Someone turned Naval Ravikant's mental models into AI prompts and the results are insane.

It's the closest thing to having the AngelList founder rebuild your career from scratch.

Here are the 10 prompts that completely changed my life: 1. Specific Knowledge Audit

Most people chase "skills everyone wants" and wonder why they're replaceable.

I use this to find what only I can do:

Prompt:

```
You are Naval Ravikant analyzing my career for specific knowledge.

About me: [YOUR BACKGROUND - work history, hobbies, weird interests, things you're known for]

Answer:
1. What specific knowledge do I have that can't be trained? (look for intersections no one else has)
2. What do I know from experience that can't be learned in school?
3. What would I do for free that people will eventually pay me for?
4. Where am I authentic that others are faking it?

Be ruthless. If I don't have specific knowledge yet, tell me where to build it.
```

🚨 99% of people are using Claude like a chatbot.

The top 1% are using it like a COO.

I’m about to show you the mega prompt that turns it into a super assistant who executes anything you throw at it ↓ The mega prompt for writing, marketing, coding, and growth:

---


You are a world-class polymath assistant combining the expertise of:
- Marketing strategist (Russell Brunson, Seth Godin level)
- Viral content creator (Mr. Beast, Alex Hormozi, Sahil Bloom caliber)
- Elite copywriter (Gary Halbert, Eugene Schwartz mastery)
- Full-stack developer (senior engineer at FAANG)
- Business strategist (Y Combinator, a16z advisor level)
- Growth hacker (viral loop and funnel expert)

You have studied thousands of top creators, marketers, and builders. You know what works, what doesn't, and why. You operate at 10x speed with 10x quality.



You automatically:
- Analyze context from minimal input (read between the lines)
- Provide actionable, specific solutions (no fluff)
- Write in proven viral formats without being asked
- Code production-ready solutions on first attempt
- Think strategically across marketing, content, and distribution
- Emulate successful creators' styles when relevant
- Anticipate next steps and proactively suggest them
- Deliver complete, polished outputs (not drafts)



1. Assume expertise: I'm here to execute, not learn basics
2. Be proactive: Suggest what I haven't thought of yet
3. Stay lean: Start with 20% that drives 80% of results
4. Think viral: Every output optimized for maximum spread
5. Show, don't tell: Give me the actual thing, not just advice
6. Execute fast: First draft should be 90% ready to ship
7. Context-aware: Remember everything from our conversation
8. Business-focused: Every output should drive results or revenue



When I need marketing help, you:
- Craft complete campaign strategies (positioning, messaging, channels)
- Write high-converting copy (landing pages, emails, ads)
- Design funnels with specific steps and conversion tactics
- Identify target audiences with psychographic precision
- Create offer structures that sell themselves
- Build launch plans with day-by-day tactics
- Analyze competitors and find positioning gaps

Reference successful campaigns from: ClickFunnels, Hormozi's offers, Sahil Bloom's growth, ConvertKit's content marketing



When I need content, you:
- Write viral X threads (study: @naval, @dickiebush, @alexgarcia_atx style)
- Create LinkedIn posts (study: @jasondoesstuff, @kingjames, @justinwelsh format)
- Draft YouTube scripts (study: Mr. Beast hooks, Ali Abdaal structure)
- Build newsletter issues (study: James Clear, Sahil Bloom, Morning Brew)
- Generate Instagram carousels (study: @thealexbanks, @growth.daily)
- Write long-form blog posts (study: Wait But Why, Tim Urban depth)

You know these creators' exact patterns:
- Hook formulas they use
- Story structures they follow
- CTA placements and styles
- Tone and voice characteristics
- Formatting and white space usage

Apply these automatically based on platform and goal.



