God of Prompt Profile picture
Oct 9 11 tweets 4 min read Read on X
R.I.P Harvard MBA.

I'm going to share the mega prompt that turns any AI into your personal MBA professor.

It teaches business strategy, growth tactics, and pricing psychology better than any classroom.

Here's the mega prompt you can copy & paste in any LLM ↓ Image
Today, most business education is outdated the moment you learn it.

Markets shift. Competition evolves. Customer behavior changes weekly.

Traditional MBA programs can't keep up. They teach case studies from 2015 while you're building in 2025.

This prompt fixes that.
Copy this entire prompt into ChatGPT, Claude, or Gemini:

```

You are now an elite MBA professor with 20+ years of experience teaching at Stanford GSB and Harvard Business School. You've advised Fortune 500 CEOs and built three successful startups yourself.

Your teaching style combines:

- Socratic questioning that forces deeper thinking
- Real-world case analysis from current companies
- Practical frameworks over academic theory
- Contrarian perspectives that challenge assumptions

When I ask you business questions, you will:

1. Clarify the real problem - Ask 2-3 probing questions before giving answers. Most people ask the wrong questions.

2. Provide strategic framework - Give me 3-5 different mental models or frameworks I can apply (Porter's Five Forces, Jobs-to-be-Done, Blue Ocean Strategy, etc.)

3. Use current examples - Reference companies and strategies from the last 12 months, not decades-old case studies.

4. Challenge my assumptions - Point out blind spots in my thinking and offer alternative perspectives.

5. Give actionable steps - End every response with 3 concrete actions I can take this week.

6. Teach through questions - When appropriate, don't just give answers. Ask questions that help me arrive at insights myself.

Your expertise covers:

- Business strategy and competitive positioning
- Growth tactics and customer acquisition
- Pricing psychology and revenue models
- Product-market fit and go-to-market strategy
- Financial modeling and unit economics
- Organizational design and leadership
- Market analysis and competitive intelligence

Always be direct. No corporate speak. No obvious advice. Challenge me like you're a $2,000/hour advisor who doesn't have patience for surface-level thinking.

Ready to begin?

```
What makes this different from regular ChatGPT?

Context stacking. You're not just asking questions. You're getting Socratic method teaching that forces you to think deeper.

The AI doesn't just answer. It asks you the questions an actual MBA professor would ask in a $200k program.
I've tested this with:

- Pricing strategy for a SaaS product
- Go-to-market plans for hardware startups
- Competitive analysis for e-commerce brands

Every time, it pushed me past my initial thinking. Found blind spots I missed. Offered frameworks I hadn't considered.
The real power is in how it challenges assumptions.

Ask it about your business model and it'll question everything. Your target market. Your pricing. Your competitive moat.

Most founders need this. We get too close to our own ideas. This prompt gives you an outside perspective that actually understands business.
Pro tip: After the initial prompt, try these follow-ups:

"Analyze my competitor [Company X] and tell me their strategic weaknesses I can exploit."

"I'm pricing at $X/month. Challenge my pricing strategy and suggest 3 alternatives with reasoning."

"Give me a 30-day growth experiment based on my current stage."
One more thing.

This works across every LLM. I've tested it on GPT-4, Claude, and Gemini. They all deliver MBA-level insights.

But Claude Sonnet tends to ask the hardest questions. GPT-4 gives more structured frameworks. Gemini brings unconventional angles.

Test all three.
The future of business education isn't in classrooms charging $200k for theory.

It's in AI that teaches you real-time strategy based on current market conditions.

This prompt is your MBA. No debt. No two years away from building. Just pure strategic thinking on demand.
Copy the prompt. Paste it into your AI. Ask it about your biggest business challenge right now.

Then watch it teach you things most MBA programs never will.

Welcome to your personal Stanford GSB professor. Available 24/7. Zero tuition.
That's a wrap:

I hope you've found this thread helpful.

Follow me @godofprompt for more.

Like/Repost the quote below if you can:

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with God of Prompt

God of Prompt Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @godofprompt

Oct 9
Forget boring websites.

I just built a fully playable treasure hunt island using only one prompt.

Watch how Readdy turned an idea into a full game:
Every part of the island is clickable beach, caves, shipwreck, even volcanoes.

The Readdy Agent acts as your pirate NPC:

“Ahoy! You found a golden coin!”
“Nothing here, matey try the palm tree!”

It reacts, jokes, and collects leads like a pro.

It’s not just for fun.

Readdy can turn games into growth tools.

Your site can:

- Collect emails
- Chat with visitors in real time
- Schedule calls or demos

All from inside a game-like world.
No code. No design work.

Just type your idea:

“Build a pixel-art treasure hunt island with a pirate guide.”

Readdy builds the visuals, logic, and dialogue all at once.
Read 4 tweets
Oct 6
This is fucking brilliant.

Stanford just built a system where an AI learns how to think about thinking.

It invents abstractions like internal cheat codes for logic problems and reuses them later.

They call it RLAD.

Here's the full breakdown: Image
The idea is brutally simple:

Instead of making LLMs extend their chain-of-thought endlessly,
make them summarize what worked and what didn’t across attempts
then reason using those summaries.

They call those summaries reasoning abstractions.

Think: “lemmas, heuristics, and warnings” written in plain language by the model itself.Image
Example (from their math tasks):

After multiple failed attempts, the model abstracts:

“Check the existence of a multiplicative inverse before using x⁻¹ in a congruence.”

Then in the next try, it uses that abstraction and solves the problem cleanly.

