Give your reviewers a head start.

AIPR is an AI assistant for peer reviewers. As an editor, you can provide it for your team. Reviewers stay in control of every decision; AIPR drafts a calibrated first read so they can spend their time on the judgment calls.

How a pilot works

  1. Send us your queue

    You hand off a batch of manuscripts via SFTP or a signed link. We hold them only for the duration of the pilot.

  2. AI first read

    Each paper gets a calibrated first read: scores, citation audit, flagged issues. Same pipeline reviewers already trust on the public site.

  3. Your reviewers take it from there

    Reviewers receive the AI's draft alongside the paper, ready to edit, override, or discard. Their final review is what reaches the author.

What your reviewers receive

Download a redacted sample to see what reaches a reviewer: the AI's draft review per paper, scoring rationale, and a summary CSV for your editorial team to track turnaround.

Request the sample bundle

Available on request — costa [at] aipr.pub.

What happens to your manuscripts

We never use your submitted content to train a model, and neither do the providers we route to. Manuscript content is used only to generate the review, and your institution can run AIPR on our managed keys, through your own cloud tenancy, or fully self-hosted. Retention and processing terms are set out in the DPA, which is signable as-is.

Read the DPASignable copy available on request. Email costa [at] aipr.pub.

Pilot pricing

Pilot pricing tailored to volume. First 6-week pilot is no-cost. Book a call to discuss your cohort.

Talk to us

Walk through what your reviewers need, your queue volume, and what the bundle should contain. No prep required.

Email to book a call

Or write to costa [at] aipr.pub.

Data and security

A short summary of how AIPR handles manuscripts, model access, and audit logging during a pilot. Pairs with the DPA for your security review.

Read the data security overviewPDF summary available on request. Email costa [at] aipr.pub.

  • We never use your submitted content to train a model. Neither do the model providers we route to. AIPR runs under standard commercial API terms, which contractually exclude your prompts and documents from any training or fine-tuning. This holds for every reviewer, every manuscript, on every tier.

  • All connections use TLS 1.2 or newer. Database backups are encrypted at rest before upload to object storage. Passwords are stored as bcrypt hashes. Sessions use HMAC-signed, HttpOnly/Secure cookies with SameSite=Lax.

  • Anonymous uploads (no account attached) are deleted after 7 days. Account-attached papers and reviews are kept for as long as the account is active. Deleting the account removes the associated personal data within 30 days. The model provider may retain a request for around 30 days for abuse monitoring. On accounts where zero data retention is enabled, that window is removed and content is dropped immediately after the response.

  • You can request a copy of your data, an export of your reviews, an account deletion, or a takedown of a review you authored, by emailing [email protected]. We respond within five working days. Deletions complete within 30 days.

  • Encrypted backups follow a tiered retention of 7 daily / 4 weekly / 3 monthly snapshots and are tested on a recurring restore cadence.

  • Standard hosted (available): AIPR runs on our managed keys under the no-training terms. This is the default and needs nothing from your side. Bring-your-own model endpoint (rolling out): Your organization supplies its own OpenAI or Azure token. LLM calls route to your endpoint, and manuscripts remain in aipr's encrypted store. Full on-premise deployment (available on request): AIPR runs inside your own environment as a separate engagement, so review content never leaves your boundary. Across every option, additional model providers supported on request.