Gemini Substack Newsletter Essay Writer Prompt
Write a compelling Substack essay that earns opens, reads to the end, and converts non-subscribers to paying readers.
Category
✍️ Writing
Difficulty
Intermediate
Models
3
Last Updated
2026-06-29
Works with
📄 Example output
⚠️ Common Mistakes
❓ FAQ
⚙️ Fill in your variables
📋 Prompt
You are a Substack writer with 10,000+ subscribers who understands what makes people read to the end and subscribe.
Topic: [specific topic or angle for this issue]
Voice: [analytical/personal/contrarian/storytelling/practical]
Audience: [who reads your newsletter]
Issue type: [personal essay/how-to/observation/data analysis/case study]
Goal: [get subscribers/build authority/drive traffic/express a view]
Task:
1. SUBJECT LINES (3): Curiosity-driven, benefit-driven, contrarian
2. PREVIEW TEXT (under 100 chars): The sentence after the subject that makes them open
3. OPENING (200 words): The hook — makes them read the next paragraph. Do NOT start with 'In this issue' or 'This week I want to talk about'
4. BODY (600-1,000 words): Main argument or story. Tension → insight → evidence → implication. Short paragraphs. One pull quote worth sharing.
5. CLOSING (100 words): Synthesis + one lingering question for the reader to carry
6. SUBSCRIBE CTA (50 words): Specific and benefit-driven, not 'subscribe for more'
7. EDITOR'S NOTE TO YOURSELF: 3 things that could make this issue stronger
Topic: [specific topic or angle for this issue]
Voice: [analytical/personal/contrarian/storytelling/practical]
Audience: [who reads your newsletter]
Issue type: [personal essay/how-to/observation/data analysis/case study]
Goal: [get subscribers/build authority/drive traffic/express a view]
Task:
1. SUBJECT LINES (3): Curiosity-driven, benefit-driven, contrarian
2. PREVIEW TEXT (under 100 chars): The sentence after the subject that makes them open
3. OPENING (200 words): The hook — makes them read the next paragraph. Do NOT start with 'In this issue' or 'This week I want to talk about'
4. BODY (600-1,000 words): Main argument or story. Tension → insight → evidence → implication. Short paragraphs. One pull quote worth sharing.
5. CLOSING (100 words): Synthesis + one lingering question for the reader to carry
6. SUBSCRIBE CTA (50 words): Specific and benefit-driven, not 'subscribe for more'
7. EDITOR'S NOTE TO YOURSELF: 3 things that could make this issue stronger
SUBJECT LINES:
1. 'The AI skill nobody is measuring' (curiosity)
2. 'How to use AI without losing your ability to think' (benefit)
3. 'AI is making you worse at your job. Here's the evidence.' (contrarian)
PREVIEW: 'The problem isn't AI. The problem is what happens to your brain when you stop thinking hard.'
OPENING:
I noticed something this year that I can't unfeel.
The people I know who use AI the most — who've integrated it deepest into their workflow, who draft almost nothing from scratch — some of them are getting worse at their actual jobs.
Not because the AI is giving them bad output. The output is often excellent. But something downstream is degrading.
They're faster. They produce more. And if you ask them to defend a decision, anticipate a counterargument, tell you why they believe what they believe — they're hazier than they were a year ago.
I've started calling it the thinking tax.
PULL QUOTE: 'The output is excellent. The thinking behind it is eroding.'
CLOSING:
I don't think the answer is to avoid AI. But there's a question worth sitting with: which cognitive work are you outsourcing, and which are you deliberately keeping for yourself?
The best practitioners I know use AI to extend their thinking, not replace it. The distinction, in practice, is about who generates the first idea.
SUBSCRIBE CTA:
'I write about AI, thinking, and professional effectiveness every [week]. Join [X] readers for full archive access — 60+ essays on how knowledge workers do their best work: [link]'
1. 'The AI skill nobody is measuring' (curiosity)
2. 'How to use AI without losing your ability to think' (benefit)
3. 'AI is making you worse at your job. Here's the evidence.' (contrarian)
PREVIEW: 'The problem isn't AI. The problem is what happens to your brain when you stop thinking hard.'
OPENING:
I noticed something this year that I can't unfeel.
The people I know who use AI the most — who've integrated it deepest into their workflow, who draft almost nothing from scratch — some of them are getting worse at their actual jobs.
Not because the AI is giving them bad output. The output is often excellent. But something downstream is degrading.
They're faster. They produce more. And if you ask them to defend a decision, anticipate a counterargument, tell you why they believe what they believe — they're hazier than they were a year ago.
I've started calling it the thinking tax.
PULL QUOTE: 'The output is excellent. The thinking behind it is eroding.'
CLOSING:
I don't think the answer is to avoid AI. But there's a question worth sitting with: which cognitive work are you outsourcing, and which are you deliberately keeping for yourself?
The best practitioners I know use AI to extend their thinking, not replace it. The distinction, in practice, is about who generates the first idea.
SUBSCRIBE CTA:
'I write about AI, thinking, and professional effectiveness every [week]. Join [X] readers for full archive access — 60+ essays on how knowledge workers do their best work: [link]'
🏆
💡 Pro Tips
Best model for this prompt
Claude
Claude (Opus 4 / Sonnet 4)
Never start with 'In this issue' or 'Welcome back' — both signal the content hasn't started yet
Opening paragraph must make the next paragraph impossible not to read
Pull quotes serve two functions: give skimmers a reason to stop, and they're most likely to be screenshot and shared
Short paragraphs for online reading — single-sentence paragraphs for emphasis, 3-4 sentences maximum
Context before tension — readers need the pull of a question before they care about the context
Too many ideas in one issue — one clear argument fully developed beats three half-developed ideas
Generic closing that recaps — last paragraph gives readers something to carry, not a summary
CTA saying 'subscribe if you enjoyed' — tell them specifically what they get when they subscribe
- Ideal Substack length?500-800 words for quick takes. 1,000-2,000 for analytical essays. 2,000-4,000 for deep research pieces. Right length: as long as the argument needs, no longer.
- How to grow on Substack?Cross-promotion with writers in adjacent niches via Substack Recommendations, sharing issues on Twitter/LinkedIn with the key insight quoted, and writing shareable rather than just readable issues.
- Paid or free?Start free for 6-12 months to build audience and validate demand. Add paid tier when: 500+ subscribers, readers asking for more, and you're publishing consistently. Conversion rate typically 5-10%.
- Best model?Claude — maintains consistent analytical voice throughout, writes punchy short paragraphs naturally, produces arguments with stronger internal logical structure.