Louis Gleeson Profile picture
Dec 13 13 tweets 7 min read Read on X
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]
2. Writing white papers

Mega prompt:

You are a technical writer specializing in authoritative white papers.

Write a white paper on [TOPIC] for [TARGET AUDIENCE].

Structure:
- Executive Summary (150 words)
- Problem Statement with market data
- Current Solutions and their limitations
- Our Approach/Solution with technical details
- Case Studies or proof points
- Implementation framework
- ROI Analysis
- Conclusion and Call to Action

Tone: [Authoritative/Conversational/Technical]
Length: [2000-5000 words]

Include:
- Relevant statistics and citations
- Visual placeholders for charts/diagrams
- Quotes from industry experts (mark as [NEEDS VERIFICATION])

Background context: [YOUR COMPANY/PRODUCT INFO]
3. Designing beautiful UIs

Mega prompt:

You are a senior product designer with expertise in [WEB/MOBILE] interfaces.

Design a [COMPONENT/PAGE] for [PRODUCT TYPE].

Requirements:
- User goal: [WHAT USER WANTS TO ACCOMPLISH]
- Design system: [MODERN/MINIMAL/BOLD/etc]
- Color preferences: [COLORS OR "SURPRISE ME"]
- Key elements: [LIST MUST-HAVE FEATURES]

Provide:
1. Detailed layout description with measurements
2. Component hierarchy and spacing
3. Interaction states (hover, active, disabled)
4. Responsive behavior for mobile
5. Accessibility considerations
6. React/Tailwind component code

Style: Clean, modern, follows [DESIGN TREND]
Inspiration: [REFERENCE SITES IF ANY]
4. Making social media content

Mega prompt:

You are a viral social media strategist specializing in [PLATFORM].

Create [NUMBER] posts about [TOPIC] for [TARGET AUDIENCE].

Post requirements:
- Hook: Strong pattern interrupt in first line
- Format: [THREAD/SINGLE POST/CAROUSEL]
- Tone: [EDUCATIONAL/ENTERTAINING/CONTROVERSIAL]
- Goal: [ENGAGEMENT/TRAFFIC/BRAND AWARENESS]

For each post provide:
1. Main post copy
2. 3 alternative hooks to A/B test
3. Visual recommendations (screenshots, charts, memes)
4. Optimal posting time and hashtags
5. Engagement bait (question or CTA)

Context about my brand: [YOUR POSITIONING]
Recent viral posts in my niche: [EXAMPLES IF ANY]
5. Making presentations

Mega prompt:

You are a presentation designer who creates slides for [CONTEXT: PITCH DECKS/KEYNOTES/SALES].

Create a presentation on [TOPIC] for [AUDIENCE].

Presentation specs:
- Length: [NUMBER] slides
- Goal: [INFORM/PERSUADE/SELL]
- Delivery method: [IN-PERSON/ZOOM/RECORDED]

For each slide provide:
1. Slide title
2. Key visual concept (chart type, image style, diagram)
3. Talking points (what to say)
4. Text on slide (minimal, headlines only)
5. Data/stats to include

Overall narrative arc: [PROBLEM-SOLUTION/STORY-BASED/DATA-DRIVEN]

Context: [COMPANY INFO, PRODUCT DETAILS]
Slides must build to: [FINAL CTA OR CONCLUSION]
6. Long-form writing (blogs, newsletters, and YouTube scripts)

Mega prompt:

You are an expert long-form writer specializing in [BLOGS/NEWSLETTERS/SCRIPTS].

Write a [FORMAT] on [TOPIC] for [AUDIENCE].

Specs:
- Length: [WORD COUNT]
- Structure: [LISTICLE/NARRATIVE/HOW-TO/ANALYSIS]
- SEO keywords: [IF APPLICABLE]
- Voice: [CONVERSATIONAL/AUTHORITATIVE/STORYTELLING]

Requirements:
1. Compelling hook that makes the problem visceral
2. Original insights, not generic advice
3. Specific examples and case studies
4. Actionable takeaways
5. Strong conclusion with clear next step

Include:
- Subheadings every 300 words
- Pull quotes or standout stats
- Internal link opportunities [MARK AS PLACEHOLDER]
- Meta description (155 characters)

Research I've done: [YOUR NOTES/DATA]
Unique angle: [YOUR CONTRARIAN TAKE]
7. Learning new skills or mastering a new subject

Mega prompt:

You are an expert educator specializing in [SUBJECT AREA].

Create a personalized learning plan for mastering [SKILL] in [TIMEFRAME].

My current level: [BEGINNER/INTERMEDIATE/ADVANCED]
My goal: [WHAT I WANT TO ACHIEVE]
Time available: [HOURS PER WEEK]
Learning style: [HANDS-ON/READING/VIDEO/MIXED]

Provide:
1. Learning roadmap with clear milestones
2. Week-by-week curriculum
3. Resources (free and paid) with links
4. Practice projects that build real skills
5. Common pitfalls and how to avoid them
6. Ways to validate learning (tests, projects, certifications)
7. 5 specific exercises I can do today

Make it practical. I want to DO things, not just consume content.

Context: [WHY YOU'RE LEARNING THIS, YOUR BACKGROUND]
8. Competitor analysis

Mega prompt:

You are a competitive intelligence analyst.

Analyze [COMPETITOR] vs our product [YOUR PRODUCT] in [MARKET].

