Platform Analytics Template (analytics.gbai)

A General Bots template for platform metrics, performance monitoring, and custom report generation.

Overview

The Analytics template provides comprehensive platform analytics capabilities, allowing administrators and stakeholders to monitor usage, track performance, analyze trends, and generate custom reports through conversational AI.

Features

Platform Overview - Key metrics summary with trend analysis
Message Analytics - Conversation statistics by channel and bot
User Analytics - Active users, sessions, and engagement
Performance Metrics - Response times and throughput monitoring
LLM Usage Tracking - Token consumption and cost analysis
Storage Analytics - Disk usage and file statistics
Error Analysis - Error patterns and troubleshooting insights
Custom Report Generator - Build and schedule personalized reports
AI-Powered Insights - Automatic trend analysis and recommendations

Package Structure

analytics.gbai/
├── analytics.gbdialog/
│   ├── start.bas              # Main menu and navigation
│   ├── platform-overview.bas  # Key metrics dashboard
│   └── custom-report.bas      # Custom report builder
└── analytics.gbot/
    └── config.csv             # Bot configuration

Scripts

File	Description
`start.bas`	Main entry point with analytics menu options
`platform-overview.bas`	Platform-wide metrics with trends and export
`custom-report.bas`	Interactive custom report generator with scheduling

Available Analytics

1. Platform Overview

High-level metrics summary including:

Total messages and trend percentage
Average active sessions
Response time performance
Error rates
LLM token consumption

2. Message Analytics

Message volume by time period
Breakdown by channel (WhatsApp, Web, API)
Bot-specific conversation stats
Peak usage times

3. User Analytics

Active users (daily, weekly, monthly)
Session duration analysis
User retention rates
Geographic distribution

4. Performance Metrics

Average response time
Response time distribution
Throughput (messages per second)
Latency percentiles (p50, p95, p99)

5. LLM Usage

Token consumption by model
Cost analysis
Usage patterns
Optimization recommendations

6. Storage Analytics

Disk usage trends
File count and types
Storage by bot/package
Cleanup recommendations

7. Error Analysis

Error frequency and patterns
Error categorization
Root cause analysis
Resolution suggestions

8. Custom Reports

Select metrics to include
Choose time ranges
Set grouping intervals
Export in multiple formats
Schedule automatic delivery

Sample Conversation

User: Show me analytics

Bot:  Welcome to the Analytics Center. I can help you 
      understand your platform metrics and generate reports.

      What would you like to analyze?
      1. Platform Overview - Key metrics summary
      2. Message Analytics - Conversation statistics
      3. User Analytics - Active users and sessions
      4. Performance Metrics - Response times
      5. LLM Usage - Token consumption and costs
      6. Storage Analytics - Disk usage
      7. Error Analysis - Error patterns
      8. Generate Custom Report

User: 1

Bot:  Generating platform overview...
      Select time range (1h, 6h, 24h, 7d, 30d):

User: 24h

Bot:  📊 Platform Overview for Last 24 Hours
      ════════════════════════════════════════
      
      📨 Messages
         Total: 15,432
         Trend: ▲ +12.5% vs previous period
      
      👥 Sessions
         Average Active: 234
         Peak: 412 (at 2:30 PM)
         Trend: ▲ +5.2%
      
      ⚡ Performance
         Avg Response Time: 145 ms
         P95: 320 ms
         P99: 580 ms
      
      ❌ Errors
         Total: 23
         Error Rate: 0.15%
         Most Common: Timeout (12)
      
      🤖 LLM Usage
         Total Tokens: 1,245,678
         Estimated Cost: $18.45
         Avg per Message: 81 tokens
      
      Would you like to:
      (D)etail, (E)xport report, (A)lerts, (B)ack

User: E

Bot:  Export format (PDF, CSV, XLSX):

User: PDF

Bot:  ✅ Report exported: platform_overview_20240515.pdf
      
      The file is available in your Drive.
      Download link: [secure link]

Custom Report Generation

User: I need a custom report

Bot:  Custom Report Generator
      What would you like to name this report?

User: Weekly Performance Summary

Bot:  Select the time range:
      1. Last Hour
      2. Last 24 Hours
      3. Last 7 Days
      4. Last 30 Days
      5. Custom Range

User: 3

Bot:  Select metrics to include (comma-separated):
      1. Message Volume
      2. Active Sessions
      3. Response Time
      4. LLM Token Usage
      5. Error Rate
      6. Storage Usage
      7. API Calls
      8. User Activity
      9. Bot Performance
      10. All Metrics

User: 1,3,4,5

Bot:  Select grouping interval:
      1. Hourly
      2. Daily
      3. Weekly

User: 2

Bot:  Generating your custom report...
      
