Five-axis rubric for grading recorded agent runs, with anchors at each score level and three scored example traces used as the calibration set.
-
Updated
Jun 2, 2026
#
trajectory-scoring
Here are 2 public repositories matching this topic...
Pure deterministic AI agent trajectory evaluation engine — zero judge-LLM cost, zero non-determinism, zero API latency.
python ai-agents mlops llm-evaluation llm-testing agent-evaluation deterministic-eval trajectory-scoring fixtura ci-cd-gating
-
Updated
Jul 26, 2026 - Python
Improve this page
Add a description, image, and links to the trajectory-scoring topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the trajectory-scoring topic, visit your repo's landing page and select "manage topics."