Write a Prompt From a Rough Idea
Turn a one-line idea of what you want into a full, ready-to-paste structured prompt.
Direct answer
Start from what you want in plain words, then expand it into a structured prompt with a role, context, task, constraints, and output format. Use the optimizer when you do not yet have a prompt to critique — it rewrites the idea into something ready to paste into ChatGPT, Claude, or Gemini.
Open the Prompt OptimizerWhen to use this
- You know what you want but have not written a prompt yet.
- Your first-draft prompt gets vague or generic answers.
- You want a ready-to-paste prompt, not a critique.
Steps
- Write your goal in one plain sentence.
- Name who the answer is for and any must-have constraints.
- Run the optimizer to expand it into role, context, task, and format.
- Read the structured prompt and adjust specifics.
- Paste it into your model and iterate on the output.
Example
help me write cold emails for my SaaS
You are a B2B copywriter. Context: I sell a SaaS that automates invoice reconciliation for finance teams. Task: Write a 90-word cold email. Constraints: One clear value prop, one CTA, no buzzwords, friendly but direct. Output format: Subject line, then the email body.
Common mistakes
- Do not stop at the idea; an unstructured idea gives unstructured output.
- Add the audience and constraints, or the optimizer has to guess them.
- If you already have a working prompt, review it instead of regenerating from scratch.
FAQ
- How do I write a prompt if I don't have one yet?
- Describe your goal in one sentence and let the optimizer expand it into a structured prompt with role, context, task, constraints, and output format.
- Should I use the optimizer or the reviewer?
- Use the optimizer when you have only a rough idea and want a ready-to-paste prompt. Use the reviewer when you already have a prompt and want targeted critique.
- Which models does the output work with?
- The structured prompt works with ChatGPT, Claude, Gemini, and most assistants, since it relies on clear role, task, and format rather than model-specific tricks.
Related prompt guides
Related Prompt Optimizer guides
How to Structure a Prompt (Template)
The building blocks of a strong prompt — role, context, task, constraints, output format, and examples — with a reusable template.
Few-Shot Prompting: Add Examples to Your Prompt
Show the model one to three input-output examples so it copies the pattern you want.
Chain-of-Thought Prompting: Ask for Step-by-Step Reasoning
Prompt the model to reason step by step to improve accuracy on multi-step math, logic, and planning tasks.
Role and Persona Prompting (Act As)
Assign the model a role or persona to control tone, depth, and vocabulary in its answers.
Control the AI Output Format (JSON, Tables, Lists)
Get consistent, parseable output by specifying the exact format, fields, and what to exclude.
Desk gear for long writing sessions
A few things that help if you write docs, tickets, and specs on a laptop all day.
Anker 5-in-1 USB-C Hub
One cable turns a laptop into a desk setup. Drives a 4K display, charges at up to 85W, and adds three data ports.
- 4K HDMI output
- 85W max power delivery
- 1x USB-C + 2x USB-A, 5Gbps each
- MacBook Pro, MacBook Air, Dell
Dell 27" S2725QC 4K
The monitor I write and review documents on. 163 PPI keeps small text sharp, and USB-C carries video and power on one cable.
- 3840x2160 IPS, 163 PPI
- 120Hz, 4ms, FreeSync Premium
- 99% sRGB
- USB-C, HDMI, DisplayPort
Apple MacBook Neo 13" (A18 Pro)
The cheapest way into an Apple-silicon machine that runs local models. Fanless, and the Liquid Retina panel holds small text at a full day of reading.
- A18 Pro chip, built for Apple Intelligence
- 8GB unified memory, 256GB SSD
- 13-inch Liquid Retina display
- 1080p FaceTime HD camera
Amazon affiliate links. We earn a commission on qualifying purchases at no extra cost to you.