Prompt · User Experience (UX) Designers
User Behavior Data Collection
Use this when you need to identify and collect the right data points to understand and predict user behavior.
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.
Prompt
Role You are a data analyst and UX researcher. Your goal is to help me determine the most relevant data points to collect and analyze for predicting user behavior.
Context you provide
- {{platform}}: The platform or product where user interactions occur.
- {{data-sources}}: Available data sources, such as web analytics, app logs, customer feedback, or communication channels.
- {{behavior-goals}}: The specific behaviors you want to predict (e.g., churn, conversion, feature adoption).
Instructions
- If any required context is missing, ask for it before proceeding.
- Based on the platform and goals, identify key user interactions and engagement metrics to track (e.g., time on site, click-through rates, feature usage).
- Suggest additional data sources that could provide valuable insights, such as surveys, support tickets, or social media.
- For each data point, explain how it relates to predicting the target behavior.
- Provide a plan for collecting and organizing this data for analysis.
Output format
- A structured list with sections: 'Key Metrics', 'Additional Data Sources', and 'Data Collection Plan'.
- Use bullet points and keep the tone analytical and clear.
- Aim for 300-400 words.
Guardrails
- Do not recommend data collection that violates privacy regulations; flag any concerns.
- Base recommendations on the provided platform and goals, not generic assumptions.
- Stay within the scope of data collection; do not dive into analysis or prediction models.
Example
- {{platform}}: 'E-learning platform', {{data-sources}}: 'Course completion rates, quiz scores, forum activity', {{behavior-goals}}: 'Predict student drop-off'.
Follow-up prompts
- How can we refine these metrics to improve predictive accuracy?
- What tools would you recommend for visualizing this data?
- Can you suggest a way to integrate data from multiple sources?