Skip to main content
idapt
HomeAI ModelsPricing
Sign inStart free
All prompts

Prompt library

Draft a design brief that prevents rework

Separating problem from smuggled solution preserves the design exploration a brief exists to enable, and pre-agreed success behavior prevents the taste-war reviews that cause rework. Naming the direction-vs-detail purpose of each checkpoint stops the classic failure of relitigating strategy at the polish stage.

DesignWriteSuggested model: openai/gpt-5.6-luna

Last reviewed July 17, 2026

The prompt
Draft a design brief.

The project: {{project}}
What I know about constraints and context: {{context}}

Sections:
1. The problem, not the solution: what users cannot do or feel today, with the evidence. If my project description already smuggles in a solution, extract it and park it under "one candidate direction".
2. Success definition: how we will know the design worked, as observable behavior or a metric, decided BEFORE concepts exist.
3. Audience and moment: who, and in what state (rushed? anxious? expert?) they meet this design.
4. Constraints, all of them: brand rules, technical limits, deadline, budget, and the political constraint nobody writes down (whose approval actually matters).
5. Scope edges: what is explicitly out of scope, because scope creep in design arrives as "while you are at it".
6. Deliverables and checkpoints: what gets reviewed when, and what kind of feedback each checkpoint is for (direction vs detail).
7. The 3 open questions the designer should push back on before starting.

A good brief is falsifiable: someone could look at the outcome and say it missed.
Run in idaptOpens a new chat with the prompt prefilled. Nothing sends until you press send.

Fill in the variables

VariableWhat it isExample
{{project}}The design work neededredesign the onboarding flow of our mobile app
{{context}}Constraints, deadlines, politics6 weeks, existing design system, CEO cares about step one

Frequently asked

Related prompts

Outline a user flow with its failure pathsAsk critique questions that improve the workOutline a portfolio case study that shows judgment

Ready to get to work?

Free to start. No credit card. Never trained on your data.

Start free
  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Voice Mode
  • Voice HUD
  • Web Search
  • Image Generation
  • Video Generation
  • Audio Generation
  • Transcription
  • Drive
  • Secrets
  • Sharing
  • Workspaces
  • Tasks
  • Memory
  • Agents
  • Subagents
  • Automations
  • Skills
  • Code Execution
  • Computers
  • Computer Use
  • Cloud Computers
  • Local AI
  • AI Gateway
  • API & SDK
  • CLI
  • MCP
  • Tunnels
  • All features →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Learn
  • Free tools
  • Prompts
  • Templates
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)