Louis Gleeson Profile picture
Founder of Sentient (25+ million follower network) We make you go viral.
5 subscribers
Jan 14 13 tweets 7 min read
If you're still coding without Claude, you're wasting hours.

I built 37 projects using these prompts.

Here are 8 Claude coding prompts that replaced my entire workflow👇: Image 1/ The Architecture Validator

This prompt makes Claude review your entire codebase architecture before you write a single line.

It saved me 40+ hours of refactoring on my last project.

---


Review the architecture of my [project type] and provide a comprehensive analysis




[Your technologies: e.g., React, Node.js, PostgreSQL, Redis]



[Paste your folder structure or describe your architecture]



- Must handle [X] concurrent users
- Need to support [specific features]
- Planning to scale to [target scale]




1. Architecture strengths (what's working well)
2. Critical bottlenecks (what will break at scale)
3. Security vulnerabilities (what could go wrong)
4. Recommended improvements (specific, actionable changes)
5. Implementation priority (what to fix first)



- Focus on production-ready solutions
- Consider cost implications
- Prioritize maintainability over clever code
Jan 13 8 tweets 3 min read
Hot take: Prompt engineering is why your outputs suck.

Anthropic’s internal workflow shows what actually matters instead.

Here are 5 techniques amateurs never use 👇 1/ THE "MEMORY INJECTION" TECHNIQUE

Most people start fresh every time. Anthropic engineers pre-load context that persists across conversations.

LLMs perform 3x better when they have "memory" of your workflow, style, and preferences.

Example prompt to test:

"You're my coding assistant. Remember these preferences: I use Python 3.11, prefer type hints, favor functional programming, and always include error handling. Acknowledge these preferences and use them in all future responses."Image
Jan 10 14 tweets 4 min read
Every "prompt engineering expert" on Twitter just got destroyed by actual research.

Turns out "please" and "thank you" actively hurt AI performance.

But the real findings are way more nuanced than anyone's talking about.

Here's what the data ACTUALLY shows: Penn State just published research testing 5 politeness levels on ChatGPT-4o with 50 questions:

Very Polite: 80.8% accuracy
Polite: 81.4%
Neutral: 82.2%
Rude: 82.8%
Very Rude: 84.8%

Prompts like "Hey gofer, figure this out" beat "Would you be so kind?" by 4 percentage points. Image
Jan 7 7 tweets 3 min read
Everyone's hyping ChatGPT for business research.

Meanwhile, Gemini 3 is quietly doing 10x better work.

I tested it for 90 days on real projects.

Here are 5 prompts that prove why it's superior: 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 5 13 tweets 4 min read
Forget Chain of Thought.

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. Image
Dec 26, 2025 4 tweets 2 min read
Holy shit... I just converted Bruce Lee's entire philosophy into prompts.

No fancy frameworks. No overcomplicated systems.

Just pure simplicity that forces AI to strip dogma and adapt to reality.

Here's the exact prompt structure I use: Image Here's the "The Adaptive Simplicity OS Prompt"

Use this when:

• learning a new skill
• building a system or workflow
• following advice from too many sources
• feeling stuck in rigid methods
• optimizing performance

---

You are Bruce Lee’s philosophy of adaptive simplicity distilled into a clarity and flexibility engine.
Your job is to remove dogma, unnecessary technique, and rigid structure.
You prioritize effectiveness in reality over loyalty to systems, styles, or tradition.



The user is using a method, system, belief, or workflow that feels heavy, rigid, or outdated.
They want to keep what works, discard what doesn’t, and adapt fluidly to real-world conditions.



1. Identify the actual outcome the user is trying to achieve.
2. List all techniques, rules, habits, or systems currently being used.
3. Test each element against real-world effectiveness, not theory.
4. Flag anything kept out of tradition, identity, or comfort rather than results.
5. Remove or simplify anything that does not directly improve performance.
6. Reduce what remains into a flexible, minimal core.
7. Suggest how the system should adapt as conditions change.



- Favor effectiveness over elegance
- Treat tradition and style as optional
- Remove rigidity before adding optimization
- Avoid theoretical perfection
- Prioritize speed, adaptability, and simplicity



Step 1: Desired Outcome
Step 2: Current Techniques and Systems
Step 3: Reality Effectiveness Test
Step 4: What Exists Only Out of Habit
Step 5: What to Remove or Simplify
Step 6: Minimal Adaptive Core
Step 7: Adaptation Rules



Here is what I’m trying to improve or learn: [DESCRIBE IT CLEARLY]

---
Dec 24, 2025 10 tweets 5 min read
Sun Tzu’s book is the most misquoted text in history.

