Does it change the design?

No. It never edits artwork, contacts reviewers or marks a request approved. The approver settles the open decisions, and you make the changes yourself.

What happens with comments that contradict each other?

It keeps them as separate items and lists them as a conflict for the approver. It never merges opposite requests, and it doesn’t dismiss feedback as personal taste.

Where does it find the feedback?

In ChatGPT Work and Claude you paste the comments, and in Claude you can attach the brief and an export of the design. Grok Bot, a ChatGPT dot and Gemini search Gmail for the project’s feedback from the last 30 days and find the brief in a Google Drive folder.

Can it tell whether the design meets accessibility rules?

No. It works from written feedback, so it doesn’t judge a design it can’t see or work out contrast from a description. An attached export only helps it match comments to elements.

Which plan do I need?

Claude works on any plan, including Free. ChatGPT Work on the web needs Plus, Pro, Business, Enterprise or Edu, and a ChatGPT dot needs ChatGPT Pro (Business Premium and Enterprise as dots roll out). Gemini needs Google AI Pro or Ultra, and Grok Bot an X Subscription, a Cursor plan or SuperGrok.

Design Feedback Sorter

Turn design feedback into a revision list

Design Feedback Sorter is an AI agent you set up in the ChatGPT, Claude, Gemini or Grok you already use. It sorts a round of design feedback into one revision list against the approved brief, separates corrections from new scope, keeps opposite requests apart and drafts the questions for whoever approves the work.

Pick your AI for the steps and the prompt

About each AI:ChatGPT WorkClaude appGrok BotOpenAI DotsGemini Task

Checked 29 Oct 2026. Not run by JuicyAgents yet. Written from each AI’s official docs; the example is illustrative.

Design Feedback Sorter · reply in the chat

Poster-v3, 1 correction and 3 questions for Noor

CorrectThe printed date to 20 October, as the brief says
Opposite requestsKept apart, unresolved
FlagThe landscape banner as new scope
AskWhat dynamic means
NoorDecides before the designer changes Poster-v3

Illustrative example: fictional Poster-v3, an approved blue A4 poster, with five comments, approver Noor and no new format approved.

How it works

What it does for you, and what it leaves to you.

Designers receive vague, changing or conflicting comments after a design direction was agreed. They need to separate corrections from new requests before doing another revision.

Interpret differently worded comments and preserve their source references in one review packet. Whether that saves more effort than it adds is unmeasured. For a few clear comments, one shared document and one approver are simpler. A review policy is still needed; an assistant cannot make stakeholders agree or enforce a contract. With Grok Bot, OpenAI Dots or Gemini, name the project instead: the agent collects its feedback emails from Gmail and the approved brief from a Google Drive folder.

You stay in charge. The designer checks that every comment is represented fairly. The named approver resolves conflicting goals and scope; the designer performs the changes.

You get

A traceable revision list, conflict list and draft clarification message

It never

Edit artwork or mark a request approved
Email reviewers or send the draft message
Merge opposite requests into one change
Quote extra fees or decide what the contract covers

The revision list it prepares

The example above, in words.

Correct the printed date to 20 October, as the brief says. Keep the two opposite requests apart, unresolved. Flag the landscape banner as new scope. Ask what dynamic means. Noor decides before the designer changes Poster-v3.

Settings

The setup prompt starts with the defaults, marked here.

Project briefs folder

Type the Google Drive folder that holds approved project briefs, with the project name in each file name. This site does not read your Drive.

Default: Project briefs

Revision list order

Choose how the assistant organizes the result; evidence and review rules stay the same.

By design element (default)
By decision needed

Your working rules

Approval authority, agreed deliverables and revision limits. Do not infer authority from seniority or tone.

Optional. Empty unless you fill it in.

Questions people ask

Does it change the design?: No. It never edits artwork, contacts reviewers or marks a request approved. The approver settles the open decisions, and you make the changes yourself.
What happens with comments that contradict each other?: It keeps them as separate items and lists them as a conflict for the approver. It never merges opposite requests, and it doesn’t dismiss feedback as personal taste.
Where does it find the feedback?: In ChatGPT Work and Claude you paste the comments, and in Claude you can attach the brief and an export of the design. Grok Bot, a ChatGPT dot and Gemini search Gmail for the project’s feedback from the last 30 days and find the brief in a Google Drive folder.
Can it tell whether the design meets accessibility rules?: No. It works from written feedback, so it doesn’t judge a design it can’t see or work out contrast from a description. An attached export only helps it match comments to elements.
Which plan do I need?: Claude works on any plan, including Free. ChatGPT Work on the web needs Plus, Pro, Business, Enterprise or Edu, and a ChatGPT dot needs ChatGPT Pro (Business Premium and Enterprise as dots roll out). Gemini needs Google AI Pro or Ultra, and Grok Bot an X Subscription, a Cursor plan or SuperGrok.

Have us set it up

Rather not set it up yourself?

We set up Design Feedback Sorter in your own accounts and the AI you already pay for, test it on your real work, and hand it over with a short walkthrough.

From $299

Runs in your accounts; you own everything
Tested before handover
Money back if we can’t make it work

Request a setup