Introduction
Updated on Jun 16, 2026
Progress® Observability Platform gives you full visibility into your AI agents and LLM-powered applications. It captures traces, measures costs, and evaluates output quality — so you can release AI features with confidence.
Key Features
With Progress Observability you can:
- Monitor every LLM call, tool invocation, and agent workflow in real time
- Track token usage and costs broken down by model, provider, and time period
- Evaluate AI output quality using LLM-as-a-Judge evaluation tasks
- Tag and filter observations to isolate specific customers, experiments, or environments
- Instrument your code in minutes using SDKs for Python and .NET
How It Works
The platform has three layers:
- SDKs—Lightweight libraries you add to your application code. Each SDK automatically captures OpenTelemetry traces for supported LLM providers and frameworks. You can also add manual instrumentation with decorators or custom spans.
- Collector—Purpose-built OpenTelemetry Collector that receives trace data from the SDKs, validates API keys, enriches spans with cost calculations and user attribution, and stores everything in the backend.
- Platform—Web dashboard where you view observations, analyze costs, create evaluation tasks, manage API keys, and configure LLM integrations.