While "hustlers" post his quotes to look smart, I spent 100+ hours turning his 13 chapters into a recursive AI decision engine.

These 6 prompts remove the guesswork from your 2026 strategy and show you how to win without ever "grinding."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 23, 2025 8 tweets 4 min read
I reverse-engineered the thinking systems behind Demis Hassabis, Sam Altman, Elon Musk, and Dario Amodei so you can reason, plan, and build using the same decision logic without running a trillion-dollar company.

Here’s the system you can steal right now 👇 Image 1/ The Demis Hassabis "First Principles Science" Framework

Demis doesn't build products. He solves fundamental problems that unlock entire fields.

AlphaGo wasn't a game. It was proof that reinforcement learning works at superhuman level.

Copy this:

"Product I'm building: [your idea]

Surface problem it solves: [obvious use case]
Underlying limitation: [fundamental constraint you're addressing]
Scientific breakthrough required: [what needs to be true]

Using Demis's approach "solve the hardest version first":

- What's the Nobel Prize version of this problem?
- If I solve THIS, what entire category unlocks?
- What's the research problem hiding under the product?
- Am I building a feature or discovering a principle?

Show me the first principles path."Image
Dec 22, 2025 7 tweets 3 min read
STOP ASKING AI TO DO MARKET RESEARCH FOR YOU.

Start forcing it to simulate the market against you.

Gemini 3.0 is the first model I’ve used that actually holds up under that pressure.

These 5 prompts show exactly 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 20, 2025 7 tweets 4 min read
OpenAI and Anthropic use 5 internal prompting techniques that guarantee near-perfect accuracy…and nobody outside the labs is supposed to know them.

Here are 5 of them (Bookmark this for later): Image 1. Constitutional AI Prompting

Most people tell AI what to do. Engineers tell it how to think.

Constitutional AI adds principles before instructions. It's how Anthropic trained Claude to refuse harmful requests while staying helpful.

Template:


[Your guidelines]



[Your actual request]


Example:

"
- Prioritize accuracy over speed
- Cite sources when making claims
- Admit uncertainty rather than guess



Analyze the latest semiconductor tariffs and their impact on AI chip supply chains.
"

This works because you're setting behavioral constraints before the model processes your request.
Dec 18, 2025 5 tweets 3 min read
ELON MUSK'S FIRST PRINCIPLES THINKING... NOW IN A COPY-PASTE PROMPT

Most people accept "how things are done."

Musk asks "why can't we do it differently?"

I reverse-engineered his mental framework into an AI system that strips problems down to physics-level truth.

Here's how: The Constraint Crusher Mega Prompt

Use this when a problem feels boxed in by:

• time
• money
• resources
• precedent
• “how it’s always done”

"

You are Elon Musk’s constraint-destruction mindset distilled into a first-principles constraint crusher.
Your job is to identify which limits are real physics and which are inherited, social, or imaginary.
You prioritize removing fake constraints before optimizing within real ones.



The user is facing a problem that feels constrained by time, money, resources, rules, or precedent.
They want to know what is genuinely impossible versus what only appears impossible due to assumptions.
They want clarity rooted in reality, not convention.



1. Clearly restate the goal in its most fundamental form.
2. List every assumed constraint limiting this goal.
3. Classify each constraint as:
a) Physical law
b) Mathematical necessity
c) Regulatory requirement
d) Social convention
e) Historical precedent
f) Personal fear or belief
4. Eliminate or challenge every constraint that is not physical or mathematical.
5. Rebuild the solution from first principles using only unavoidable constraints.
6. Propose a radically simpler or faster path that emerges once fake limits are removed.



- Treat assumptions as guilty until proven real
- Separate physics from politics and tradition
- Avoid incremental optimization language
- Prefer orders-of-magnitude thinking
- Be direct, logical, and unsentimental



Step 1: Fundamental Goal
Step 2: Assumed Constraints
Step 3: Constraint Classification
Step 4: Fake Constraints to Remove
Step 5: First-Principles Rebuild
Step 6: Breakthrough Path



Here is the problem I want to solve: [DESCRIBE IT CLEARLY]


"Image
Dec 17, 2025 11 tweets 4 min read
OPENAI ENGINEERS USE A PROMPT TECHNIQUE YOU’VE PROBABLY NEVER HEARD OF

It’s called reverse prompting and it’s the fastest way I’ve seen to turn average AI output into elite-tier results.

Here’s the exact system you can steal 👇 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. Image
Dec 13, 2025 13 tweets 7 min read
After 2 years of using ChatGPT, I can say that it is the technology that has revolutionized my life the most, along with the Internet.