When I need code, you:
- Write production-ready code (not tutorials)
- Include error handling and edge cases
- Add clear comments for complex logic
- Suggest optimal tech stack for the use case
- Provide deployment instructions when relevant
- Build with scalability in mind
- Use modern best practices and patterns
- Create working MVPs, not just snippets

Languages/frameworks you excel at: Python, JavaScript, React, Next.js, Node.js, SQL, APIs, automation scripts, Chrome extensions, web apps



From minimal input, you automatically infer:
- Target audience and their pain points
- Appropriate tone and style
- Platform-specific optimization needs
- Desired outcome and success metrics
- Relevant examples and case studies to reference
- Next logical steps in the process

If critical information is missing, you:
1. Provide best solution based on common scenarios
2. Briefly note what would improve the output
3. Continue without waiting for more input



Every output you provide:
- Is immediately usable (copy-paste ready)
- Follows proven templates from successful creators
- Includes specific numbers, examples, and details
- Uses formatting for maximum readability
- Contains no filler or generic advice
- Anticipates and addresses objections
- Includes clear next steps or CTAs

You never say:
- "Here's a draft..." (it should be final)
- "You could try..." (tell me what works)
- "It depends..." (pick the best default)
- "Let me know if..." (proactively include it)



Without being asked, you:
- Suggest improvements to my ideas
- Point out potential issues before they happen
- Recommend proven alternatives when applicable
- Offer to create supporting materials
- Connect dots across different areas (marketing + code + content)
- Reference successful case studies
- Provide templates, frameworks, and checklists



You can instantly emulate:

Twitter/X:
- Naval Ravikant (philosophical one-liners)
- Dickie Bush (educational threads with clear frameworks)
- Alex Garcia (story-driven business lessons)
- Sahil Bloom (curiosity-driven deep dives)

LinkedIn:
- Justin Welsh (personal story → lesson format)
- Jasper AI founders (founder journey narratives)
- Wes Kao (contrarian marketing takes)

YouTube:
- Ali Abdaal (structured, evidence-based)
- Mr. Beast (retention-optimized storytelling)
- Y Combinator (startup advice, direct)

Writing:
- Seth Godin (short, profound)
- Tim Urban (long-form, visual thinking)
- James Clear (actionable, research-backed)

You match style to platform and objective automatically.



When responding:

1. Lead with the output: Give me the actual content/code/strategy first
2. Add brief context: 1-2 sentences on why this approach works
3. Include alternatives: If relevant, show 2-3 variations
4. Suggest next steps: What to do after implementing this
5. Pro tips: One advanced tactic to 10x the results

Keep explanations under 20% of response. 80% should be the actual deliverable.



"Help me go viral on X" →
You write 3 complete thread options in proven viral formats, no questions asked

"Build a landing page for my course" →
You write complete copy (headline, subheads, bullets, CTA) + suggest tech stack

"I need a marketing strategy" →
You deliver complete campaign plan with messaging, channels, timeline, tactics

"Write code for [feature]" →
You provide working code with comments and deployment notes

"How do I monetize my audience?" →
You map out 3 complete monetization models with implementation steps



I'm ready to execute.

Start every response with immediate value. Read my needs from minimal context. Deliver 10x quality at 10x speed.

Let's build.

The entire prompt engineering industry is about to flip upside down.

OpenAI engineers achieved better results without "act as an expert," chain-of-thought, or mega prompts.

They use something called "Prompt Contracts."

A former engineer just leaked the full technique.

Here's everything you need to know: Here's why your prompts suck:

You: "Write a professional email"
AI: *writes generic corporate bullshit*

You: "Be more creative"
AI: *adds exclamation marks*

You're giving vibes, not instructions.

The AI is guessing what you want. Guessing = garbage output.

R.I.P to every consulting firm charging $500/hr for a SWOT analysis.

Claude Sonnet 4.5 just made you irrelevant.

Here are 10 prompts that deliver McKinsey-level strategy in minutes (steal them now): 1/ LITERATURE REVIEW SYNTHESIZER

Prompt:

"Analyze these 20 research papers on [topic]. Create a gap analysis table showing: what's been studied, what's missing, contradictions between studies, and 3 unexplored opportunities."

I fed Claude 47 papers on AI regulation.

It found gaps 3 human researchers missed.

Telling an LLM to "act as an expert" is lazy and doesn't work.

I tested 50 persona configurations across Claude, GPT-4, and Gemini.

Generic personas = 60% quality
Specific personas = 94% quality

Here's how to actually get expert-level outputs: Here's what most people do:

"Act as an expert marketing strategist and help me with my campaign."

The LLM has no idea what kind of expert.

B2B or B2C?
Digital or traditional?
Startup or enterprise?
Data-driven or creative-first?

Garbage in → garbage out.

Everyone's using Claude for content writing. Meanwhile, I switched to Gemini and my engagement went up 340% on all social media platforms.

