# Diagnose recent Sessions

> Use a disclosed Historical Job to find recurring failures before building a promotion Dataset.

---

LLMS index: [llms.txt](/harbor-self-evolving/llms.txt)

---

Historical evaluation lowers the cold-start cost. Preview bounded Session metadata, inspect what may reach the Judge, then confirm a non-promotion Job.

## You do {#you-do}

Select recent completed Sessions that reflect the failure, review exclusions and consent to the disclosed Judge/data boundary.

## Harbor records {#harbor-records}

A private redacted Batch, frozen Judge identity, one Trial per Session, criterion applicability, coverage and reason codes.

## This does not prove {#does-not-prove}

Historical scores are not comparable Candidate regression evidence and never go through Promotion Gate.