Logs
Logs contain the inputs and outputs of each time a Function File is called.
Logs in Humanloop are records of each execution of a Function File (Prompt, Agent, Tool, Evaluator, or Flow). They capture the complete context of the execution, including inputs, output, and metadata like which Version was used.
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.