      ✅ Report generated successfully!
      
      📋 Weekly Performance Summary
      📅 Period: May 8-15, 2025
      📊 Metrics: Messages, Response Time, LLM Usage, Errors
      📈 Grouping: Daily
      
      Download: [secure link]
      
      Would you like to schedule this report?

User: Yes, weekly

Bot:  ✅ Report scheduled!
      
      Frequency: Weekly on Monday at 8:00 AM
      Delivery: Email to your address
      
      You can manage scheduled reports anytime.

Metrics Query System

The template uses a metrics query system:

' Query metrics for a time range
messages = QUERY METRICS "messages" FOR "24h"
totalMessages = SUM(messages, "count")

' Query with grouping
hourlyMessages = QUERY METRICS "messages" FOR "24h" BY "1h"

' Query with offset for comparison
prevMessages = QUERY METRICS "messages" FOR "24h" OFFSET 1
trend = ((totalMessages - SUM(prevMessages, "count")) / SUM(prevMessages, "count")) * 100

Export Formats

Reports can be exported in multiple formats:

Format	Description
PDF	Formatted report with charts
XLSX	Excel spreadsheet
CSV	Raw data export
JSON	Structured data format

Scheduled Reports

Configure automatic report delivery:

Schedule	Cron Expression	Description
Daily	`0 8 * * *`	Every day at 8 AM
Weekly	`0 8 * * 1`	Monday at 8 AM
Monthly	`0 8 1 * *`	1st of month at 8 AM

SET SCHEDULE "0 8 * * 1", "generate-scheduled-report.bas"

Configuration

Configure in analytics.gbot/config.csv:

Parameter	Description	Example
`Default Time Range`	Default period for queries	`7d`
`Data Retention Days`	How long to keep metrics	`90`
`Admin Email`	Email for scheduled reports	`admin@company.com`
`Enable AI Insights`	Auto-generate insights	`true`
`Export Path`	Report storage location	`/reports/`

Customization

Adding Custom Metrics

' Track custom events
INSERT INTO "custom_metrics" VALUES {
    "name": "feature_usage",
    "value": 1,
    "tags": {"feature": "chat", "plan": "pro"},
    "timestamp": NOW()
}

' Query custom metrics
usage = QUERY METRICS "feature_usage" FOR "30d" WHERE tags.feature = "chat"

Custom Dashboard Widgets

' Add to start.bas
TALK "Custom Metrics:"
TALK "9. Feature Usage"
TALK "10. Revenue Analytics"
TALK "11. Customer Health Score"

' Handle custom options
CASE 9
    CALL "feature-usage.bas"
CASE 10
    CALL "revenue-analytics.bas"

AI-Powered Insights

' Generate AI insights from metrics
SET CONTEXT "You are an analytics expert. Generate executive insights."

insights = LLM "Analyze this data and provide 3-5 key insights: " + JSON(report_data)

Integration Examples

With Alerting

' Set up alerts based on metrics
errorRate = SUM(errors, "count") / SUM(messages, "count") * 100

IF errorRate > 5 THEN
    SEND MAIL admin_email, "High Error Rate Alert", 
        "Error rate is " + errorRate + "%, above 5% threshold.", []
END IF

With External BI Tools

' Export data for external tools
data = QUERY METRICS "messages" FOR "30d" BY "1d"
WRITE "analytics_export.csv", CSV(data)

' Or send to webhook
POST "https://bi-tool.example.com/webhook", data

Best Practices

Set appropriate time ranges - Don’t query more data than needed
Use caching - Cache expensive queries
Schedule off-peak - Run heavy reports during low traffic
Monitor the monitor - Track analytics query performance
Archive old data - Move historical data to cold storage
Validate insights - Review AI-generated insights for accuracy

Troubleshooting

Issue	Cause	Solution
Slow queries	Large time range	Reduce range or add filters
Missing data	Metrics not collected	Verify instrumentation
Export fails	Large report size	Export in chunks
Stale data	Cache not refreshed	Clear cache
Incorrect trends	Insufficient history	Wait for more data

Use Cases

Operations Teams - Monitor platform health and performance
Product Managers - Track feature usage and engagement
Executives - High-level KPI dashboards
Support Teams - Identify error patterns
Finance - LLM cost tracking and optimization

Data Privacy

Analytics data is aggregated and anonymized
User-level data requires appropriate permissions
Respect data retention policies
Comply with GDPR/CCPA as applicable

BI Template - Business Intelligence reporting
Talk to Data - Natural language data queries
CRM - CRM analytics and pipeline reports

General Bots Documentation