> This page is for version v5.0 (default).
> For other versions, use one of these documentation indexes:
> - v5.0 (default): https://humanloop.com/docs/v5/llms.txt
> - v4.0: https://humanloop.com/docs/v4/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://humanloop.com/docs/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://humanloop.com/docs/_mcp/server.

> Logs contain the inputs and output of each time a Function Files is called.

Logs in Humanloop are records of each execution of a [Function File](/docs/explanation/files#function-files) (*Prompt*, *Agent*, *Tool*, *Evaluator*, or *Flow*). They capture the complete context of the execution, including `inputs`, `output`, and metadata like which [Version](/docs/explanation/files#files-are-version-controlled) was used.

## External logging

When you are not using Humanloop to run Prompts (or other Function Files), but use your own infrastructure — for instance in a production setting — you can still collect and store the Logs on Humanloop. This enables you to collect interesting cases and lets you leverage Humanloop's monitoring and evaluation capabilities.

Monitoring Evaluators run every time a Log is patched. If the Log is part of a trace, the Evaluators re-run and the stats of the Log are updated.

![](/docs/_fern-img/45c4ae9729af643c18daab4d46cceb2d83d6f7b3af057ed7b373d28b412c5dd2.webp)