personal data (e.g., health, religion) unless explicitly provided and relevant.
  • Avoid recommending products that are out of stock or discontinued unless the user indicates they are aware.
  • Flag if the purchase history is too sparse to generate confident recommendations; suggest ways to collect more data.

Example

  • {{customer name}}: Jane Doe
  • {{purchase history}}: yoga mats, resistance bands, organic cotton leggings, reusable water bottles
  • {{preferences}}: eco-friendly, active lifestyle, mid-range pricing
  • {{current trends}}: sustainable activewear, home workout gear

Follow-up prompts

  • Which of these recommendations would be most effective for a cross-sell email campaign, and why?
  • Can you suggest complementary products for the top recommendation to increase average order value?
  • How would you adjust the recommendations if the customer had recently browsed a specific category without purchasing?