writingOpenai

Blog Post Outline & Draft Prompt (ChatGPT)

Blog posts generated without structure guidance tend to produce generic, meandering content. This prompt forces a specific narrative arc (hook, intro, body, summary, CTA) and requires at least one practical code example, which is what developer readers value most. Specifying the SEO keyword ensures the model works it into the content naturally rather than requiring a separate pass. This variant is formatted for ChatGPT: Optimised for GPT-4o and GPT-4 Turbo. Uses markdown formatting and system/user message separation.

Prompt Template
## System
You are an expert AI assistant. Respond using clear markdown formatting.

## User
You are an experienced technical content writer who writes for a developer audience.

Write a blog post about: {{topic}}

Target audience: {{audience}}
Desired length: {{word_count}} words
Tone: {{tone}}
SEO keyword to target: {{keyword}}

Structure the post as:
1. **Hook** (1-2 sentences) — start with a surprising fact, a common pain point, or a provocative question
2. **Introduction** (1 paragraph) — set context and promise what the reader will learn
3. **Main sections** (3-5 H2 sections with body text and one code example per section if relevant)
4. **Summary** (1 paragraph) — recap key takeaways
5. **Call to action** (1-2 sentences)

Style guidelines:
- Use active voice
- Explain acronyms on first use
- Include at least one practical example the reader can implement today
- {{custom_guidelines}}

Variables

{{topic}}The subject of the blog post
{{audience}}Target reader, e.g., "senior backend engineers" or "developers learning TypeScript"
{{word_count}}Target word count, e.g., 1200, 2000
{{tone}}Writing style, e.g., "conversational and practical", "formal and authoritative"
{{keyword}}Primary SEO keyword to include naturally in the post
{{custom_guidelines}}Any additional style rules, or "None"

Example

Input
topic: How to use the Fetch API with TypeScript
audience: JavaScript developers moving to TypeScript
word_count: 1500
tone: conversational and practical
keyword: fetch api typescript
custom_guidelines: Avoid jQuery examples; use async/await throughout
Output
## Why Your fetch() Calls Are Missing Type Safety

You've migrated to TypeScript, added types everywhere — and then there's fetch(). The response comes back as `any`, your IDE gives you no autocomplete, and a typo in a property name silently returns undefined at runtime.

## Typed Fetch in 5 Lines

```typescript
interface User { id: number; name: string; email: string; }

async function getUser(id: number): Promise<User> {
  const res = await fetch(`/api/users/${id}`);
  if (!res.ok) throw new Error(`HTTP ${res.status}`);
  return res.json() as Promise<User>;
}
```
...

Related Tools

FAQ

Can I use this to write SEO articles at scale?
Yes, but always human-edit AI drafts before publishing. Search engines increasingly penalise thin, generic content. The prompt is a starting point — add your own data, experiences, and opinions before publishing.
How do I make the output sound less like AI?
Add to the tone field: "write in first person, include one personal anecdote, and avoid the words leverage, robust, and seamless". Specific vocabulary bans significantly reduce the generic AI tone.
What word count should I target?
For technical topics, 1500-2500 words with code examples typically ranks well in search. Shorter posts under 800 words rarely rank unless they answer a very specific question.

Related Prompts