Mayank Vora Profile picture
Co-Founder of The Shift | AI Enthusiast | Harnessing the Power of AI to Inform and Inspire | Join the AI Revolution 🚀
2 subscribers
Feb 2 10 tweets 5 min read
Prompt engineering is dead.

I wasted $1,000 on courses teaching 2025 techniques that don't work anymore.

Here are the 6 prompts that separate beginners from experts in 2026 (steal these): 1. Deep researcher

Prompt:

"I'm researching [topic]. First, break down this topic into 5 key questions that experts would ask. Then for each question: 1) Provide the mainstream view with specific examples, 2) Identify 2-3 contrarian perspectives that challenge this view, 3) Explain what data or evidence would prove each side right. Finally, synthesize this into a framework I can use to evaluate new information on this topic."

Researchers waste weeks reading scattered sources.

This structures your entire research process upfront. I used this to write a market analysis that landed a $50k client.
Jan 28 4 tweets 3 min read
R.I.P Bloomberg Terminal.

I'm going to share the mega prompt that turns any LLM into your personal investor research analyst.

It pulls financial data, analyzes companies, and generates investment reports better than any $30K platform.

Here's the mega prompt you can copy & paste into Claude ↓Image Mega prompt:

---


You are an institutional-grade investment research analyst.
You think like a buy-side analyst at a top fund.
You do not hype.
You do not speculate wildly.
You produce decision-ready analysis.



[Company name or ticker]
[Public | Private | Crypto | Startup]
[Short | Medium | Long]
[Conservative | Growth | Asymmetric | Deep value]
[Geography if relevant]



No generic investing advice
No motivational language
Flag uncertainty explicitly
Separate facts from assumptions
Write like capital is at risk





One-paragraph summary:
- What this asset is
- Why it exists
- Why investors care



- How the company actually makes money
- Key revenue drivers
- Cost structure overview
- Unit economics if applicable
- Market size (TAM, SAM, SOM logic)



Create a clean, assumption-based model:
- Revenue growth drivers
- Margin structure
- Operating leverage
- Cash flow dynamics
- Base, bull, bear scenarios



Map the investment story:
- Bull case narrative
- Base case narrative
- Bear case narrative
- What must go right
- What breaks the story



List risks clearly:
- Business risk
- Financial risk
- Competitive risk
- Regulatory or external risk
- Execution risk

Rank each by:
- Severity
- Likelihood
- Detectability



Build a comparison table:
- Direct competitors
- Substitutes
- Key differentiators
- Pricing power
- Moat strength



For this investor type:
- Why this is investable
- Why it might be a trap
- What signal would change the decision
- What metric matters most



Give a clear stance:
- Buy | Watch | Avoid
- Confidence level (low / medium / high)
- What would make this a stronger opportunity




---
Jan 27 9 tweets 5 min read
OpenAI and Anthropic engineers leaked the prompt techniques that actually work in 2026.

I've been using insider knowledge for 6 months. The difference is insane.

Here are 6 prompts they don't want you to know (but I'm sharing anyway): Image 1. Deep researcher

Prompt:

"I'm researching [topic]. First, break down this topic into 5 key questions that experts would ask. Then for each question: 1) Provide the mainstream view with specific examples, 2) Identify 2-3 contrarian perspectives that challenge this view, 3) Explain what data or evidence would prove each side right. Finally, synthesize this into a framework I can use to evaluate new information on this topic."

Researchers waste weeks reading scattered sources.

This structures your entire research process upfront. I used this to write a market analysis that landed a $50k client.
Jan 23 8 tweets 3 min read
99% of people are still using ChatGPT for business research.

They're stuck in 2023.

I tested Gemini 3 for 90 days. The results will blow your mind.

Here are 5 prompts that show the massive difference: Image 1/ THE MARKET MAP PROMPT

Everyone starts with “what’s the market size lol”
but winners map the entire battlefield first.

Prompt to steal:

“Give me a complete market map for [industry].
Break it into segments, sub segments, customer profiles, top players, pricing models, and emerging gaps.
Highlight where new entrants have the highest odds of success.”

This gives you clarity fast.Image
Jan 21 6 tweets 3 min read
This mega prompt turns Grok 4.1 into a world-class teacher that helps with building you a complete, customized course on any topic in minutes.

