Multi-Turn Conversation and Prompts for Peer Review Organization: Draft Materials and Hand Over Responsibilities

Peer Review: review conversation for material handover. Compare the source records, required inputs and downstream results before handing the task over.

What this category's data looks like

This page is intended for peer review organizations, and the materials cover three categories: review invitations, expert review comments, and author revision notes. Review invitations are drafted by editors and include the manuscript title, submission date, expert name, and response deadline; expert review comments are submitted by reviewers and include the review conclusion, itemized comments, signature, and submission date; author revision notes are written by authors and include point-by-point responses, revision locations, version number, and receipt. The material sources are manuscript system exports and archived correspondence emails, and the update cadence rolls forward with the three nodes of submission for review, return from review, and revision. When these three categories of materials enter the multi-turn dialogue and prompt feature, the review invitation serves as the task starting point and field baseline, the expert review comments serve as the basis for judgment, and the author revision notes serve as the response draft. Based on this, the model drafts materials that can be issued and handover records; once the fields are complete, the responsible parties are clear, and the version and date are consistent, they are handed to the next stage for sign-off.

Configuration and implementation checks

This step is executed by the memory turns and prompt configuration in the application settings, and the output references the historical message range and answer constraints. The materials that can be issued and the handover records are then completed by the model. The memory turns control how many previous dialogue turns can be referenced at most when answering; if the value is too small, the preceding text cannot be used, and if the value is too large, irrelevant content is brought in and consumption increases.

ObjectCheckVerification action
Review invitationThe fields include manuscript title, submission date, expert name, and response deadline, and are consistent with the title and date in the expert review commentsCheck the memory turns value in the application settings, run a trial with two consecutive questions, check whether the second turn picks up the references from the first turn, and verify the messages range corresponding to chatId
Expert review commentsThe fields include review conclusion, itemized comments, signature, and submission date, and match the expert names and count in the review invitationCompare the usage records of two runs, check the consumption change after adjusting the turns, and verify the version number and date recorded in variables
Author revision notesThe fields include point-by-point responses, revision locations, version number, and receipt, and are consistent with the item numbers and count in the expert review commentsDraft one according to the template and complete one handover, check whether it is blocked when the signature or receipt is missing, and verify whether historical messages in messages are mistakenly treated as opening messages

Three common errors

  • Symptom: The same expert name is written differently in the review invitation and the expert review comments. Cause: The two materials are entered separately, and no name field alignment or receipt verification was performed.
  • Symptom: The version number of the author revision notes does not match the submission date of the expert review comments. Cause: The version was not synchronized after revision, the old draft overwrote the new draft, and there is no sign-off record.
  • Symptom: When the second question uses a reference, the answer does not address the question, and the response becomes slower with increased consumption. Cause: The memory turns are too large and bring in irrelevant history, or the opening message is treated as preceding text and participates in the answer.

How to verify the setup

This feature acceptance: ask two consecutive follow-up questions, see whether the second question picks up the references from the first question, and verify the records where the three identifiers chatId, messages, and variables are located.

Business test: draft one according to the template and complete one handover, and see whether missing items are blocked.

  • Check the current memory turns value in the application settings and match it with the preceding text range required by the question.
  • Compare the usage records of two runs and confirm that consumption changes accordingly after adjusting the turns.