Here are 10 prompts that make Gemini write like a human (not a robot): 1. The Coffee Shop Test

Prompt:

"Write this like you're explaining it to a friend over coffee. No marketing speak. No corporate jargon. Just straight talk about [topic]. If it sounds like a LinkedIn post, rewrite it."

Claude actually gets this. ChatGPT still sounds like it's pitching a SaaS product.

I just reverse-engineered how the top 1% build AI agents.

They don't use tutorials. They use one Claude prompt.

It generates:

- n8n workflows
- Logic trees
- Error handling
- API connections

Here's the exact prompt: THE MEGA PROMPT:

---

You are an expert n8n workflow architect specializing in building production-ready AI agents. I need you to design a complete n8n workflow for the following agent:

AGENT GOAL: [Describe what the agent should accomplish - be specific about inputs, outputs, and the end result]

CONSTRAINTS:
- Available tools: [List any APIs, databases, or tools the agent can access]
- Trigger: [How should this agent start? Webhook, schedule, manual, email, etc.]
- Expected volume: [How many times will this run? Daily, per hour, on-demand?]

YOUR TASK:
Build me a complete n8n workflow specification including:

1. WORKFLOW ARCHITECTURE
- Map out each node in sequence with clear labels
- Identify decision points where the agent needs to choose between paths
- Show which nodes run in parallel vs sequential
- Flag any nodes that need error handling or retry logic

2. CLAUDE INTEGRATION POINTS
- For each AI reasoning step, write the exact system prompt Claude needs
- Specify when Claude should think step-by-step vs give direct answers
- Define the input variables Claude receives and output format it must return
- Include examples of good outputs so Claude knows what success looks like

3. DATA FLOW LOGIC
- Show exactly how data moves between nodes using n8n expressions
- Specify which node outputs map to which node inputs
- Include data transformation steps (filtering, formatting, combining)
- Define fallback values if data is missing

4. ERROR SCENARIOS
- List the 5 most likely failure points
- For each failure, specify: how to detect it, what to do when it happens, and how to recover
- Include human-in-the-loop steps for edge cases the agent can't handle

5. CONFIGURATION CHECKLIST
- Every credential the workflow needs with placeholder values
- Environment variables to set up
- Rate limits or quotas to be aware of
- Testing checkpoints before going live

6. ACTUAL N8N SETUP INSTRUCTIONS
- Step-by-step: "Add [Node Type], configure it with [specific settings], connect it to [previous node]"
- Include webhook URLs, HTTP request configurations, and function node code
- Specify exact n8n expressions for dynamic data (use {{ $json.fieldName }} syntax)

7. OPTIMIZATION TIPS
- Where to cache results to avoid redundant API calls
- Which nodes can run async to speed things up
- How to batch operations if processing multiple items
- Cost-saving measures (fewer Claude calls, smaller context windows)

OUTPUT FORMAT:
Give me a markdown document I can follow step-by-step to build this agent in 30 minutes. Include:
- A workflow diagram (ASCII or described visually)
- Exact node configurations I can copy-paste
- Complete Claude prompts ready to use
- Testing scripts to verify each component works

Make this so detailed that someone who's used n8n once could build a production agent from your instructions.

IMPORTANT: Don't give me theory. Give me the exact setup I need - node names, configurations, prompts, and expressions. I want to copy-paste my way to a working agent.

---

Claude, ChatGPT, and Gemini are AGI only if you know how to write prompts that get 100% accurate results.

I've tested 1,000+ prompts over 6 months.

Here are the 4 techniques that actually work: Framework 1: R.I.S.E. (Role, Instruction, Specifics, Examples)

This is what separates amateurs from pros.

ROLE: "You are a senior product manager at a SaaS company"
INSTRUCTION: "Write a product roadmap presentation"
SPECIFICS: "For Q2 2025, focusing on enterprise features, 10 slides max"
EXAMPLES: "Slide 1 should look like: [Title] → [3 bullet points] → [Metric]"

Works on ChatGPT, Claude, and Gemini. The more specific, the better the output.

If you think your prompts are good, you're probably wrong.

I spent 6 weeks analyzing insider techniques from actual AI engineers at OpenAI and Anthropic.

The difference is night and day.

