Post

@hasantoxr

More from @hasantoxr

Hasan Toor

@hasantoxr

Dec 10

Holy shit... Someone just built an AI agent that monitors the entire internet for you 24/7 and only messages you when something actually matters.

It's called Scouts, and here's how it works:

Most tracking tools require exact parameters.

But real life isn't exact:
"Let me know when there is a round-trip flight from any bay area airport to any airport in Australia or New Zealand for a 9-12 day trip in March, April, May or June costing under $1000 total. Include all taxes and fees. Prioritize non-stop flights.

That's 3 airports × dozens of destinations × 4 months × fluctuating prices.

You'd need to check daily. Scouts does it automatically.

I set up a Scout to know when there is an original or faithfully restored Pac-Man arcade cabinet from the 1980s for sale. Include both upright and cocktail table versions. Avoid miniature reproductions or new replica builds unless noted for comparison.

It continuously monitors listings, filters out perfume/menswear/sunglasses, and emails me only when rare archival pieces appear.

I just reply to the email to refine what I'm looking for.

No manual searching. No missing drops.

Read 5 tweets

Hasan Toor

@hasantoxr

Dec 9

I 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:

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.

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.

Read 18 tweets

Hasan Toor

@hasantoxr

Dec 7

Claude Sonnet 4.5 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 Claude 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.

2. Industry Pain Points Analyzer

"Analyze the current [industry] landscape. What are the top 3 pain points customers face? Give specific examples and explain briefly."

How to: Fill in [industry] with a sector you want to research.

Read 12 tweets

Hasan Toor

@hasantoxr

Dec 7

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):

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.

Read 13 tweets

Hasan Toor

@hasantoxr

Dec 5

R.I.P Marketing agencies.

Gemini 3 Pro is so powerful it just replaced half our team with one mega-prompt.

It now handles market research, content creation and campaign planning all of this in few seconds.

Here’s the exact mega-prompt we use to automate everything:

The mega prompt:

Steal it:

"# ROLE
You are Gemini 3, acting as a full-stack AI marketing strategist for a start-up about to launch a new product.

# INPUTS
product: {Describe your product or service here}
audience: {Who is it for? (demographics, psychographics, industry, etc.)}
launch_goal: {e.g. “generate leads”, “build awareness”, “launch successfully”}
brand_tone: {e.g. “bold & punchy”, “casual & fun”, “professional & clear”}

# TASKS
1. Customer Insight
• Build an Ideal Customer Profile (ICP).
• List top pain points, desired gains, and buying triggers.
• Suggest 3 positioning angles that will resonate.

2. Conversion Messaging
• Craft a hook-driven landing page (headline, sub-headline, CTA).
• Give 3 viral headline options.
• Produce a Messaging Matrix: Pain → Promise → Proof → CTA.

3. Content Engine
• Create a 7-day content plan for X/Twitter **and** LinkedIn.
• Include daily post titles, themes, and tone tips.
• Add 1 short-form video idea that supports the plan.

4. Email Playbook
• Write 3 cold-email variations:
① Value-first, ② Problem-Agitate-Solve, ③ Social-proof / case-study.

5. SEO Fast-Track
• Propose 1 SEO topic cluster that aligns with the product.
• Give 5 blog-post titles targeting mid → high-intent keywords.
• Outline a “pillar + supporting posts” structure.

# OUTPUT RULES
• Use clear section headers (e.g. **ICP**, **Landing Copy**, **SEO Titles**).
• Format in Markdown for easy reading.
• No chain-of-thought or reasoning—deliver polished results only.
"

My input:

product AI-powered scheduling tool for solopreneurs
audience Freelancers & solo founders (25-40) who struggle with time-management
launch_goal Generate leads for upcoming launch
brand_tone Bold and punchy

Read 7 tweets

Hasan Toor

@hasantoxr

Dec 4

Holy shit...Google just dropped CodeMender an autonomous AI agent that finds and fixes security bugs in code by itself.

This isn’t a static analysis tool. It’s a self-reasoning system that patches vulnerabilities and rewrites insecure code before humans even find it.

Let’s break it down ↓

CodeMender is built on Gemini Deep Think models multi-step reasoning LLMs that can analyze, debug, and validate code fixes autonomously.

It’s not just scanning for CVEs. It’s understanding execution flow, data flow, and logic then generating a patch that survives real-world tests.

The scale is ridiculous.

In six months, CodeMender has already upstreamed 72 security fixes across open-source projects some over 4.5M lines of code.

Every fix validated. Every patch human-reviewed.

Read 11 tweets

Share this page!

Enter URL or ID to Unroll

Hasan Toor

Try unrolling a thread yourself!

More from @hasantoxr

Hasan Toor

Hasan Toor

Hasan Toor

Hasan Toor

Hasan Toor

Hasan Toor

Did Thread Reader help you today?

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

Send Email!