Observability

Monitor, trace, and debug your agents with built-in integrations for popular observability platforms.

Idun Agent Platform includes built-in observability backed by OpenTelemetry auto-instrumentation. It captures traces, logs, and metrics from your agents with minimal configuration.

You configure observability once in the Manager UI, then attach configurations to any agent. Each configuration stores your provider credentials and settings, and you can reuse it across multiple agents.

Supported providers

How it works

When you attach an observability configuration to an agent, the platform automatically instruments the agent runtime. Depending on the provider, you get:

• Traces showing agent execution flow, LLM calls, and tool invocations
• Latency metrics for each step in the agent graph
• Cost tracking based on token usage
• Error traces with full context for debugging
• Structured logs for centralized log analysis

Observability configurations are saved at the workspace level and can be reused across multiple agents. You only need to set up provider credentials once.

Configuration

Manager UI

1. Browse the provider catalog

   Navigate to Observability in the sidebar. The catalog shows provider cards: Langfuse, Phoenix, LangSmith, GCP Logging, and GCP Trace are active. Datadog APM, AWS X-Ray, Azure Monitor, and Jaeger are planned.

   
2. Add a provider

   Click + on your provider and fill in the credentials.

   
3. Attach to an agent

   Attach the configuration to agents from the agent detail Overview tab.

Config file

Add an observability section to your config.yaml with the provider and its credentials:

config.yaml

observability:
  provider: "langfuse"
  public_key: "pk-lf-..."
  secret_key: "sk-lf-..."
  host: "https://cloud.langfuse.com"

See the provider-specific pages for the full list of fields each provider requires.