PromptJoy

Public prompt detail for browsing before sign in.

Sign inSign up
Back to discovery
Product Design
GPT-4o

UX critique that ends with a concrete action plan

Finds friction in a flow and translates it into prioritized design changes.

Prompt metadata
Enough context to judge fit before you copy the prompt into a real workflow.

Workflow

Product Design

Model fit

GPT-4o

Author

PromptJoy Editorial

Author role

Editorial curation

Origin

PromptJoy curated launch library

Published

Apr 9, 2026

Copy, save, and vote
Copy works on this curated prompt now. Its visible copy count updates on this device, and signed-in users can also save or vote here while the shared library fills in.

Copies the full prompt body so you can use it immediately in your model of choice.

Visible copy count on this device: 402

Current vote signal: +131

Sign in to save or vote on this curated prompt. Your state will stay on this device for your signed-in account while the shared library fills in.

What happens here

Copy keeps the prompt body exact and updates the visible count on this device. Save and vote also work on this curated prompt for signed-in users until the shared public library is live.

Live trust breakdown

Task clarity

78

+18 names the role the model should play

Input contract

48

+24 tells the user what inputs to provide

Output contract

66

+18 defines what the model should return

Guardrails

20

+12 sets quality constraints for the response

Safety

100

+12 does not request secrets or sensitive identifiers

Reusability

44

+12 separates context, output, and rules into readable blocks

Community signal

66

+24 strong positive vote ratio

Remix into your draft

Trust score

61

Vote signal

+131

Saves

111

Copies

402

Trust score breakdown
A rubric-based quality score with visible evidence and improvement opportunities. No LLM API is used to produce these numbers.

Task clarity

Checks whether the prompt clearly names the role, task, and workflow it is meant to support.

78

Evidence

  • +18 names the role the model should play
  • +18 states the job the prompt is meant to do
  • +14 title describes the use case rather than a generic label
  • +10 has task-oriented tags

Improve

  • No obvious improvement flagged.

Input contract

Checks whether the prompt tells the user what context, data, or materials to provide.

48

Evidence

  • +24 tells the user what inputs to provide
  • +14 asks for task-specific context, not just raw text

Improve

  • Separate required context into bullets or fields.
Prompt body
Written by PromptJoy Editorial for product design work on GPT-4o, with attribution preserved on the detail page.
ux
critique
prioritization
Act as a product designer reviewing a flow for usability and conversion.

I will provide screenshots, a description of the flow, the user intent, and the main failure point.

Return:
1. friction points in the current experience
2. why each issue matters for the user and the business
3. a priority-ranked action list
4. revised interface copy where wording is a problem
5. one thing to keep because it is already working
Public detail stays open, but save and vote still require sign-in
This page stays public for browsing and copying. When you sign in, the save and vote controls on this curated prompt stay available on this device without moving the public prompt library behind auth.
Create account to saveLog in to saveSign up to remixLog in to remix

Output contract

Rewards prompts that define the shape, order, and priority of the answer.

66

Evidence

  • +18 defines what the model should return
  • +22 uses a multi-part output format
  • +14 specifies how the answer should be organized

Improve

  • No obvious improvement flagged.

Guardrails

Looks for constraints that reduce generic answers, unsupported assumptions, and avoidable cleanup.

20

Evidence

  • +12 sets quality constraints for the response

Improve

  • Add rules that prevent generic or unwanted output.
  • Tell the model how to handle missing evidence or uncertainty.

Safety

Checks for sensitive-data exposure, harmful misuse language, and whether the prompt sets safe-use boundaries.

100

Evidence

  • +12 does not request secrets or sensitive identifiers
  • +10 avoids obvious harmful misuse instructions
  • +8 avoids jailbreak or policy-bypass wording

Improve

  • Add a short safety boundary for sensitive data, authorization, or privacy.

Reusability

Checks whether the prompt is portable, readable, and discoverable enough to reuse.

44

Evidence

  • +12 separates context, output, and rules into readable blocks
  • +10 has enough metadata for discovery and reuse
  • +8 does not depend on private one-off context

Improve

  • Aim for a reusable prompt between roughly 80 and 260 words.

Community signal

Uses copy, save, and vote behavior cautiously, with low confidence until enough activity exists.

66

Evidence

  • +24 strong positive vote ratio
  • +13 saved 111 times
  • +16 copied 402 times
  • +13 based on 660 total interactions

Improve

  • No obvious improvement flagged.