Documentationbreadcrumb arrow Grafana Cloudbreadcrumb arrow Observe and actbreadcrumb arrow Agent Observabilitybreadcrumb arrow Manage privacy and securitybreadcrumb arrow Understand data handling
Grafana Cloud

Data handling and privacy

Agent Observability captures generation data that your SDKs export. This article explains what data is collected, how it’s stored, and how to control retention.

Understand collected data

Agent Observability stores the generation data your SDK sends, including:

  • Conversation IDs and generation IDs.
  • Model provider and name.
  • System prompts, input messages, and output messages.
  • Tool definitions, tool calls, and tool results.
  • Token usage and timing data.
  • Agent names and computed version hashes.
  • Metadata and tags you attach.
  • Evaluation scores and feedback.

Agent Observability also receives OpenTelemetry metrics and traces from your agents via the collector.

Control your data

You control what data Agent Observability receives by configuring your SDK:

  • Embedding capture is off by default. Enable it only for debugging because it may include sensitive input data.
  • Raw artifacts (full provider request/response) are off by default.
  • Metadata and tags are application-defined — include only what’s useful for observability.
  • System prompts and messages are captured as-is. If your prompts contain sensitive data, consider filtering before export.

Instrument coding agents privately

Agent Observability SDKs can instrument coding agents, and ready-made integrations work with the most popular ones, including Claude Code, Codex, Cursor, GitHub Copilot, OpenCode, and Pi.

By default, integrations capture only metadata: model, token usage, tool names, and timing. Your conversations, prompts, tool calls, and tool results stay local. Sending that content to Agent Observability is an explicit opt-in.

To enable conversation capture for a coding-agent integration, set the content capture mode in ~/.config/agento11y/config.env:

Bash 
AGENTO11Y_CONTENT_CAPTURE_MODE=full

The supported modes are metadata_only (default), no_tool_content, and full. Refer to Instrument coding agents for the integration setup steps.

Understand storage

Generation data is stored in two tiers:

  • Hot storage (MySQL): recent generation metadata and payloads for fast queries.
  • Cold storage (object storage): compacted, compressed payloads kept until the retention period expires.

In Grafana Cloud, data handling follows Grafana Cloud’s standard data processing agreements.

Configure retention

Agent Observability retains conversation and generation data for 30 days by default.

Grafana Cloud customers can contact Grafana Support to request a different retention period.

Understand online evaluation privacy

When using LLM judge evaluators, generation content (messages, prompts, tool calls) is sent to the configured judge provider for scoring. The judge provider processes this data according to its own terms of service. Choose judge providers that meet your organization’s data handling requirements.

Next steps