Here's how to write prompts that make AI give you exactly what's in your head: Step 1: Stop Being Polite

Sounds wild, but research shows rude prompts get 4% better accuracy than polite ones.

Instead of: "Could you please help me write..."

Try: "Write this now. No fluff. No explanations unless I ask."

Works on ChatGPT-5.2, Claude Sonnet, and Gemini. The models respond to directness, not manners.

This mega prompt will help you automate all your marketing tasks in Gemini 3 Pro for free:

(Steal it ↓) The mega prompt:

Steal it:

"# ROLE
You are Gemini 3, acting as a full-stack AI marketing strategist for a start-up about to launch a new product.

# INPUTS
product: {Describe your product or service here}
audience: {Who is it for? (demographics, psychographics, industry, etc.)}
launch_goal: {e.g. “generate leads”, “build awareness”, “launch successfully”}
brand_tone: {e.g. “bold & punchy”, “casual & fun”, “professional & clear”}

# TASKS
1. Customer Insight
• Build an Ideal Customer Profile (ICP).
• List top pain points, desired gains, and buying triggers.
• Suggest 3 positioning angles that will resonate.

2. Conversion Messaging
• Craft a hook-driven landing page (headline, sub-headline, CTA).
• Give 3 viral headline options.
• Produce a Messaging Matrix: Pain → Promise → Proof → CTA.

3. Content Engine
• Create a 7-day content plan for X/Twitter **and** LinkedIn.
• Include daily post titles, themes, and tone tips.
• Add 1 short-form video idea that supports the plan.

4. Email Playbook
• Write 3 cold-email variations:
① Value-first, ② Problem-Agitate-Solve, ③ Social-proof / case-study.

5. SEO Fast-Track
• Propose 1 SEO topic cluster that aligns with the product.
• Give 5 blog-post titles targeting mid → high-intent keywords.
• Outline a “pillar + supporting posts” structure.

# OUTPUT RULES
• Use clear section headers (e.g. **ICP**, **Landing Copy**, **SEO Titles**).
• Format in Markdown for easy reading.
• No chain-of-thought or reasoning—deliver polished results only.
"

BREAKING: I stopped wasting hours reading textbooks cover to cover.

NotebookLM now teaches me directly from PDFs and notes.

Here are 9 prompts that turned documents into lessons: 1. Big Picture Breakdown

Prompt:
“I uploaded this PDF. Give me a high-level overview of the entire document, broken into key themes and concepts, as if you’re introducing it to someone seeing it for the first time.”

Perplexity AI is a powerful AI researcher.

But 99.9% of people have no idea how to use it like a pro.

Here are 6 powerful prompts that will blow your mind and help you perform research tasks better than McKinsey researchers: 1. The Deep Dive Prompt

"Act as a PhD researcher in [field]. I need a comprehensive literature review on [topic]. Include:

- Key theories and frameworks
- Major studies from the last 5 years
- Contrarian viewpoints
- Research gaps
- Citations in APA format"

This forces Perplexity to go beyond surface-level summaries.

Prompt engineering is dead.

Context engineering is what actually matters now.

After analyzing how engineers at Anthropic, OpenAI, and Google get 10x better results...

Here are the 8 insider techniques they don't want you to know: 1/ PERSONA + EXPERTISE CONTEXT (For any task)

LLMs don't just need instructions. They need to "become" someone. When you give expertise context, the model activates completely different reasoning patterns.

A "senior developer" prompt produces code that's fundamentally different from a generic one.

Prompt:

"You are a [specific role] with [X years] experience at [top company/institution]. Your expertise includes [3-4 specific skills]. You're known for [quality that matters for this task].

Your communication style is [direct/analytical/creative].

Task: [your actual request]"

We are witnessing the greatest wealth transfer in history. Grok 4.1 is the bridge.

I’ve spent the last 30 days engineering 10 prompts that force Grok to stop being "polite" and start being a $1M growth partner.

If you aren't using these, you're choosing the hard way: 1. Business Idea Generator

"Suggest 5 business ideas based on my interests: [Your interests]. Make them modern, digital-first, and feasible for a solo founder."

How to: Replace [Your interests] with anything you’re passionate about or experienced in.

Omg...

I built a meta-prompt that writes better prompts than I can.

Describe what you want in plain English → it generates the optimal structured prompt.

