AI Second Brain Foundations (Class #2)

Michael Simmons

Sep 24, 2025

∙ Paid

The General AI Memory Problem

There is a prototypical AI usage pattern that most people follow over time:

You’ve used AI for a while.
You realize that prompt engineering (created instructions for AI) will only get you so far.
You also realize that you need context engineering (providing AI with info about you) in order to get the best results.
After months of procrastination, you finally create a profile about you and your company, which your AI can automatically access without you having to retype it for each prompt.
Once you’ve created it, you rarely go back to it and keep it up to date.

If this describes you, I have good news, bad news, and an opportunity.

Good news: You are ahead of 90% of people using AI.
Bad news: You are missing out on critical context you could be providing to AI.
Opportunity: You can get much better answers from AI.

The Problem With General AI Profiles

If you followed the steps above, you’ve created a general, static memory profile.

While this is a good first step, it has two serious flaws.

First, in real life, what really matters is specialized memory.

For example, consider how much what you share varies based on the context:

Talking to a therapist, you share personal details about your life you wouldn’t share publicly.
Talking to a teacher, you share specific learning challenges related to the class topic.
Talking with your team about strategy, you talk about opportunities, products, markets, ideas, and actions.

In each of these situations, your boilerplate bio will only take you so far. What you really need is a specialized memory.

Second, you need a dynamic memory rather than a static one.

For example:

As you learn a topic, you gain skills, mindsets, habits, and mental models. To be most helpful, AI needs to meet you where you were, not where you are.
As time goes by, you and your company and the market change every single day a little bit.

This begs many questions…

What areas in your life should you make specialized, dynamic profiles?
What process should you use to create them?
What process should you use to update them?

Enter today’s session…

Class Overview

In today’s rapidly evolving AI landscape, we’re witnessing exponential growth across multiple dimensions - from pre-training scaling laws to inference scaling, convergence effects, and tool-use capabilities. While this creates unprecedented opportunities, it also demands that we develop more sophisticated approaches to learning and memory management.

The traditional approach of simply collecting prompts or storing general information is no longer sufficient. Instead, we need to think strategically about creating specialized memory profiles that provide AI with the precise context it needs to deliver truly personalized, high-value responses in the most important context areas in our lives.

Today’s session focused on developing “meta-memory” as a foundational skill. Just as we learned that learning how to learn is crucial in a rapidly changing world, we now need to consciously design dynamic memory systems that can be updated, specialized for different contexts, and optimized for the specific challenges we face.

The opportunity window is significant. While many are still focused on basic prompting, those who master context engineering and specialized profiles now will be positioned to create agent-like systems that replicate their unique expertise and workflows - potentially turning their core competencies into scalable software solutions.

All students walked away with a prompt I shared to help them automatically create a specialized memory prompt for any context.

Specifics On What We Covered

Explored exponential scaling laws driving unprecedented AI development acceleration
Introduced meta-memory as a new foundational skill for conscious memory design
Created specialized memory profiles for specific contexts and applications
Demonstrated learning profile creation using real-time automation challenges
Developed fashion/style profiles through interactive questioning and taste refinement
Built specialized prompts for breakthrough knowledge discovery through disconfirming evidence
Practiced voice-enabled profile creation for dynamic learning experiences
Analyzed client case histories for therapeutic and consulting applications
Examined the entrepreneurial opportunity to transform expertise into agents
Integrated specialized profiles with project management and automation workflows

The Bottom Line: We’re moving beyond basic AI usage toward sophisticated context engineering. Those who master specialized learning profiles now will have significant advantages as AI capabilities continue to expand exponentially. The key is identifying your unique expertise areas and systematically building memory systems that allow AI to replicate and enhance your specialized knowledge and decision-making processes.

AI-Generated Podcast Summary Of The Class

1×

0:00

-14:33

How To Access The Full Course

Free members get a 30-minute video preview of the class.

Basic paid members get:

Access to a monthly 90-minute class for 12 months.
Prompt to create specialized profiles for any context
Class resources (chat transcript, slides, full class transcript, prompts that are shared)

Said differently, paid members get access to 18 hours of learning for just $20/month or $149/year. This comes to just $8 for every hour of live class. And this doesn’t even include our other live monthly class, Augmented Awakening, or over $2,500 in other perks (20+ prompts, 7 courses, 3 books, blockbuster article library, etc).