FF/Resources

Free Resource

Agent Evaluation Suite

A ready-made test suite for an agent headed to production: sixteen weighted test cases, scored for you automatically.

Get the download

Tell us where to send it. We'll email you the link straight away.

Protected by reCAPTCHA — Google Privacy / Terms.

Define your tests once. The workbook computes per-category scores and an overall pass rate from the results you record. The Sample (AcmeCorp) tab shows a completed eval with annotated failure modes.

Download →

Sample (AcmeCorp) tab inside the workbook shows a completed example with the formulas firing on realistic data.