🚨BREAKING: 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.
```
2. Leverage Identification
Naval says wealth requires leverage: code, media, labor, or capital.
Here's how I figure out which leverage I actually have access to:
Prompt:
``` Naval defines leverage as: code (software), media (content with no marginal cost), labor (people working for you), capital (money)
Analyze my current position:
[DESCRIBE YOUR SKILLS, RESOURCES, NETWORK, ASSETS]
For each type of leverage, tell me:
- Do I have it? (yes/no + evidence)
- How could I acquire it in 6 months?
- Which type matches my specific knowledge best?
Rank the 4 types by "easiest for me to scale right now." Show your reasoning.
```
3. Play Long-Term Games Validator
I was stuck in short-term gigs that went nowhere.
This prompt helped me identify which opportunities compound:
Prompt:
```
You are Naval evaluating an opportunity.
Opportunity: [DESCRIBE JOB/PROJECT/BUSINESS]
Answer these:
1. Is this a long-term game with long-term people? (will the same players be here in 10 years?) 2. Does this build specific knowledge or generic skills? 3. What compounds if I do this for 5 years? 4. What's the tail risk? (best case scenario if this works)
Naval's rule: "Pick an industry where you can play long-term games with long-term people."
Does this pass? Yes/No + why.
```
4. Productize Yourself Roadmap
Naval says "Learn to sell, learn to build. If you can do both, you will be unstoppable."
I use this to figure out my path:
Prompt:
```
Naval's framework: Selling + Building = Unstoppable
About me:
- Building skills: [WHAT YOU CAN CREATE - code, design, writing, etc.]
- Selling skills: [WHAT YOU CAN PERSUADE - pitching, marketing, negotiating]
Create a 12-month roadmap to "productize myself":
**Months 1-3:** [What to build/learn]
**Months 4-6:** [How to sell it]
**Months 7-9:** [Scale/automate]
**Months 10-12:** [Expected outcome]
Focus on intersection of specific knowledge + leverage. No generic advice.
```
5. Accountability vs. Authenticity Check
Naval says take accountability but stay authentic.
Most people fake one or the other. This prompt finds where I'm bullshitting:
Prompt:
```
I'm considering: [DECISION/CAREER MOVE]
Naval's test:
- "If you're authentic, you have nothing to hide and nothing to prove"
- "Take accountability so people know who to credit or blame"
Be honest: 1. Am I doing this because it's authentic to me, or because it looks good? 2. Am I willing to be publicly accountable for this outcome? 3. What would I do if no one was watching and I couldn't brag about it?
If this fails the authenticity test, what would pass it?
```
6. Reading for Actual Understanding
Naval reads obsessively but says "read what you love until you love to read."
I stopped forcing myself through books and used this instead:
Prompt:
```
Book: [BOOK YOU'RE READING]
Extract Naval's style: 1. What are the 3 core mental models in this book? 2. How would I apply each one to [YOUR SPECIFIC PROBLEM]? 3. What does this book assume that might be wrong?
Then:
- Should I finish this book or move on? (Naval abandons books freely)
- What should I read next based on what I'm trying to solve?
No summaries. Only actionable models and direct applications.
```
7. Decision-Making: Expected Value Calculator
Naval makes decisions using expected value, not outcomes.
For each option, calculate:
- Best case outcome (what if it works perfectly?)
- Worst case outcome (what if it fails completely?)
- Probability of success (be honest, not optimistic)
- Expected value (best case × probability) - (worst case × probability)
Naval's rule: "If you can't decide, the answer is no."
Which option has highest EV? Or should I reject all of them?
```
8. Building Credibility vs. Chasing Status
I was optimizing for status (titles, follower counts) instead of credibility.
This prompt helped me see the difference:
Prompt:
```
Naval distinguishes:
- Status = relative position in hierarchy (I'm above you)
- Credibility = trust earned through accountability (I delivered before)
Audit my last 6 months:
[DESCRIBE: projects, posts, career moves, time spent]
For each activity:
- Am I building credibility or chasing status?
- Will this matter in 5 years?
- Would I do this if no one knew about it?
What should I kill? What should I double down on?
```
9. Wealth Creation vs. Wealth Capture
Most people confuse making money with creating wealth.
Naval's distinction changed how I evaluate opportunities:
Prompt:
```
Opportunity: [JOB/BUSINESS/PROJECT]
Naval's framework:
- Wealth creation = making something people want (positive sum)
- Wealth capture = extracting value from what exists (zero sum)
Analyze: 1. Am I creating new wealth or capturing existing wealth? 2. Is this a positive-sum game or zero-sum competition? 3. What value am I adding that didn't exist before? 4. Can this scale without my direct time?
If it's pure capture, what would the wealth creation version look like?
```
10. Escape Competition Through Authenticity
Naval says "Competition is for losers" (Peter Thiel) - you escape competition by being yourself.