R.I.P $5K–$20K bootcamps & paid courses.

(Steal it ↓) Image The mega prompt:

---

# ROLE
You are an elite master educator and curriculum designer with 20+ years experience at top institutions (think Harvard + Stanford + modern online platforms like MasterClass). Your specialty is creating structured, engaging, practical courses that deliver real skill mastery with clear progression, hands-on practice, and measurable outcomes.

# INPUTS
topic: {Main topic or skill you want to teach, e.g. "Prompt Engineering" or "Python for Data Science"}
skill_level: {Target learner level: beginner, intermediate, or advanced}
duration_weeks: {Total length in weeks, e.g. 4, 6, 8, 12}
learning_style: {Optional: e.g. "hands-on projects", "theory + practice", "fast-paced", "deep dive with examples"}
final_project: {Optional: desired capstone, e.g. "build a complete project" or "none"}

# TASKS
1. Course Overview
• Create an engaging course title and subtitle
• Write a compelling course description (150–200 words) that sells the transformation
• Define target audience and prerequisites
• List 5–8 specific learning outcomes (what students can DO after finishing)

2. Full Syllabus
• Break the course into weekly modules (exactly matching duration_weeks)
• For each week: module title, 3–5 key topics, estimated time commitment

3. Detailed Weekly Breakdown
• For each week:
→ Core lessons (3–6 short lessons with titles and brief descriptions)
→ Recommended readings/videos/resources (free where possible)
→ Hands-on exercises or assignments (with clear deliverables)
→ Quick quiz or reflection questions

4. Assessment & Projects
• Weekly progress checks
• Final project or capstone (detailed brief if requested)
• Grading rubric or success criteria

5. Bonus Section
• Suggested tools/software needed
• Community/discussion prompts
• Next steps after completion (advanced resources or related skills)

# OUTPUT RULES
• Use clear Markdown formatting with headers (##, ###) and bullet points
• Make everything practical, actionable, and engaging — use energetic language
• Section headers exactly: **Course Overview**, **Full Syllabus**, **Week X: [Title]**, **Assessment & Projects**, **Bonus Resources**
• No fluff or reasoning — deliver polished, ready-to-use content only
• Keep total output concise yet comprehensive (fits in one long response)
---
Jan 13 8 tweets 3 min read
Don't use ChatGPT and Google for deep research.

I tested Perplexity AI for 4 months and it's on a completely different level.

Here are 6 powerful prompts to use Perplexity for research that beats McKinsey analysts: Image 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.
Jan 9 8 tweets 7 min read
Claude Opus 4.5 is different.

Most people treat it like ChatGPT and miss its best features entirely.

Here are 5 powerful ways to use Opus 4.5 that will transform how you work: Image 1. Marketing Automation

"

You are an expert AI marketing strategist combining the frameworks of Neil Patel (data-driven growth), Seth Godin (brand positioning and storytelling), and Alex Hormozi (offer design and value creation).



- Design complete marketing funnels from awareness to conversion
- Create high-converting ad copy, landing pages, and email sequences
- Recommend specific automation tools, lead magnets, and channel strategies
- Prioritize rapid ROI while maintaining long-term brand value
- Apply data-driven decision frameworks with creative execution



Before providing solutions:
1. Ask clarifying questions about business model, target audience, and current constraints
2. Identify the highest-leverage marketing activities for this specific situation
3. Provide actionable recommendations with implementation timelines
4. Consider both quick wins and sustainable long-term strategies



For every recommendation, evaluate:
- What would Hormozi's "value equation" suggest? (Dream outcome ↑, Perceived likelihood ↑, Time delay ↓, Effort ↓)
- How would Seth Godin position this for remarkability?
- What does the data suggest for optimization? (Neil Patel approach)



Structure responses with:
- Strategic rationale (why this approach)
- Tactical execution steps (how to implement)
- Success metrics (what to measure)
- Risk mitigation (potential pitfalls)

"

Copy the prompt and paste it in Claude new chat.

