Return judgments, not a replacement project
Review the evidence. Send the assessment back.
The sender exports a review packet from Test Bench. Open it here, assess the criteria, and download a return file. The sender previews it before applying it; existing judgments are archived, not silently replaced.
No account, model call, server upload or browser storage. Work stays in this tab until you download it. Packets contain private source, exact prompts, responses, model/date labels, checks and the current saved review context. They are not redacted, signed, authenticated or blinded. This page cannot verify who reviewed a file or whether a model ran.
Workflow, matching rules and worked return example · Sender: export or import a review
The local review editor requires JavaScript. The workflow guide and examples remain readable without it.
Open a packet, not a project
Review packet JSON (UTF-8, up to 10 MB)
Reviewer label (self-reported, not verified; up to 80 characters)
Download review packet / return file
Clear this packet
No file opened. Nothing is saved automatically.
You may save unfinished ratings and notes. The sender imports only rows with a completed accept/reject decision; undecided rows, including their partial notes, are skipped. A completed decision requires every criterion assessed; acceptance requires all to pass. Automatic checks are separate and never accept an answer for you.
Recording to review
Source input
Exact recorded prompt
Raw recorded response
Current automatic checks and full rules
Recording-time rules (may differ from current checks)
Existing saved review context (not blinded)
Assess each criterion
Your explanation (up to 1,800 characters)
Overall decision
Not decided / skip on return
Accept under these criteria
Reject under these criteria
Changing a criterion resets the overall decision. A passing format check is not proof of meaning, source fidelity or reliability. Notes and reviewer labels remain editable and unsigned. Download before leaving; no email or return is sent automatically.