Here's how I found my monopoly:
Prompt:
```
List my skills/knowledge: [EVERYTHING YOU'RE DECENT AT]
Naval's insight: "Combine things you're good at until you're the best in the world at that combination."
Find 2-3 skill intersections where: 1. I'm top 10% in each individual skill 2. The combination is unique (almost no one else has all 3) 3. There's actual demand for this combination
Then: What would I call myself? (not job title - identity)
Example: "Developer + Writer + Crypto" = "Technical storyteller for web3"
```
Which mental model are you implementing this week?
Gemini now teaches me any topic in whatever format I want.
Here are 8 prompts that turned it into a personalized tutor 👇
1. The “Explain Like I Learn Best” Prompt
Teach me [topic] in the exact format that matches my learning style.
Ask me 3 questions first to detect my style (visual, conceptual, example-first, hands-on).
Then rebuild the explanation from scratch based on my answers.
→ This destroys generic tutorials because it adapts to you, not the algorithm.
Whenever I'm stuck on a business decision for more than 3 days, I run these 10 Claude prompts and get more clarity in 15 minutes than 3 weeks of overthinking ever gave me.
Copy and paste them into any chat:
1. THE REAL QUESTION FINDER
Before you solve anything, you need to know what you're actually solving.
Most business decisions feel hard because you're asking the wrong question.
Paste this:
"I've been stuck on this decision for [X] days: [describe the decision]. Before giving me advice, reframe this for me.
Tell me:
1) What the surface-level question appears to be, 2) What the actual underlying question I'm wrestling with really is, 3) What fear or assumption is driving my indecision, 4) What the real decision would look like if I stripped away the noise."
You'll realize you've been debating the wrong thing the entire time.
2. THE 10/10/10 RULE
Suzy Welch built her entire career on this framework.
Claude applies it in 30 seconds.
"Run my current decision through the 10/10/10 test:
1) How will I feel about this decision 10 minutes from now, 2) How will I feel about it 10 months from now, 3) How will I feel about it 10 years from now, 4) Based on all three time horizons, tell me which option creates the most long-term value and which one I'm avoiding out of short-term discomfort."
Most bad decisions look smart at 10 minutes and stupid at 10 years.
Holy shit…Professors at NYU, Stanford, and Case Western stopped building courses by hand.
They're using NotebookLM to do it in hours and one just called it the biggest shift in academic research in 20 years.
Here's the exact workflow they shared publicly:
Step 1 - The source upload strategy that changes everything.
Most people upload one or two documents.
Professors building full courses upload their entire reading list at once.
Up to 50 sources per notebook on the free tier.
500,000 words per source.
PDFs, Google Docs, URLs, YouTube lectures, audio files, images with OCR.
One notebook = one course unit.
The workflow Stanford faculty documented publicly:
→ Upload all assigned readings for a unit
→ Upload the course syllabus
→ Upload previous years' exam questions
→ Upload any relevant primary sources
NotebookLM now has a 1-million token context window.
It holds the entire unit in its head simultaneously and reasons across all of it at once.
No AI on the market does this grounded in YOUR specific sources.
Step 2 - The curriculum mapping prompt.
Once sources are uploaded, this is the first prompt professors run:
"Based on all uploaded materials, create a complete curriculum map for this unit. Identify the 5 core concepts students must understand. For each concept, list: the source that introduces it, the source that deepens it, and the source that challenges or complicates it. Then suggest a logical teaching sequence."
What comes back is a structured roadmap of the entire unit with every claim cited back to the exact uploaded source.
NYU's Assistant Dean used a version of this to identify course equivalencies across an entire revised curriculum for student advising.
What used to require weeks of manual cross-referencing across departments happened in one session.
Perplexity Computer has been quietly shipping features that make every other AI tool feel like a chatbot.
Most people don't even know these exist.
Here are 10 things it can do right now that will change how you work ↓
𝟏. Scheduled Tasks That Run While You Sleep
Computer doesn't just answer questions — it runs jobs on a schedule.
→ "Every Monday at 7am, audit my website SEO and email me the report"
→ "Every morning, pull competitor pricing changes and flag anything new"
→ "Every Friday at 5pm, compile my team's weekly metrics from Slack and Sheets"
You set it once. It runs forever. No reminders. No manual work.
You wake up and the work is already done.
𝟐. 20+ AI Models. Zero Switching.
Computer doesn't use one model. It uses over 20.
And here's the part nobody realizes — it picks the best model for each step automatically.
→ Research step? Routes to the best model for web retrieval.
→ Writing step? Routes to the best model for long-form.
→ Analysis step? Routes to the best model for reasoning.
→ Image generation? Routes to the best visual model.
One prompt. Multiple models working behind the scenes.
You never switch tabs, accounts, or subscriptions again.