AI Observability: Dashboards
The AI Observability module includes 12 dashboards. Each covers a different aspect of AI infrastructure operations.
| Dashboard | Purpose |
|---|---|
| Infrastructure Overview | Summary operational picture of all AI components |
| Agents | AI agent behavior: requests, responses, tokens, durations |
| Traces | Spans, statuses, and trace distribution |
| LLM Costs | Cost by models and providers |
| Service Metrics | Inference and AI service metrics |
| GPU Status | Load, memory, temperature, errors |
| Claude Code - Overview | Claude Code costs and API requests, skills, conversations, and application errors |
| Claude Code - Organization | Members and seats, adoption, skills and MCP servers, outcomes, and organizational spending |
| Claude Code - Team and Productivity | PRs, commits, code lines, suggestion acceptance, and team cost per outcome |
| Claude Code - Member | Activity, spending, models, sessions, and subscription limits for one member |
| Claude Code - Subscription and Billing | Subscription seats and budget, tokens, limits, recommendations, and reconciliation with a spend-report equivalent |
| Codex | Local Codex activity: requests, TTFT, tokens, sessions, projects |
Infrastructure Overview
Summary AI Observability dashboard for operational control of the entire AI infrastructure.
Agents
AI Observability dashboard for analyzing AI agent behavior - requests, responses, tokens, and durations.
Traces
AI Observability dashboard for analyzing AI request traces - spans, trace groups, statuses.
LLM Costs
AI Observability dashboard for analyzing LLM costs - tokens, cost, models, providers.
Service Metrics
AI Observability dashboard for analyzing AI service runtime metrics - vLLM, queue, latency, KV cache.
GPU Status
AI Observability dashboard for monitoring GPUs - load, memory, temperature, ECC errors.
Claude Code - Overview
AI Observability dashboard summarizing Claude Code costs, API requests, skills, conversations, and application errors.
Claude Code - Organization
AI Observability dashboard for Claude Code usage across an organization - members and seats, adoption, skills and MCP servers, outcomes, and spending.
Claude Code - Team and Productivity
AI Observability dashboard for team outcomes in Claude Code - PRs, commits, code lines, suggestion acceptance, skills, tools, and cost per outcome.
Claude Code - Member
AI Observability dashboard for a Claude Code member - activity, spending, tokens, models, skills, daily summaries, sessions, and subscription limits.
Claude Code - Subscription and Billing
AI Observability dashboard for Claude Code subscription seats, spending, tokens, limits, and cost reconciliation.
Codex
AI Observability dashboard for monitoring local Codex - requests, tokens, TTFT, durations, projects.