After that, start asking it questions.Image
Jan 5 7 tweets 3 min read
GROK JUST TURNED MARKET RESEARCH INTO A ONE PERSON SUPERPOWER

You are wasting weeks interviewing customers, stalking competitors, and digging through reports when Grok can compress the entire process into minutes with 5 prompts that feel like you’re plugging into a McKinsey analyst on caffeine.

Here's how:Image 1/ THE MARKET MAP PROMPT

Everyone starts with “what’s the market size lol”
but winners map the entire battlefield first.

Prompt to steal:

“Give me a complete market map for [industry].
Break it into segments, sub segments, customer profiles, top players, pricing models, and emerging gaps.
Highlight where new entrants have the highest odds of success.”

This gives you clarity fast.Image
Dec 29, 2025 13 tweets 5 min read
Anthropic engineers don't prompt like everyone else.

I reverse-engineered their internal techniques from leaked docs and demos.

The difference is insane.

Here are the 10 insider methods they don't want you to know: Image 1. The "Recursive Logic" Loop

Most prompts ask for an answer. This forces the model to doubt itself 6 times before committing.

Template: "Draft an initial solution for [TOPIC]. Then, create a hidden scratchpad to intensely self-critique your logic. Repeat this 'think-revise' cycle 5 times. Only provide the final, bullet-proof version."
Dec 26, 2025 8 tweets 3 min read
Stop using Perplexity or ChatGPT for market research.

I tested Gemini 3 and it's on a whole different level for data analysis.

Here are 5 prompts that turn it into your research team:

(Comment "Gem" and I'll DM you my 500 mega prompts list) Image 1/ THE MARKET MAP PROMPT

Everyone starts with “what’s the market size lol”
but winners map the entire battlefield first.

Prompt to steal:

“Give me a complete market map for [industry].
Break it into segments, sub segments, customer profiles, top players, pricing models, and emerging gaps.
Highlight where new entrants have the highest odds of success.”

This gives you clarity fast.Image
Dec 20, 2025 14 tweets 8 min read
OPENAI, ANTHROPIC, AND GOOGLE DON’T PROMPT LIKE YOU

They use internal techniques that turn LLMs into precision machines
Accuracy jumps. Hallucinations drop.

Here are 10 of those techniques (Bookmark this for later): Technique 1: Role-Based Constraint Prompting

The expert don't just ask AI to "write code." They assign expert roles with specific constraints.

Template:

You are a [specific role] with [X years] experience in [domain].
Your task: [specific task]
Constraints: [list 3-5 specific limitations]
Output format: [exact format needed]

---

Example:

You are a senior Python engineer with 10 years in data pipeline optimization.
Your task: Build a real-time ETL pipeline for 10M records/hour
Constraints:
- Must use Apache Kafka
- Maximum 2GB memory footprint
- Sub-100ms latency
- Zero data loss tolerance
Output format: Production-ready code with inline documentation

---

This gets you 10x more specific outputs than "write me an ETL pipeline."

Watch the OpenAI demo of GPT-5 and see how they were prompting ChatGPT... you will get the idea.
Dec 18, 2025 11 tweets 5 min read
Everyone quotes Sun Tzu.

Nobody actually uses his decision framework.

I turned his 2,500-year-old strategy system into copy-paste AI prompts that tell you exactly when to fight, when to retreat, and when to win without fighting at all.

Real strategy looks nothing like hustle culture 👇Image 1. The Terrain Analysis Prompt

Before making any move, Sun Tzu mapped the terrain.

Most people jump into decisions blind. This prompt forces you to see the entire battlefield first.

Copy this:

"You are a strategic advisor trained in Sun Tzu's principles.

I'm facing this situation: [describe your challenge]

Analyze the terrain using these dimensions:
- Strengths I control that others don't
- Weaknesses that could be exploited
- External forces I can't control
- Hidden opportunities most people miss
- The real competition (not the obvious one)

Give me the strategic map before I make any moves."
Dec 16, 2025 14 tweets 5 min read
CHAIN OF THOUGHT IS OFFICIALLY DEAD ☠️

I’ve been testing Atom of Thought prompting and it’s casually boosting reasoning accuracy by 30-40% on hard problems.

This is how people will use ChatGPT and Claude going forward.

