Analytics Dashboards

Analyze AI fleet performance metrics including costs, requests, and agent stats.

24|4|Updated Dec 11, 2025
One-click install
npx skills add https://github.com/systempromptio/systemprompt-template --skill analytics-dashboards-systempromptio
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Analytics Dashboards
Source: https://github.com/systempromptio/systemprompt-template/tree/main/services/skills/analytics_dashboards
Command: npx skills add https://github.com/systempromptio/systemprompt-template --skill analytics-dashboards-systempromptio

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a comprehensive overview of your AI fleet's performance, including costs, request volume, agent performance, tool reliability, sessions, and conversations, allowing you to quickly identify trends and areas for improvement.

Core Features & Use Cases

  • Fleet Overview: Gain a high-level view of your AI fleet's performance.
  • Cost Analysis: Understand your total spend and where it goes.
  • Request and Routing: Analyze request volume, tokens, latency, and cache hit rate.
  • Agent Performance: Evaluate agent task counts, success rates, and costs.
  • Tool Analysis: Monitor tool executions, success rates, and p95 latency.
  • Session and Conversation Insights: Review active sessions, stats, and recent conversations.
  • Content Engagement: Assess content engagement and top performing content.
  • Traffic Analysis: Analyze sources, geographic distribution, devices, and bot traffic.
  • Use Case: Use this Skill to determine if your AI fleet is within budget and if there are any bottlenecks or inefficiencies that need to be addressed.

Quick Start

Run 'systemprompt analytics overview' to get a one-screen overview of your AI fleet's performance.

Frequently Asked Questions about Analytics Dashboards

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I monitor AI fleet performance and costs across multiple agents?

You can monitor AI fleet performance by generating a comprehensive overview of costs, request volume, agent stats, and tool reliability. This allows you to quickly identify spending trends and operational bottlenecks across your entire fleet.

What metrics are included in an AI fleet analytics overview?

An AI fleet analytics overview includes costs, request volume, token counts, latency, cache hit rates, agent task success rates, tool execution stats, session activity, and traffic sources to provide a complete picture of fleet health.

How do I analyze agent task success rates and tool execution latency?

You can analyze agent task success rates and tool execution latency by reviewing the agent performance and tool analysis metrics, which evaluate task counts, success rates, costs, and p95 latency for your AI operations.

Can I track AI token spend and request routing volume without external dependencies?

Yes, you can track token spend and request routing volume without external dependencies. The Skill internally handles data across your fleet to analyze total spend, request tokens, and cache hit rates natively.

What is the best way to identify bottlenecks in AI agent and tool performance?

The best way to identify bottlenecks is to analyze tool execution success rates alongside p95 latency and agent task counts. This highlights inefficiencies and reliability issues within your AI fleet operations.

How do I get a quick summary of active AI sessions and traffic sources?

You can get a quick summary of active sessions and traffic sources by running a single overview command. It reviews active sessions, recent conversations, geographic distribution, devices, and bot traffic.