Turn the feedback you received into the plan you'll actually act on.
Feedback Triage scaffolds the cognitive work of processing supervisor emails, peer review, committee notes, and editor decision letters. You paste the feedback, highlight the parts that matter, and the tool turns each one into a structured item with type, severity, underlying concern and a specific action. It exports a response letter or revision plan when you're done.
Your feedback stays in your browser. No AI reads it; nothing is uploaded.
Feedback arrives faster than you can act on it
Reviewer 2 wrote three pages. Your supervisor's email has seven points buried in two paragraphs. The committee gave you a dozen comments at the end of a two-hour meeting. Without structure, all of it blurs into one undifferentiated lump — and you address the easy parts while the consequential ones quietly slip.
- Surface complaint vs. underlying concern. "The methods are unclear" rarely means only "the writing is unclear." Reading critique well is a skill; the gap is where revision-and-resubmit cycles fail.
- Severity collapse. Treating everything as equally important is the same as sorting nothing — and "important" is the silent default when nobody forces you to pick.
- No action conversion. "I read the comment" and "I have a specific action with success criteria" are very different states. The gap between them is rarely closed.
A thinking tool, not a decoder
How it works
Paste the feedback
Pick one of eight source types — supervisor email, journal peer review, conference review, committee notes, editor decision letter, grant reviewer comments, reading group, or other — and paste the text.
Highlight & triage
Select any portion of the source text. It becomes a feedback item — verbatim text, type, severity, underlying concern, specific action, optional success criteria, effort, status, and a private note that's never exported.
Export the right document
Plain action list (free for everyone), a Response-to-Reviewers letter for journal submissions, a Revision action plan for supervisor / committee / editor / grant feedback, plain text, and PDF. Bracketed prompts mark where your prose goes.
What's inside
Highlight & extract
The cognitive forcing function. By forcing you to physically select the text you're addressing, the tool prevents feedback being processed as one undifferentiated blob — and source-text coverage becomes visible at a glance.
Severity that actually sorts
Critical / Important / Cosmetic — calibrated against consequence (what happens if I don't address this?), not anxiety. With colour-coded source highlights and a built-in calibration guide.
Underlying-concern field
A required field per item: what is this person actually worried about, beneath the surface complaint? Four techniques for excavating it ship inside the reference library.
Response & revision exports
One-click Response-to-Reviewers letter (journal / conference) or Revision action plan memo (supervisor / committee / editor / grant). Plus plain text and PDF. Bracketed prompts mark where your authored prose goes.
Five reference frameworks
Short authored essays on reading peer review, decoding supervisor signal, calibrating severity, excavating underlying concerns, and declining feedback professionally. Static, on-device, no AI.
No AI, on purpose
Nothing here classifies your feedback, suggests severities, drafts response paragraphs, or summarises. You do the thinking; the tool provides the structure and the exports.
Privacy & Trust
- Your feedback never leaves your machine. Everything you paste, highlight, classify, or note — including the private internal note on every item — lives in
chrome.storage.localon your device. - No AI runtime, no telemetry, no analytics, no account. The extension does not read any web page and runs no inference on your content.
- One optional network call, only if you ask for it. If you enter an email and click Subscribe for product updates, only that email address is sent to GradSummit's sign-up service — never any pasted feedback, items, concerns, actions, or notes.
- Internal notes are never exported. The private "internal note" field on every feedback item is excluded from every export by design — verified by an automated test.
It is a thinking tool for processing critique — not an AI that decodes reviewer comments for you. Read the full privacy policy.
Built by Dr. Rafiq Muhammad, PhD — author of the Mastering Research book series.
Pricing
Every feature, for everyone — no subscription, no tiers, no account.
All eight source types, the highlight-and-extract flow, every export format, and the full reference framework library are unlocked.
Email is entirely optional and opt-in — leave it blank forever, or add it to hear about occasional updates.
Frequently asked questions
Does an AI decode my reviewer comments?
No — and deliberately so. There is no AI runtime anywhere in this tool. It does not classify the type, suggest severity, infer the underlying concern, draft your response paragraphs, or summarise anything. You do the decoding; the tool provides the structure, the prompts, and the exports. The meta-skill of reading critique well is exactly what the product exists to develop — AI doing it for you would defeat it.
Is my pasted feedback uploaded anywhere?
No. Every piece of feedback you paste, every item you extract, every classification you make, every interpretation, every action plan, and every private note stays in chrome.storage.local on your device. The only thing the extension can send to GradSummit is your email address — and only if you explicitly opt in to product updates and click Subscribe. No feedback content is ever transmitted. See the full privacy policy.
What about reviewer confidentiality?
Many journals' reviewer agreements prohibit redistribution of reviewer comments. Pasting comments into Feedback Triage is not a transfer to a third party — the content remains in your browser, on your device. We make zero outbound calls with any of it. The legal interpretation of any specific journal's policy is between you and the journal; the tool provides a local workspace.
What does "underlying concern" mean?
The verbatim text is the surface complaint — what the reviewer or supervisor literally wrote. The underlying concern is what they're actually worried about beneath it. "The methods are unclear" might mean (a) the writing is unclear, (b) the method itself is wrong, or (c) an assumption needs to be stated. The action that follows from each is completely different. The tool requires you to articulate the underlying concern as a separate field, because the gap between verbatim and concern is where most revisions go off the rails.
What are the five reference frameworks?
Five short authored essays shipped inside the extension: How to read peer review like a reviewer, Supervisor signal-to-noise, Severity calibration guide, Underlying concern excavation, and Decided not to address — when and how. Total ~4,500 words. Static, on-device, no AI. They teach the meta-skill explicitly.
How much does it cost?
It's free, with no subscription and no paid tiers. Every export, every source type, every framework, and the full item card with all optional fields is available to everyone. There's nothing to buy and no account to create.
Can I get my data out?
Yes. Settings has a one-click backup export to JSON, and every session exports as Markdown, plain text, or PDF. One click in settings clears everything from your device. Uninstalling the extension also clears chrome.storage.local.
What if I find a bug?
Email support@gradsummit.com — replies go to a real human (the developer).