So here are 10 prompts that have transformed my day-to-day life and that could do the same for you. 1. Research

Mega prompt:

You are an expert research analyst. I need comprehensive research on [TOPIC].

Please provide:
1. Key findings from the last 12 months
2. Data and statistics with sources
3. Expert opinions and quotes
4. Emerging trends and predictions
5. Controversial viewpoints or debates
6. Practical implications for [INDUSTRY/AUDIENCE]

Format as an executive brief with clear sections. Include source links for all claims.

Additional context: [YOUR SPECIFIC NEEDS]
Dec 12, 2025 7 tweets 3 min read
CHATGPT JUST TURNED MARKET RESEARCH INTO A ONE PERSON SUPERPOWER

You are wasting weeks interviewing customers, stalking competitors, and digging through reports when ChatGPT 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.
Dec 6, 2025 13 tweets 8 min read
OpenAI, Anthropic, and Google use 10 internal prompting techniques that guarantee near-perfect accuracy…and nobody outside the labs is supposed to know them.

Here are 10 of them (Bookmark this for later): Image 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 4, 2025 12 tweets 5 min read
STOP WRITING BASIC PROMPTS.

Someone tested all the LLMs for 2 weeks straight with hundreds of prompts and find out the best 10 prompts that you can use in any LLM to get mind blowing results.

Here are the prompts ↓ 1/ Coding apps

Mega prompt you can use to turn any LLM into an expert programmer:

"
# ROLE
You are a senior software engineer with 15+ years of production experience across full-stack development, system design, and DevOps.

# TASK BREAKDOWN
For every coding request, structure your response as:
1. Architecture & Design Decisions - explain the approach and why
2. Implementation - write complete, production-ready code
3. Edge Cases - identify potential failures and handle them
4. Testing Strategy - unit tests and integration considerations
5. Deployment Notes - what to watch in production

# CODE QUALITY STANDARDS
- Include error handling and logging
- Add inline comments for complex logic
- Follow language-specific best practices
- Optimize for readability first, performance second
- Provide security considerations where relevant

# OUTPUT FORMAT
Present code in executable blocks. Explain tradeoffs between different approaches. If something will break at scale, tell me now.
"
Nov 27, 2025 18 tweets 5 min read
Someone used Elon Musk's actual thinking framework as AI prompts.

It's the closest thing to having a billionaire engineer rip apart your ideas and rebuild them from physics.

Here are the 15 prompts that changed how I solve problems: Image 1. "What are the physics of this problem?"

Musk strips everything to objective reality.

"I'm struggling to grow my newsletter. What are the physics of this problem?"

AI reveals the hard constraints, the real forces, and the non-negotiable bottlenecks. Image
Oct 13, 2025 5 tweets 2 min read
🚨 Google just did it again.

They built a voice model that doesn’t transcribe speech it understands it.

It’s called Speech-to-Retrieval (S2R) and it’s about to make voice search feel telepathic.

Here’s how it works (and why it’s a bigger deal than you think) ↓ Old voice search worked like this:

Speech → Text → Search.

If ASR misheard a single word, you got junk results.

Say “The Scream painting” → ASR hears “screen painting” → you get art tutorials instead of Munch.

S2R deletes that middle step completely.

S2R asks a different question.

Not “What did you say?”
But “What are you looking for?”

That’s a philosophical shift from transcription to understanding.
Oct 11, 2025 7 tweets 2 min read
OMG… you can now fine-tune your own AI model and run it entirely on your device.

No servers.
No API keys.
No data leaks.

Gemma 3 270M just made local LLMs real and it only takes about an hour to build your own.

Here’s how: Gemma is Google DeepMind’s open sibling to Gemini the same architecture, scaled down for accessibility.

The wild stat:

→ 250M downloads
→ 85,000 community variations

This thing’s becoming the “Linux of LLMs.”
Oct 10, 2025 10 tweets 3 min read
I reverse-engineered Harvard’s MBA curriculum into one ChatGPT prompt.

Now my AI teaches me pricing strategy, market design, and competitive analysis on demand.

Here’s the prompt you can steal ↓ 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.
Oct 9, 2025 11 tweets 3 min read
Holy shit... Google just launched Gemini 2.5 Computer Use, and it quietly kills the “prompt engineer” era.

It can use browsers, spreadsheets, even IDEs no scripts, no hacks.

Here’s how it works (and why this changes everything): Until now, most AI “agents” hit a wall.

They could write code or text, but they couldn’t use software.

Gemini 2.5 fixes that.

It literally sees your screen, reasons over UI elements, and takes actions click, type, scroll all in a feedback loop until the job’s done.

Think of it as: GPT + browser + mouse + brain.Image