Overview

In Ascerta, a Request refers to an API call to a Provider, such as getting a chat completion from Anthropic or generating an image with DALL-E. Requests are the fundamental unit of tracking in the Ascerta system and serve as your statement of record for all GenAI interactions.

The Core of Ascerta Tracking

Requests form the backbone of Ascerta's tracking and analytics system. Each request represents a discrete API call that Ascerta captures, enriches, and analyzes. When Ascerta instruments a request, it records much more than just cost:

• Usage metrics: Tokens, images, or other resource consumption
• Performance data: Response times, latency statistics
• Cost information: Calculated based on the latest Provider pricing
• Success/failure status: Whether the API call completed successfully
• Semantic information: Use cases, user IDs, custom properties
• Limit tracking: How the request affects your defined budgets and quotas

This comprehensive data collection makes requests the central element in Ascerta's monitoring, analytics, and control capabilities.

How Ascerta Works with Requests

Your application communicates directly with the GenAI provider, while Ascerta captures metrics asynchronously:

Your App → GenAI Provider
       ↓
     Ascerta

This approach provides:

• Minimal latency impact
• No direct dependency on Ascerta for request success
• Comprehensive usage tracking
• Support for all Ascerta analytics features