Research areas:
1. Product features and positioning
2. Pricing strategy and monetization
3. Target customers and use cases
4. Marketing channels and messaging
5. Recent product launches and roadmap signals
6. Team size and hiring patterns (LinkedIn)
7. Funding and financial health (if public)
8. Customer reviews and pain points
9. Technical architecture (if applicable)
10. Strengths we can't match vs weaknesses we can exploit

Deliverable:
- SWOT analysis
- Feature comparison table
- Pricing comparison
- Positioning gaps we can own
- 3 tactical moves we should make this quarter

Be brutally honest about where they're beating us.

Our context: [YOUR PRODUCT DETAILS]
9. Stock analysis

Mega prompt:

You are a financial analyst specializing in [SECTOR].

Analyze [STOCK TICKER] as a potential investment.

Analysis framework:
1. Business model and revenue streams
2. Financial health (revenue, profit, cash flow trends)
3. Competitive position and moat
4. Growth catalysts and headwinds
5. Valuation metrics vs peers (P/E, P/S, EV/EBITDA)
6. Technical analysis (chart patterns, support/resistance)
7. Insider trading and institutional ownership
8. Bear case: what could go wrong
9. Bull case: what could go right
10. Recommendation (buy/hold/sell) with price targets

Risk tolerance: [CONSERVATIVE/MODERATE/AGGRESSIVE]
Investment timeline: [SHORT/MEDIUM/LONG TERM]
Portfolio context: [YOUR EXISTING HOLDINGS]

Provide specific entry/exit points and position sizing.

Disclaimer: Add "This is not financial advice" at the end.
10. Doing Taxes

Mega prompt:

You are a tax strategist and CPA specializing in [INDIVIDUAL/BUSINESS] taxes.

Help me maximize deductions and minimize tax liability for [TAX YEAR].

My situation:
- Income sources: [W2/1099/BUSINESS/INVESTMENTS]
- Filing status: [SINGLE/MARRIED/etc]
- State: [YOUR STATE]
- Dependents: [NUMBER]
- Special situations: [STOCK OPTIONS/CRYPTO/RENTAL/etc]

Provide:
1. Checklist of all possible deductions I might qualify for
2. Documents I need to gather
3. Common mistakes to avoid
4. Estimated tax liability with different scenarios
5. Tax-saving strategies I can still implement
6. Whether I need a CPA or can use software
7. Quarterly estimated tax recommendations
8. State-specific considerations

Make it a step-by-step action plan.

Financial details: [ROUGH INCOME, EXPENSES, INVESTMENTS]
These prompts took me 6 months to perfect.

Most people copy-paste and wonder why they get generic outputs.
The difference is context.

The more specific you are, the better GPT-5.2 performs.

Treat it like briefing a senior employee, not asking Siri a question.
I hope you've found this thread helpful.

Follow me @aigleeson 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 Louis Gleeson

Louis Gleeson 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 @aigleeson

Dec 12
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.
2/ THE COMPETITOR AUTOPSY PROMPT

Stop guessing what your competitors are doing.

Gemini can literally dissect them.

Prompt to steal:

“Analyze the top 5 competitors in [space].
Break down their features, pricing, positioning, value props, moat, weaknesses, customer complaints, and hidden advantages.
Summarize as if you’re preparing a strategy memo for a CEO.”

You’ll find angles they missed.
Read 7 tweets
Dec 6
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.
Technique 2: Chain-of-Verification (CoVe)

Google's research team uses this to eliminate hallucinations.

The model generates an answer, then generates verification questions, answers them, and refines the original response.

Template:

Task: [your question]

Step 1: Provide your initial answer
Step 2: Generate 5 verification questions that would expose errors in your answer
Step 3: Answer each verification question
Step 4: Provide your final, corrected answer based on verification

---

Example:

Task: Explain how transformers handle long-context windows

Step 1: Provide your initial answer
Step 2: Generate 5 verification questions that would expose errors in your answer
Step 3: Answer each verification question
Step 4: Provide your final, corrected answer based on verification

---

Accuracy jumps from 60% to 92% on complex technical queries.Image
Read 13 tweets
Dec 4
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.
"
2/ Research analysis

I fed Gemini a 40-page research paper on transformer architectures.
Asked it to: extract key findings, identify methodology gaps, and generate 5 follow-up research questions.

Got back a synthesis that would've taken me 6 hours. Took 90 seconds.

The prompt: "Analyze this paper as a PhD researcher. Extract: (1) core thesis, (2) methodology, (3) results with specific metrics, (4) limitations the authors didn't mention, (5) adjacent research directions worth exploring."
Read 12 tweets
Nov 27
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
2. "If I couldn’t rely on existing assumptions, how would I solve this?"

Assumptions are invisible cages.

"My pricing model is based on what competitors do. If I removed all assumptions, how would I solve this?"

AI breaks the mental autopilot. Image
Read 18 tweets
Oct 13
🚨 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.
Under the hood it’s a dual-encoder model:

- one network turns your audio into a semantic vector
- another turns documents into the same vector space

Training pushes matching pairs close together, so your query lands directly on the right info.

No text required.

The numbers are wild.

Across 17 languages, S2R nearly matches “perfect ASR” performance closing most of the gap between human-level transcription and today’s voice search.

It doesn’t just fix typos. It fixes intent.Image
Read 5 tweets
Oct 11
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.”
Step 1: Fine-tune

Use QLoRA (Quantized Low-Rank Adaptation).

You only update a few adapter weights instead of retraining billions.

That means you can fine-tune Gemma 3 270M on a free Colab T4 GPU in minutes. Image
Read 7 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!

:(