Claude Agent SDK Dashboard

This dashboard offers a clear view into Claude Agent SDK usage and performance. It highlights key metrics such as model distribution, error rates, request volumes, and latency trends. Teams can also track detailed records of errors, to better understand adoption patterns and optimize reliability and efficiency.

Dashboard Preview

What This Dashboard Monitors

This dashboard tracks critical performance metrics for your Claude Agent SDK usage using OpenTelemetry to help you:

• Track Reliability: Monitor error rates to identify reliability issues and ensure applications maintain a smooth, dependable experience.
• Analyze Model Adoption: Understand which AI models are being used through Claude Agent SDK to track preferences and measure adoption of different models.
• Monitor Usage Patterns: Observe token consumption and request volume trends over time to spot adoption curves, peak cycles, and unusual spikes.
• Optimize Costs: Track token and cost distribution across models and services to identify optimization opportunities and manage AI spend effectively.
• Ensure Responsiveness: Track P95 latency to surface potential slowdowns, spikes, or regressions and maintain consistent user experience.
• Understand Service Distribution: See which services and programming languages are leveraging Claude Agent SDK across your stack.
• Analyze Tool Usage: Monitor tool call distribution to understand which capabilities are being utilized most frequently.

Metrics Included

Token Usage Metrics

• Total Token Usage (Input & Output): Displays the split between input tokens (user prompts) and output tokens (model responses), showing exactly how much work the system is doing over time.
• Token Usage Over Time: Time series visualization showing token consumption trends to identify adoption patterns, peak cycles, and baseline activity.
• Token Distribution by Model: Breakdown of token consumption across different AI models, helping identify which models consume the most tokens and optimize model selection.

Cost Metrics

• Cost Distribution by Model: Shows the financial cost breakdown across different AI models, enabling cost analysis and helping teams make informed decisions about model selection based on budget constraints.
• Cost Distribution by Service: Visualizes cost allocation across different services in your stack, making it easy to identify which services drive the most AI spend and prioritize optimization efforts.

Performance & Reliability

• Total Error Rate: Tracks the percentage of Claude Agent SDK calls that return errors, providing a quick way to identify reliability issues.
• Request Duration (P95 Over Time): Measures the 95th percentile duration of requests over time to surface potential slowdowns and ensure consistent responsiveness.

Usage Analysis

• Model Distribution: Shows which AI models from various providers are being called through Claude Agent SDK, helping track preferences and measure adoption across different models.
• Requests Over Time: Captures the volume of requests sent to Claude Agent SDK over time, revealing demand patterns and high-traffic windows.
• Services and Languages Using Claude Agent SDK: Breakdown showing where Claude Agent SDK is being adopted across different services and programming languages in your stack.
• Tool Call Distribution: Distribution of which tools are being called most frequently through Claude Agent SDK, helping teams understand feature usage patterns and identify commonly used capabilities.
• Tools: List of tool calls along with how many times each tool was called and average duration of each tool.
• Claude Agent SDK Logs: Comprehensive list of all generated logs for Claude Agent SDK applications associated with the given service name.

Error Tracking

• Error Records: Table logging all recorded errors with clickable records that link to the originating trace for detailed error investigation.