In this Newsletter:

• Automate Your Job Before Somebody Else Does (Even If You Can't Code)

• AI Signal of the Week: Mastering AI Through Human Connection, Not Prompt Engineering

• AI Future Signal: Self-Improving AI Systems

• General Preferences: The Overlooked Power Tool in Claude
  

Years ago, I decided to try my hand at web design.

This was during the early days of the World Wide Web, when websites were built using clunky table-based layouts. Making sites display consistently across browsers felt like solving a Rubik's cube blindfolded.

Then vendors started selling templates built on top of WordPress and other content management systems.

Around this time, I joined an organisation building a new website. They'd hired a boutique agency—brilliant designers and coders charging £20,000 for the project.

The organisation needed to add a single menu item to the website. The agency's quote? £500 for this tiny change.

That's when I spoke up. "Look," I told the organisation, "you might not know this, but we could build an entire website for £2,000." "It won't be as uniquely crafted as what these specialists are offering, but it will absolutely do the job."

I got the contract.

The 'real' programmers were furious. They sent an angry email about how template users weren't proper developers and didn't understand 'real' coding. After that email, we never heard from them again.

Learning Through Support

My first foray into web design with templates wasn't exactly smooth sailing. I posted questions almost daily on the template vendor's forum, paying good money for their support.

I was really thankful that there were such responsive people around in the forum, always ready to assist.

But years later, I realised I only needed so much help because their code was buggy and overcomplicated. However, I persisted, learned, and grew.

The Hidden AI Opportunity: History Repeats (With a Twist)

Today's AI automation landscape mirrors that early web revolution perfectly. Tasks that currently command premium fees from specialists can now be handled by someone using AI tools.

Just like those early web templates, the tools aren't perfect yet. But they're good enough to get the job done—and they're improving rapidly.

Here's where today's opportunity is dramatically different. You don't need to pay for special access to experts anymore. You don't need to wait for someone to respond to your forum post.

AI is your infinitely patient teacher—and the more context you give it about your specific situation, the better it can help you.

The best AI systems won't be built by engineers. They'll be built by people who deeply understand the processes being automated. People like you.

Your Power Move: Start Building

Look at your daily workflows. Identify which processes could be automated. Start exploring tools like Flowise—an open source project built on top of LangGraph that lets you build AI agents right on your computer.

These agents can automate almost anything. No coding required. And unlike my early days with web templates, you now have an infinitely patient mentor: AI chatbots themselves.

This Week's Challenge

Choose one repetitive task in your workflow. Spend one hour exploring how tools like Flowise might automate it. Document what you learn.

Your expertise combined with AI tools creates an unbeatable advantage. The best time to start was yesterday. The second best time is now.

Subscribe at 10xbetter.ai for weekly insights on staying relevant in an AI-powered future.

AI Signal of the Week: Mastering AI Through Human Connection, Not Prompt Engineering

Research shows that even as AI capabilities soar, most people find these systems surprisingly difficult to work with effectively. AI professor Ethan Mollick puts it plainly: "To people who aren't used to using them, AI systems are surprisingly hard to get a handle on, resulting in a failure to benefit from their advice."

The answer isn't better prompt engineering. Mollick suggests treating AI as a peculiar new colleague rather than a tool to master. "Treat AI like an infinitely patient new coworker who forgets everything you tell them each new conversation", he explains in his latest article at One Useful Thing.

"Any recent frontier model is likely much better than any intern you would hire, but also weirder." If you're teaching AI adoption or want to understand how to work more effectively with these systems, give Mollick's article a read at One Useful Thing.

Subscribe at 10xbetter.ai for weekly insights on staying relevant in an AI-powered future.

AI Future Signal: Self-Improving AI Systems

I recently built a multi-agent system where one AI effectively debugged and optimised another's output. AI was improving AI in real time.

This experience came to mind when I saw this fascinating TikTok of former Google CEO Eric Schmidt discussing AI's future. Though from a while back, his timeline for AI advancement feels more relevant than ever.

Schmidt predicts that within five years, AI systems will begin improving their own code. By 2030-2032, he suggests we'll have systems achieving 90% of expert-level performance across multiple domains—from physics to chemistry to art.

Based on what I'm seeing in development today, we might reach these milestones even sooner. The implications for cybersecurity, biological research, and human productivity are profound.

You don't need to be a coder to start experimenting with multi-agent systems today. As we've covered elsewhere in this newsletter, building your own AI agents is surprisingly accessible—and could give you valuable insight into this rapidly approaching future.

Subscribe at 10xbetter.ai for weekly insights on staying relevant in an AI-powered future.

General Preferences: The Overlooked Power Tool in Claude

Today I want to shine a light on an overlooked feature which is actually still in beta in Claude.

General personal preferences, found under Settings, affect every conversation you have with Claude.

This cross-conversation influence makes them both powerful and potentially problematic.

The challenge lies in optimizing these preferences without inadvertently constraining (or poisoning!) future interactions.

My Optimized General Preference Setup

Through extensive testing, I've developed these core preferences:

1. Output Structure

1. Place primary content in artifact windows

2. Keep meta-commentary separate but adjacent

This separation delivers clean, copyable content while maintaining helpful context.

2. Writing Process

1. Start with core elements (thesis, main points, key direction)

2. Offer specific areas to develop further based on need

This framework encourages systematic development without forcing rigid structures.

3. Style Specifications

- Output in UK English, using Oxford comma

- Express ideas directly without comparative negation

- Avoid "This isn't X, it's Y" constructions

The Benefits

This configuration:

- Keeps outputs clean and immediately usable

- Maintains conversation flexibility

- Provides consistent structure without constraining content

- Enables efficient workflows across projects

Community Input Needed

What belongs in your general preferences?

Share your insights:

- Which preferences enhance all conversations?

- How do you maintain consistency without limiting flexibility?

- What settings have proven most valuable across different use cases?

Next week (if I still feel like it): Hands on with Claudes new Style feature

---

Subscribe at 10xbetter.ai for weekly insights on staying relevant in an AI-powered future.