Data handling and privacy

Agent Observability captures generation data that your SDKs export. This article explains what data is collected, where it resides, and how to control retention. Data handling follows Grafana Cloud’s standard data processing agreements.

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:

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 data residency and inference location

Learn where Agent Observability stores your data and how stack region affects LLM judge inference.

Grafana Cloud stores Agent Observability generation data in your tenant within your stack’s region. That data includes conversation and generation payloads, metadata, evaluation scores, and feedback. Grafana-operated LLM judge inference follows three regional patterns.

Stack region	Data storage	Grafana-operated LLM judge inference
EU	Your stack’s region	EU/EEA regional infrastructure
US	Your stack’s region	Americas regional infrastructure
Other regions	Your stack’s region	Might run outside your stack’s region

Agent Observability doesn’t offer country-level geolocation control. If your stack is in the EU, data residency stays within the EU/EEA broadly. Grafana doesn’t guarantee that data is limited to a specific EU country.

Agent Observability doesn’t run your application’s LLM calls. Your agents call the model providers you configure. Those inference locations follow your provider setup and aren’t controlled by Agent Observability.

When you use features that rely on an LLM judge, Agent Observability sends the content being scored to the configured judge provider. That content can include messages, prompts, and tool calls. Grafana-operated judge providers process prompts and responses with zero retention.

Refer to Grafana Cloud regional availability for available regions.

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

LLM judge evaluators send generation content to the configured judge provider for scoring. That content can include messages, prompts, and tool calls. For where that inference runs and how stack region affects residency, refer to Understand data residency and inference location.