Prompt Details
Model
Chat - (gpt-5.4)
Token size
560
Example input
[Mobile App / Web App / SaaS Platform]: SaaS Platform
[Small / Growing / Large]: Growing
[Subscription / Ads / Freemium / Ecommerce]: Freemium
[Early / Growth / Mature]: Growth
[Basic / Advanced / Full Analytics]: Full Analytics
Example output
1οΈβ£ Analytics System Architecture
Data Collection Pipeline
Client-side SDK collects user interaction data from web and mobile interfaces
Events are captured using event tracking libraries (e.g., Segment-style tracking)
Data sent to event ingestion API in real time
Event queue system buffers incoming events to prevent overload
Data Processing Workflow
Event data streamed into message queues
Stream processing layer cleans and validates event data
Data transformation pipeline structures events into analytics-ready format
Processed data stored in a data warehouse for querying
Analytics Infrastructure Overview
Event ingestion service for collecting user data
Stream processing engine for real-time analytics
Data warehouse for historical analysis
BI layer for dashboards and reporting
---
2οΈβ£ Key Metrics Framework
Product Performance Metrics
Feature load success rate
API response time
Application uptime percentage
Active feature usage frequency
User Engagement Indicators
Daily Active Users (DAU)
Weekly Active Users (WAU)
Average session duration
Feature interaction rate
Business Growth Metrics
Free-to-paid conversion rate
Monthly recurring revenue growth
User acquisition rate
Churn rate
---
3οΈβ£ Event Tracking Strategy
User Interaction Events
User login event
Feature click event
Page navigation event
Form submission event
Feature Usage Tracking
Feature activation event
Feature completion event
Feature drop-off event
Conversion Funnel Monitoring
Landing page visit
Account creation
Product activation
Upgrade to paid plan
---
4οΈβ£ Dashboard Design
Key Dashboard Sections
User activity overview
Feature adoption dashboard
Conversion funnel dashboard
Revenue performance dashboard
Metric Visualization Strategy
Line charts for user activity trends
Funnel charts for conversion analysis
Heatmaps for feature interaction
Bar charts for feature comparison
Reporting Layout Structure
Executive overview at the top
Engagement metrics in the middle
Detailed feature analytics below
Revenue and growth metrics at the bottom
---
5οΈβ£ User Behavior Analytics
Session Analysis
Average session duration
Session frequency per user
Session depth (number of actions per session)
User Journey Tracking
Entry points analysis
Navigation path tracking
Feature adoption journey
Retention Analysis
Day 1 retention rate
Day 7 retention rate
Day 30 retention rate
---
6οΈβ£ Performance Monitoring
App Performance Metrics
Page load time
API latency
Server response time
Latency Tracking
Network latency monitoring
Backend processing time tracking
Time-to-interaction measurement
Error Monitoring
Application crash rate
API failure rate
Client-side error frequency
---
7οΈβ£ Revenue Analytics
Monetization Metrics
Average revenue per user (ARPU)
Monthly recurring revenue (MRR)
Upgrade conversion rate
Customer Value Tracking
Customer lifetime value (LTV)
Revenue per cohort
Expansion revenue from existing users
Conversion Rate Analysis
Free trial to paid conversion
Feature-based upgrade triggers
Pricing page conversion rate
---
8οΈβ£ Alerting & Insight System
Automated Alerts for Anomalies
Sudden drop in active users
Spike in application errors
Unusual traffic patterns
KPI Threshold Monitoring
DAU falling below threshold
Conversion rate below expected range
Retention rate decline
Growth Opportunity Insights
High-performing features identified
Drop-off points in conversion funnel
Features with highest engagement
---
9οΈβ£ Data Governance
Data Accuracy Checks
Event validation rules
Duplicate event detection
Schema consistency monitoring
Data Privacy Considerations
User data anonymization
Compliance with data protection regulations
Consent-based tracking
Analytics Data Lifecycle Management
Raw event data retention policy
Aggregated data storage for long-term analysis
Archiving outdated analytics data
---
π Executive Analytics Blueprint
Most Important Metric to Monitor
Product Activation Rate (percentage of new users completing the key onboarding action)
Biggest Analytics Blind Spot
Lack of deep feature-level engagement analysis
One Dashboard Improvement to Implement Immediately
Add a real-time product activation funnel dashboard to identify onboarding drop-offs quickly π
By purchasing this prompt, you agree to our terms of service
GPT-5.4
Successful applications rely on clear data insights to understand user behavior, product performance, and growth trends.
Without structured analytics systems, teams struggle to make data-driven decisions.
This prompt designs a complete analytics architecture including metrics tracking, dashboards, event tracking, and performance monitoring.
Buyer Benefits
π KPI dashboard planning
π User behavior analytics structure
β Event tracking architecture
π Performance monitoring framework
π Data-drive
...more
Added over 1 month ago
