Skip to main content

​
Overview

The Anthropic integration in the Engineering Metrics Dashboard allows organizations to connect their Anthropic API usage data to the platform and analyze LLM usage metrics, user activity, model consumption, and business impact insights. This integration is part of the LLM Metrics module.
Important:
  • Only one Anthropic admin key can be configured per organization.
  • Multiple Anthropic connections are not supported.
  • The integration requires a valid admin key with the necessary permissions.

​
Prerequisites

Before setting up the integration, ensure you have:
  • Access to the Engineering Metrics Dashboard
  • An Anthropic admin API key
  • Required permissions to configure integrations and projects

​
Step 1: Navigate to LLM Integrations

  1. Open the Engineering Metrics Dashboard.
  2. Navigate to the Integrations section.
  3. Select LLM Metrics Integrations.
  4. Choose Anthropic from the available providers.

​
Step 2: Create a New Anthropic Connection

  1. Click New Connection.
  2. Enter a unique Connection Name.
  3. Paste the Anthropic Admin Key in the provided field.
Note: The admin key is typically provided by the organization or company administrator to enable AI access and usage tracking.

​
Step 3: Test the Connection

  1. Click Test Connection.
  2. Wait for the validation process to complete.

​
Expected Result

If the admin key is valid and has the required permissions, the connection test will succeed. If the test fails:
  • Verify the admin key.
  • Confirm permissions.
  • Retry the connection test.

​
Step 4: Save the Connection

After a successful connection test:
  1. Click Save Connection.
The Anthropic connection will now appear in the available connections list.
Important: Only one Anthropic connection can exist within the same organization.

​
Step 5: Create an LLM Metrics Project

After creating the Anthropic connection:
  1. Navigate to the Projects section.
  2. Click Add Project.
  3. Select LLM Metrics as the project type.
  4. Enter the required project details.

​
Step 6: Select the Anthropic Data Source

  1. In the Data Source section, select Anthropic.
  2. Choose the saved Anthropic admin key connection.
  3. Confirm the selected connection.
Once confirmed, the data scope will automatically be added to the project.

​
Step 7: Configure Sync Behavior

The Sync Behavior section controls how and when data is collected.

​
Data Collection Range

Select the time range for which data should be collected. Examples
  • Last 10 Days
  • Last 30 Days
  • Last 6 Months
  • Last 1 Year

​
Sync Frequency

Choose how frequently the platform should collect data. Available options include:
  • Daily
  • Weekly
  • Monthly
  • Custom Schedule
Example 
Every 2 Hours

​
Schedule Status Options

The integration provides the following scheduling controls.

​
Active

The synchronization schedule runs automatically based on the configured frequency.

​
Inactive

The synchronization schedule is disabled and will not run automatically.

​
Pause

Temporarily pauses the synchronization schedule for the connection.

​
Scheduled Time

Users can configure a custom execution time for scheduled synchronization jobs.

​
Step 8: Complete Project Setup

  1. Review the configuration.
  2. Click Complete Setup.
The Anthropic integration project is now configured successfully.

​
Step 9: Run Initial Synchronization

  1. Open the configured project.
  2. Click Run Sync Now.
This action:
  • Collects the latest Anthropic usage data
  • Processes the collected metrics
  • Updates the dashboard with the latest information

​
Understanding Sync Operations

​
Run Sync Now

The Run Sync Now option fetches the latest available data from Anthropic. Whenever new usage data becomes available, running sync will update the platform accordingly.

​
Retransform Data

Retransform Data does not fetch new data. Instead, it reprocesses already collected data to:
  • Standardize inconsistent data
  • Resolve formatting mismatches
  • Recalculate processed metrics
In most cases, running a normal synchronization also triggers the required transformation process automatically.

​
Monitoring Integration Status

The Status section displays:
  • Synchronization history
  • Task execution details
  • Success and failure status
  • Processing duration
  • Completed operations
This helps users monitor the health and activity of the integration.

​
Viewing Anthropic Metrics

After synchronization completes:
  1. Navigate to the LLM Metrics Dashboard.
  2. Search for the configured Anthropic project.
  3. Open the project to view metrics and analytics.
The dashboard provides visibility into:
  • User activity
  • API usage
  • Model consumption
  • Organization-level AI adoption
  • Usage trends

​
Available Insights

​
User-Level Usage Data

The dashboard displays usage information for users consuming Anthropic APIs within the organization.

​
API Key and Sub-Key Tracking

Projects may contain multiple API keys and sub-keys. The platform tracks usage distribution across:
  • Projects
  • Sub-keys
  • Individual API keys

​
Model Usage Analytics

Users can monitor which Anthropic models are being used across the organization. Examples may include:
  • Claude Models
  • Different Model Versions
  • Usage Distribution Across Teams

​
ROI and Business Impact Summary

The ROI and Business Impact section provides estimates related to:
  • Development time savings
  • Productivity improvements
  • Operational efficiency
  • Estimated cost optimization
These values are calculated using predefined internal metrics and usage patterns.

​
Executive Summary

The Executive Summary section provides a higher-level overview of AI adoption and organizational impact.
Note: Some Executive Summary features may still be under active development depending on the deployment version.

​
Troubleshooting

​
Connection Test Failed

Possible Causes
  • Invalid admin key
  • Missing permissions
  • Expired credentials
Recommended Actions
  • Verify the admin key
  • Confirm permissions with the administrator
  • Retry the connection test

​
No Data Appearing After Sync

Possible Causes
  • Initial synchronization still running
  • Incorrect project configuration
  • Schedule disabled
Recommended Actions
  • Check the Status section
  • Re-run synchronization manually
  • Verify sync schedule settings

​
Schedule Not Running

Possible Causes
  • Schedule set to Inactive
  • Schedule currently Paused
Recommended Actions
  • Set the schedule status to Active
  • Verify the configured sync frequency and execution time

​
Best Practices

  • Use clear and unique connection names
  • Periodically verify admin key validity
  • Configure regular synchronization schedules
  • Monitor synchronization status regularly
  • Review ROI and usage metrics periodically for adoption insights

​
Summary

The Anthropic integration enables organizations to centralize and monitor LLM usage data directly within the Engineering Metrics Dashboard. By configuring the admin key connection, scheduling synchronization, and monitoring usage analytics, teams can gain visibility into:
  • AI adoption
  • Model usage
  • User activity
  • Business impact across the organization