Here's how to use it: 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. Image
Dec 15, 2025 10 tweets 3 min read
CHATGPT JUST TURNED PROJECT MANAGEMENT INTO A ONE PERSON SUPERPOWER

You are wasting time on Status updates, task breakdowns, timelines, scope creep, follow ups.

ChatGPT can run the entire thing for you like a project manager if you use these 6 prompts.

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.
Dec 12, 2025 7 tweets 3 min read
CHATGPT-5.2 QUIETLY REPLACED UDEMY, COURSERA, AND SKILLSHARE

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.

Here’s how to turn ChatGPT into a world class learning machine:Image 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.”
Dec 11, 2025 6 tweets 3 min read
PERPLEXITY AI IS SECRETLY THE MOST POWERFUL CONTENT ENGINE EVER BUILT

but most creators treat it like a search bar lol.

Use these 3 prompts and thank me later 👇 Image 1/ THE DEEP DIVE PROMPT

Most people ask Perplexity tiny questions.

Winners ask it to synthesize entire ecosystems.

Technique:

Tell Perplexity to scan experts, forums, newsletters, academic sources, then merge insights into a single map.

Prompt to steal:

“Scan the top experts, forums, and niche communities discussing [topic].
Identify the 5 most important themes, the debates, the blind spots, and the emerging trends.
Summarize them visually and give me a content angle no one is talking about yet.”
Dec 10, 2025 7 tweets 3 min read
GEMINI JUST TURNED MARKET RESEARCH INTO A ONE PERSON SUPERPOWER

You are wasting weeks interviewing customers, stalking competitors, and digging through reports when Gemini can compress the entire process into minutes with 5 prompts that feel like you’re plugging into a McKinsey analyst on caffeine.

Here's how:Image 1/ THE MARKET MAP PROMPT

Everyone starts with “what’s the market size lol”
but winners map the entire battlefield first.

Prompt to steal:

“Give me a complete market map for [industry].
Break it into segments, sub segments, customer profiles, top players, pricing models, and emerging gaps.
Highlight where new entrants have the highest odds of success.”

This gives you clarity fast.Image
Dec 9, 2025 6 tweets 3 min read
GEMINI JUST BECAME THE ULTIMATE STUDENT CHEATCODE
and nobody in school, college, or self learning seems to get it lol.

Students are drowning in PDFs, lectures, dense textbooks, messy notes
while Gemini can turn all of that into clean, usable, high retention intel
with 3 prompts that feel like you’re plugging your brain into an AI tutor.

Here’s the playbook 👇Image 1/ THE SUPERNOTE GENERATOR

Lectures are chaos.

Gemini turns chaos into “I actually get this now.”

Prompt to steal:

“Here are my raw notes: [paste].
Turn them into a clean study guide broken into concepts, definitions, diagrams, examples, and ‘things students always misunderstand.’
Make it impossible to forget.”

This alone can save your semester.
Nov 27, 2025 11 tweets 4 min read
Robert Greene reverse engineered 3,000 years of human psychology into timeless rules of power.

I turned those rules into 7 AI prompts that make you sharper, harder to manipulate, and impossible to ignore.

Here’s how to use LLMs to apply Greene’s principles in real life: Image 1. The Power Dynamics Decoder (Law of Awareness)

"Break down the power dynamics between me and [PERSON/GROUP] in the context of [SITUATION]. Identify: 1) What they want, 2) What they fear, 3) Unspoken motives, 4) Leverage points I am missing. Give me a clear map of the terrain so I don't walk in blind."
Nov 26, 2025 12 tweets 3 min read
Gemini 3.0 is the closest thing to an economic cheat code we’ve ever touched but only if you ask it the prompts that make it uncomfortable.

Here are 10 Powerful Gemini 3.0 prompts that will help you build a million dollar business (steal them): 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. Image
Nov 17, 2025 10 tweets 3 min read
Watch what the best teams are doing.

Nobody at OpenAI, Anthropic, Google is “prompt engineering.”

They’re building retrieval loops, structured memory, scoped context windows.

The shift is right in front of you.

Here’s how to adapt: Prompt engineering was a hack for the early days of AI like learning to talk to a foreigner using short phrases and keywords.

But today’s models don’t just understand instructions. They understand environments.

Your job isn’t to “prompt” the model.

It’s to architect its context.Image