Observe and export AI usage
Last validated:
Aperture captures telemetry for every LLM request, including token counts, model names, session grouping, and tool use data. You can access this data through the Aperture dashboard or export it for integration with external monitoring and compliance tools. For more information on what Aperture captures and how session tracking works, refer to How Aperture works.
You can also connect Aperture with external services such as log aggregators and authorization engines. Refer to Integrate with external tools for available integrations.
Connector observability. MCP tool calls that an LLM initiates appear in captures as part of the LLM request and response bodies (the tool_use and tool_result content blocks). You can view these in the Logs page like any other request detail.
HTTP connector proxy requests (traffic to /v1/connectors/{id}/) do not appear in the dashboard or in captures. These requests are logged to the Aperture server log only. The server log records the user (login_name), connector ID, method, path, and response status for each proxied request. This is a current limitation. Refer to Connectors for more information on configuring MCP and HTTP connectors.
Aperture dashboard reference
Reference for the pages every Aperture user can access in the dashboard, organized by sidebar group, including My Dashboard, Agent Config, Models, Connectors, Chat, and Usage Overview.
Aperture admin dashboard reference
Reference for admin-only Aperture dashboard pages, grouped by sidebar section, including Security, Administration, Usage & Adoption, Integrations, and API Docs.
Export usage data to S3
Configure Aperture to export LLM usage data to an Amazon S3 bucket for compliance, analysis, and long-term retention.