Back to guide/General Productivity

Tip: Iterate with Follow-Ups

Setting up an iterative workflow from the start tells ChatGPT this is draft one, not the final product. The [NEEDS INPUT] markers and follow-up questions create a natural feedback loop.

chatgpt-prompt-tipsdocument_typetopicaudience
Edit View
Prompt
Write the first draft of a {{document_type}} about {{topic}} for {{audience}}.

After you write it, I will give you feedback to refine it. For this first draft:
- Focus on getting the structure and main points right
- Mark any sections where you're unsure of my preferences with [NEEDS INPUT]
- At the end, list 3 questions you'd ask me to improve the next draft

Keep it under {{word_count}} words.

Variables to customize

{{document_type}}{{topic}}{{audience}}{{word_count}}

Why this prompt works

Setting up an iterative workflow from the start tells ChatGPT this is draft one, not the final product. The [NEEDS INPUT] markers and follow-up questions create a natural feedback loop.

Save this prompt to your library

Organize, version, and access your best prompts across ChatGPT, Claude, and Cursor.

Related prompts

Task Decomposition Agent

Forcing the agent to plan before acting prevents premature execution and wasted steps. Explicit dependency mapping enables parallel execution and catches logical gaps early.

Tool Selection Agent

The ReAct pattern (Reason + Act) creates an explicit reasoning trace that improves tool selection accuracy. The error-handling rule prevents infinite retry loops.

Prompt Compressor

Explicitly requiring all functional requirements to be preserved prevents the model from over-compressing and losing critical instructions.

Memory Management Agent

Explicit memory read/write instructions create agents that improve over time. Categorization keeps memories organized, and the deduplication rule prevents context bloat.