Louis Gleeson Profile picture
Aug 16 9 tweets 3 min read Read on X
RIP SEO.

a16z just called it: traditional search is dead.

Welcome to Generative Engine Optimization (GEO).

Now people ask AI, not Google and if you’re not in the answer, you don’t exist.

Here's how to add this 1 small file to your website to get your brand in any LLM:
SEO was for Google.

AIO (AI Optimization) is for Large Language Models.

Right now, LLMs are crawling the web and pulling content into their “knowledge”.

If you don’t guide them, they might ignore you or use outdated info. Image
Why it matters:

• AI search is exploding (ChatGPT Search, Perplexity, Arc Search, etc.)
• Models build answers from web data
• If you’re not optimized, you’ll be invisible in AI responses even if you rank on Google
How to create your llm.txt:

1. Open a plain text editor → Name it llm.txt
2. Add your rules:

"
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

Sitemap: yoursite.com/sitemap.xml
Data-source: yoursite.com/ai-dataset.json
"
3. Include AI-friendly resources:

• JSON/CSV/Markdown with facts, summaries, product info
• Keep it updated

4. Upload it to your site’s root domain:


5. Test it in your browser to make sure it’s publicyoursite.com/llm.txt
Example AI data source (JSON):

[
{
"name": "Your Company",
"description": "AI-powered platform for...",
"founded": "2023",
"website": ""
}
]

This gives LLMs clean, structured data to use in answers.yoursite.com
Prompt to use for making LLM.TXT file in a second:

"
I want to create an LLM.TXT file for my website so it ranks across all Large Language Models (ChatGPT, Claude, Perplexity, Gemini, etc.).

Ask me for:

- My website URL
- Sitemap URL
- Any structured data URLs (JSON, CSV, or Markdown)
- Any content I want to restrict from AI crawlers
- Any preferred crawlers to block or allow

Then, generate a complete LLM.TXT file with:
- Allow/Disallow rules for major AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, etc.)
- Links to my sitemap(s) and structured data
- Clear comments explaining each section

Make sure it’s optimized for maximum AI visibility and compliant with current AI crawler standards.
"
Google SEO took 20 years to mature.

AI SEO is just starting.

The brands that act now will own the AI answer box for years.

- Add llm.txt today.
- Tomorrow, you’ll be the default answer in AI.

Learn more here:
llmstxt.org
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

Aug 14
The most in-demand skill right now isn’t coding.

It’s prompting.

One line of text can now get you:

• code
• designs
• strategies
• full apps

Here’s how to write prompts that actually work:
You’re going to learn:

• What great prompts look like
• How to structure them for better output
• 10+ expert techniques that boost accuracy, logic & creativity

Whether you're a beginner or pro this will level you up.
1. Beginner: Zero-Shot Prompting

Give the model a clear, specific instruction.

✅ "Summarize this article in 3 bullet points."
❌ "What do you think about this?"

Clarity > Creativity at this stage. Image
Read 17 tweets
Aug 13
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. Learn anything from a 20-year expert even if you're clueless

"Pretend you are an expert with 20 years of experience in {industry/topic}. Break down the core principles a total beginner must understand. Use analogies, step-by-step logic, and simplify everything like I’m 5."
2. Brutally honest thought partner to sharpen your thinking

"Act as my personal thought partner. I’ll describe {my idea/problem}, and I want you to question every assumption, point out blind spots, and help me evolve it into something 10x better."
Read 12 tweets
Aug 11
10 ChatGPT-5 prompts so powerful and useful, they feel illegal to use:

(Bookmark this for later 🔖)
1. Learn anything from a 20-year expert even if you're clueless

"Pretend you are an expert with 20 years of experience in {industry/topic}. Break down the core principles a total beginner must understand. Use analogies, step-by-step logic, and simplify everything like I’m 5."
2. Brutally honest thought partner to sharpen your thinking

"Act as my personal thought partner. I’ll describe {my idea/problem}, and I want you to question every assumption, point out blind spots, and help me evolve it into something 10x better."
Read 12 tweets
Aug 2
This is wild.

You can ask ChatGPT-4o to explain Warren Buffett’s portfolio, analyze market trends, and even spot risky stocks.

Here are 10 essential prompts for every trader:
1/ Market Analysis:

"Analyze the current trends in the stock market, focusing on [input sector or stock]. Identify any emerging patterns and suggest potential investment opportunities. Consider recent earnings reports and industry news in your analysis."
2/ Portfolio Diversification:

"Given a portfolio with a mix of [input current sectors or stocks], suggest strategies to diversify further while minimizing risk. Include potential sectors to explore and specific stocks to consider."
Read 12 tweets
Aug 2
Claude’s XML prompting system is one of the most underrated cheat codes in AI.

• tighter control
• clearer formatting
• zero hallucination

Here’s how to use it ↓
Why XML?

Claude was trained on structured, XML-heavy data like documentation, code, and datasets.

So when you use XML tags in your prompts, you’re literally speaking its native language.

The result? Sharper, cleaner, and more controllable outputs.

(Anthropic says that XML tag prompts gets best results)Image
Why it works:

✅ Clarifies intent
✅ Mimics Claude's training structure
✅ Boosts reasoning + structure
✅ Reduces hallucination

Now let’s dive into 5 🔥 real-world use cases:
Read 10 tweets
Jul 31
I finally understand how large language models actually work

After reading the 2025 textbook “Foundations of LLMs”

It blew my mind and cleared up years of confusion

Here’s everything i learned (in plain english): Image
To understand LLMs, start with pre-training.

We don’t teach them specific tasks.

We flood them with raw text and let them discover patterns on their own.

This technique is called self-supervised learning and it’s the foundation of everything.
There are 3 ways to pre-train:

→ Unsupervised: No labels at all
→ Supervised: Classic labeled data
→ Self-supervised: Model creates its own labels (e.g., “guess the missing word”)

LLMs use #3 it scales like crazy and teaches them language from scratch.
Read 19 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!

:(