AI Skill Report Card

Analyzing AI Platform Metrics

C+65·Mar 30, 2026·Source: Extension-page
8 / 15
Python
# Platform health snapshot metrics = { 'topics': 57, 'experts': 42, 'knowledge_bases': 90, 'models': 19, 'agents': 11, 'users': 265 } growth_rates = { 'topics': 12, 'experts': 8, 'knowledge_bases': 15, 'models': 5, 'agents': 5, 'users': 20 } print("Platform Health Score:", calculate_health_score(metrics, growth_rates))
Recommendation
Replace the pseudocode Quick Start with concrete executable analysis code showing actual calculations and thresholds for health scoring
12 / 15

Progress:

  • Collect core metrics (topics, experts, KBs, users, agents)
  • Calculate growth rates and trends
  • Analyze usage patterns and engagement
  • Identify resource allocation opportunities
  • Generate actionable insights
  • Create executive summary with recommendations

Detailed Steps

  1. Metrics Collection

    • Core resources: Topics, Experts, Knowledge Bases, Models, Agents
    • User metrics: Total users, active users, growth rate
    • Usage patterns: Chat frequency, peak times, response times
  2. Engagement Analysis

    • Chat frequency trends over time periods
    • Topic-expert relationship mapping
    • Knowledge base access patterns
    • Agent utilization rates
  3. Security & Access Review

    • Access control distribution (Individual/Group/Organization)
    • Knowledge base security posture
    • Integration connectivity status
  4. Performance Assessment

    • Response time analysis
    • System adoption rates
    • Resource utilization efficiency
    • Error patterns from notifications
Recommendation
Transform abstract examples into real input/output pairs with actual metric dashboards and specific numeric insights rather than general recommendations
10 / 20

Example 1: Input: Platform shows 265 users, 57 topics (+12%), 42 experts (+8%), 90 KBs (+15%) Output: "Strong growth trajectory. KB expansion (15%) outpacing user growth (implied) suggests deepening engagement. Recommend scaling expert capacity to match KB growth."

Example 2: Input: 81% of KBs are org-level access, 28.8% topics individual access, 7 active integrations Output: "Knowledge democratization strategy working (81% org access). Topic personalization high (28.8% individual). Integration ecosystem stable at 7 connections."

Recommendation
Add concrete calculation formulas and benchmarks for ratios, growth thresholds, and red flag indicators instead of just listing best practices
  • Focus on ratios: Topics per expert (1.4), KBs per user (0.34), agents per expert (0.26)
  • Track access patterns: Balance individual customization with organizational sharing
  • Monitor notification patterns: Failed document processing indicates system stress
  • Correlate growth rates: Identify resource bottlenecks before they impact performance
  • Use time-series data: Daily chat frequency reveals usage patterns and adoption trends
  • Don't analyze metrics in isolation - look for correlations and dependencies
  • Don't ignore failed notifications - they indicate system capacity issues
  • Don't focus only on growth percentages - consider absolute numbers for capacity planning
  • Don't overlook access distribution - security and collaboration balance is critical
  • Don't assume high agent count means high utilization - check actual usage metrics
0
Grade C+AI Skill Framework
Scorecard
Criteria Breakdown
Quick Start
8/15
Workflow
12/15
Examples
10/20
Completeness
8/20
Format
15/15
Conciseness
12/15