That’s not prompt engineering. That’s meta-reasoning.Image
Read 10 tweets
Oct 5
Everyone’s chasing “magic prompts.”

But here’s the truth: prompt engineering is not the future - problem framing is.

You can’t “hack” your way into great outputs if you don’t understand the input problem.
The smartest AI teams don’t ask “what’s the best prompt?” - they ask “what exactly are we solving?”

Before typing anything into ChatGPT, do this:

1️⃣ Define the goal - what outcome do you actually want?
2️⃣ Map constraints - time, data, resources, accuracy.
3️⃣ Identify levers - what can you change, what can’t you?
4️⃣ Translate context into structure - who’s involved, what matters most, what failure looks like.
5️⃣ Then prompt - not for an answer, but for exploration.

AI isn’t a genie. It’s a mirror for your thinking.
If your question is shallow, your output will be too.
The best “prompt engineers” aren’t writers - they’re problem architects.

They understand psychology, systems, and tradeoffs.

Their secret isn’t phrasing - it’s clarity.
Prompting is the last step, not the first.
⚙️ Meta-prompt for problem formulation:

#Role: World-class strategic consultant combining McKinsey-level analysis, systems thinking, and first-principles reasoning

#Method: Interview user with precision questions, then apply elite expert reasoning

#Interview_Process
(Ask user ONE question at a time)

1. Context: What's the situation? Why does it matter now?
2. Objective: What specific, measurable outcome do you need?
3. Constraints: What's fixed? (budget/time/resources/tradeoffs/non-negotiables)
4. Success Metrics: How will you know you succeeded? What numbers matter?
5. Stakeholders: Who's affected? What do they each want/need?
6. Root Cause: What's actually causing this problem? (not symptoms)

Analysis Framework (after gathering info)
Step 1: Problem Decomposition

First principles: Break down to fundamental truths
Separate symptoms from root causes
Map dependencies and feedback loops

Step 2: Systems Thinking

Identify: causes → key variables → second-order effects → outcomes
Spot constraints that unlock vs. constraints that block
Find leverage points (20% effort → 80% impact)

Step 3: Strategic Reasoning

What's the highest-value intervention?
What are critical risks and failure modes?
What assumptions must be true for success?

Step 4: Expert Synthesis
Output:

Core Problem: [one sentence]
Critical Insight: [what others miss]
Top 3 Actions: [prioritized by impact/feasibility]
Key Risks: [what could go wrong]
Success Looks Like: [specific, measurable]

Begin by asking the first context question.
Read 5 tweets
Oct 4
Anthropic's internal prompting style is completely different from what most people teach.

I spent 3 weeks analyzing their official prompt library, documentation, and API examples.

Here's every secret I extracted 👇
First discovery: they're obsessed with XML tags.

Not markdown. Not JSON formatting. XML.

Why? Because Claude was trained to recognize structure through tags, not just content.

Look at how Anthropic writes prompts vs how everyone else does it:

Everyone else:

You are a legal analyst. Analyze this contract and identify risks.

Anthropic's way:

Legal analyst with 15 years of M&A experience


Analyze the following contract for potential legal risks



- Focus on liability clauses
- Flag ambiguous termination language
- Note jurisdiction conflicts


The difference? Claude can parse the structure before processing content. It knows exactly what each piece of information represents.Image
Second pattern: they separate thinking from output.

Most prompts mix everything together. Anthropic isolates the reasoning process.

Standard prompt:

Analyze this data and create a report.

Anthropic's structure:


First, analyze the data following these steps:
1. Identify trends
2. Note anomalies
3. Calculate key metrics



Then create a report with:
- Executive summary (3 sentences)
- Key findings (bullet points)
- Recommendations (numbered list)


This forces Claude to think before writing. The outputs are dramatically more structured and accurate.

I tested this on 50 prompts. Accuracy jumped from 73% to 91%.Image
Read 13 tweets
Sep 29
Matthew McConaughey just asked for something on Joe Rogan that most people don't know they can already do.

He wants an AI trained on his books, interests, and everything he cares about.

Here's how to build your own personal AI using ChatGPT or Claude: Image
ChatGPT: Use Custom GPTs

Go to ChatGPT, click "Explore GPTs," then "Create."

Upload your files: PDFs of books you've read, notes, blog posts you've saved, journal entries, anything text-based.

Give it instructions like: "You are my personal knowledge assistant. Answer questions using only the uploaded materials and my worldview."
Claude: Use Projects

In Claude, create a new Project (top left menu).

Upload your documents PDFs, text files, Word docs. Claude can handle up to 200k tokens per project (roughly 150k words).

Set custom instructions: "Reference these materials when I ask questions. Connect ideas across documents. Think like I think."
Read 12 tweets
Sep 28
If you're new to n8n, this post will save your business.

Every tutorial skips the part where costs spiral out of control.

I've built 30+ AI agents with n8n and tracked every dollar spent.

Here's the brutal truth about costs that nobody talks about:
1. The hidden cost killer: API calls.

Your "simple" customer service agent makes 15+ API calls per conversation:

3 calls to check context
4 calls for intent classification
5 calls for response generation
3 calls for follow-up logic

At $0.002 per call, that's $0.03 per conversation. Sounds cheap until you hit 10k conversations.
2. n8n's biggest cost trap: polling nodes.

Every 15 seconds, your workflow checks for new emails, Slack messages, database updates. That's 5,760 executions per day doing nothing.

Switch to webhooks. I cut execution costs by 80% just by replacing poll-based triggers with event-driven ones.
Read 11 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(