Files
docker-agent/examples/eval
David Gageot 20b25b3da9 remove shebang lines from example configs
Remove the leading '#!/usr/bin/env docker agent run' shebang and
following blank line from all example YAML and HCL files, as the
config format is now self-documenting.
2026-05-20 16:26:18 +02:00
..
2025-11-20 12:55:22 +01:00
2025-11-20 12:55:22 +01:00

Simple eval

This is a simple agent that has two eval sessions saved in the evals directory, to run the eval you can:

$ docker agent eval demo.yaml ./evals

This will output something like

Eval file: 41b179a2-ed19-4ae2-a45d-95775aaa90f7
Tool trajectory score: 1.000000
Rouge-1 score: 0.521739
Eval file: 5d83e247-061f-4462-9b2d-240facde45f3
Tool trajectory score: 1.000000
Rouge-1 score: 0.829268