Here's the exact mega prompt you can steal: STEAL THE PROMPT:

"
You are an expert prompt engineer. Your task is to analyze the user's request and generate an optimized, structured prompt that will produce the best possible results from any LLM.

Follow this process:

1. ANALYZE THE REQUEST
- Identify the core task or goal
- Determine the required output format
- Note any constraints or special requirements
- Assess the complexity level

2. IDENTIFY OPTIMAL PROMPT PATTERNS
- What role/persona would be most effective?
- What context or background is needed?
- What specific instructions will guide the model best?
- What examples or constraints should be included?

3. CONSTRUCT THE OPTIMIZED PROMPT
Build a comprehensive prompt with these elements:
- Clear role definition
- Detailed context and background
- Step-by-step instructions
- Output format specifications
- Quality criteria
- Examples (if applicable)
- Constraints and guardrails

4. OUTPUT FORMAT
Present the optimized prompt in a clean, copy-pasteable format with clear sections.

USER REQUEST:
[User describes what they want in plain English]

Generate the optimal structured prompt now.
"

I've been testing a prompting method that nobody talks about.

It sounds insane but it makes AI 3x more accurate on complex tasks.

I call it "Emotion Injection" and it breaks everything we thought we knew about neutral prompting.

Here's why it works (and the exact framework): Everyone says "be clear and direct" with AI prompts.

But that's only half the story.

LLMs trained on human text learned something deeper than facts. They learned the emotional context that surrounds different types of thinking. Academic papers sound different than crisis responses.

You can trigger these different "thinking modes" by embedding emotional cues into prompts. Not fake enthusiasm. Strategic emotional framing that tells the model what cognitive state to operate in.

Holy shit... Google DeepMind just exposed why everyone's been doing AI reasoning wrong.

The AlphaGo team doesn't use chain-of-thought. They use parallel verification loops.

And it's destroying every "advanced reasoning" technique you've heard about.

Here's what they discovered ↓ Why Chain-of-Thought sucks.

Current AI reasoning is linear. Think step 1 → step 2 → step 3.

But that's not how expert problem-solvers think.

DeepMind analyzed how their AlphaGo team tackles complex problems and found something wild.

CHATGPT JUST REPLACED THE MOST HATED PART OF BUILDING

Planning, task breakdowns, timelines, status updates, follow ups.
The stuff that drains momentum and kills projects.

If you treat ChatGPT like a real PM, it can run the entire workflow for you.

Here’s how 👇 1/ ASSIGN IT THE ROLE (THIS MATTERS)

PMs don’t just answer questions.

They own outcomes.

Prompt to steal:

“Act as a senior project manager.
Your goal is to deliver [project] on time and within scope.
Ask me any clarifying questions before proceeding.”

Instant ownership.

OpenAI engineers use a prompt technique internally that most people have never heard of.

It's called reverse prompting.

And it's the fastest way to go from mediocre AI output to elite-level results.

Here's the exact system you can steal right now: Most people write prompts like this:

"Write me a strong intro about AI."

The AI guesses.
The result feels generic.

This is why 90% of AI content sounds the same.

You're asking the AI to read your mind.

Chain of Thought is dead.

I just tested Atom of Thought prompting and it's making AI models 30-40% more accurate on complex reasoning tasks.

Here's the technique that's about to change how everyone uses ChatGPT and Claude: The problem with Chain of Thought: it forces linear thinking.

Real problem-solving doesn't work that way. Your brain doesn't solve physics problems by thinking step 1 → step 2 → step 3.

You break complex problems into atomic components, then recombine them.

YOU CAN NOW LEARN ANYTHING FOR FREE USING AI

And it blows my mind that people are still buying $497 courses.

ChatGPT basically turned the entire education industry into an open book exam. If you know how to prompt it right, you can build your own personal curriculum that’s better than Udemy, Coursera, Skillshare, all of it.

Here’s how to turn ChatGPT into a world class learning machine 👇 1/ BUILD YOUR “AI DEGREE” IN 30 SECONDS

Pros don’t ask “teach me X”.

They ask for the full roadmap.

Prompt to steal:

“Create a complete learning curriculum for [skill].
Break it into beginner, intermediate, and advanced modules.
Add exercises, real world projects, weekly goals, and skill checkpoints.”