# Agent Evaluation Report

## Summary

## Decision
GO / NO-GO / CONDITIONAL

## Version Matrix
- Agent:
- Model:
- Prompt:
- Tools:
- Dataset:
- Evaluators:
- Environment:

## Dataset
- Cases:
- Categories:
- Critical:
- Epochs:

## Scorecard

## Reliability

## Safety

## Efficiency

## Regression

## Failure Analysis

## Known Limitations

## Evidence
- Raw traces:
- Per-sample results:
- Artifacts:
