This week, an entrepreneur friend gave me feedback on a blog and podcast series I did on a biography. He said the posts resonated with him because of the insights I shared. Connecting the dots between different people and periods was helpful and would be hard for him to do himself. And because the insights derive from the experiences of people who did what he’s attempting to do, but on a massive scale, they’re more valuable because the people’s outcomes make them more credible.

I appreciate my friend giving me his candid feedback. The books I read are available to everyone, so it surprises me when people value the connections I make between ideas in different books. Because I discovered those connections, I assume others have also done so, or could have. But I’m learning that’s not common. I suppose this is because of the effort required to find important ideas in the sea of unstructured text that is books. And because of the dispersed nature of books.

My takeaway is to lean more into sharing the connections between ideas in various books. It’s tremendously valuable to entrepreneurs.

I was chatting with a friend who’s an entrepreneur about AI workflows and learning tools. He told me about a new product from Google. Gemini Advanced just released its deep research feature, an AI research assistant. It uses Google’s Gemini large-language models to research complex topics on the internet and generate a comprehensive report of its findings. Google describes it as an “agentic system that uses Google’s expertise of finding relevant information on the web to direct Gemini’s browsing and research.” My friend told me a story about how he used it to help him learn about a topic. The tool provided him with a thirteen-page report that got him up to speed on the topic quickly.

What I like about this tool is that it gives you a step-by-step plan for how it plans to research the topic before it starts, and you can edit the plan if you need to. The tool then begins researching by searching for phrases, learns from those searches, and then searches for new phrases to learn more. It concludes by compiling everything it learned in a single document, which can be exported in a Google Doc. Google's blog post goes into more detail and includes a demo. The downside is that the tool costs $20 per month. But you can try it for free for 30 days, which is what I’m doing.

Researching things online can be a pain; it’s not something everyone is good at. I’m excited about this tool because it has the potential to help everyone efficiently find the information online that’s helpful to them.

I was chatting with a friend about how many books the “book library” MVP would need to include to be useful to entrepreneurs. He was thinking thousands or tens of thousands. However, I think it’s much less than that if you consider the number of books a person can read on their own. I’d imagine the average entrepreneur would get value from the MVP if a few hundred or even as few as one hundred books were included.

Let’s look at some numbers to demonstrate this, using my experience with this project as an example. Since February of this year, I’ve read 50 books, mostly biographies. By the end of the year, I aim to read 52 books, 1 per week on average.

Assuming I keep up that pace indefinitely, here’s how many books I’ll have read over various periods:

• Year 1: 52
• Year 2: 104
• Year 3: 156
• Year 4: 208
• Year 5: 260
• Year 10: 520
• Year 15: 780
• Year 20: 1,040
• Year 30: 1,560
• Year 40: 2,080
• Year 50: 2,600

I could read about 2,600 books at the absolute most, and that’s over 50 years. Even cracking 1,000 books would take me 20 years. And that’s reading a book a week, which my friends and family think is aggressive.

So, let’s say a founder reads half as fast: 2 books a month, or 26 books a year. Take all those numbers and cut them in half: 4 years to reach 100, 19 years to reach 500, and 38 years to reach 1,000.

Considering these figures, I think the “book library” could be hugely valuable to myself and other entrepreneurs. If I could use this tool to access the wisdom in a few hundred biographies to help me overcome hurdles, that would be the equivalent of several years of reading a book a week to acquire the same wisdom (assuming I remembered all of it). If the library included 1,000 books, it would be like accessing 20 years of reading.  

I love reading. It’s my favorite way to learn. But it’s not a time-efficient way of learning. Reading is powerful for entrepreneurs perpetually short on time and always looking for solutions to pressing problems, but it’s not a time-efficient problem-solving tool.

I’m excited about the value this tool can offer to entrepreneurs. It could be a great learning and problem-solving tool for entrepreneurs—and one that’s time efficient. It doesn’t need thousands of books to be valuable when it launches. A few hundred or even a hundred could give entrepreneurs access to the wisdom they would otherwise have to spend several years reading books to acquire.

Reading is valuable and something I plan to do as long as possible. I don’t want this tool to replace reading, I want it to complement it by pointing entrepreneurs to the right information in the right book at the exact time they need it.

This week, I was talking to my engineering friend, and he mentioned that he’d figured out a way to improve the output of his AI responses. He showed me how changing the prompt had resulted in a significantly improved response on something he was working on. But his insight was about how he improved the prompt. He asked AI to write the prompt for him! It returned a better prompt, which resulted in a better response. It was akin to him saying, Show me how to ask you questions in a way you understand best. Later in the week, I tuned in to a webinar in which the presenter used a similar technique to generate his prompts. I was hearing the same technique from two credible people in the same week.

I’ve been trying to improve my prompts for a few months, but I never considered this approach. I tried it today while I was using AI to help me with some tasks, and the results were much better. I’ve read and listened to a lot of stuff about prompting over the last few months, but this is probably the one thing that’s improved my prompting the most.

Going forward, I’ll ask AI to write or edit my prompts for me.

One thing that resonated with me in Warren Buffett: Inside the Ultimate Money Mind was the idea of studying failure. The book mentions that Charlie Munger studied failure to improve his decision-making. Munger studied the failures of others as a way of understanding thinking errors, which is studying psychology.

This got me thinking. I want to be more intentional about studying failure. I get excited about hearing what worked from entrepreneurs, but I need to be equally (or more) excited to learn about their failures and the why behind them. I’m really curious about psychology and want to keep improving my own decision-making, so this approach is appealing.

I think the first step is to regularly analyze my own failures and mistakes. I’m going to put some thought into ways I can make this a habit and see if I can adopt strategies others have used successfully.

I’m reading Warren Buffett: Inside the Ultimate Money Mind, which is a book about the mindset of Warren Buffett and other investors. One of the things it discusses is how Buffett and other investors make decisions. Robert Hagstrom points out that to understand psychology is to understand human decision-making. That’s why successful investors like Charlie Munger studied psychology to improve their own decision-making.

I’ve never thought much about psychology,  but this book got me thinking about it in relation to entrepreneurship—specifically, entrepreneurial wisdom. In this post, I shared that wisdom is the ability to apply knowledge in a manner that aligns with the outcome you desire. Wisdom means changed behavior and improved decision-making—knowing what to do and when to do it.

I’m always looking for ways to improve my decision-making (and share what I learn). But I’ve never really thought about trying to understand psychology to accomplish this until now. Hagstrom has me interested in learning more about psychology.

I’m going to try to find one of two books about psychology and add them to my reading list.

As I was poking around on the internet over the holiday, a book written by an indie hacker entrepreneur caught my eye. Traditional places like Amazon don’t sell the book. Instead, this entrepreneur is not only self-publishing but also self-distributing the book—the only place you can buy it is his website. I’ve seen this before, but it definitely piqued my interest.  

The founder does two things that made me lean in more (and want to purchase his book). First, he posts stats about book sales: total books sold since launch, total revenue generated, and number of books sold today were prominent. I hadn’t seen this before, and I loved it. I took it as his way of communicating how much value has been provided to others—in the aggregate and recently. And it’s more social proof.

Second, the book is never finished. He’s constantly updating it as he learns new things. He shows the last time he updated the content and the last time he published new book files. The book was written about five years ago, his last update was within the last twenty-four hours, and new files were published today (as of this writing). I like this approach because his book content stays current. I’ve never seen this before.

This entrepreneur is doing a great job of marketing his book, and he got me excited about it. I’m going to grab a copy and add it to my booklist.

I did a lot of reading this weekend for my “book library” MVP. I dug deep into retrieval augmented generation (RAG) and learned some helpful things:

• There are different variations of RAG: GraphRAG, StructRAG, LightRAG, etc. New versions have been introduced every few months this year. Which is the right one depends on your use case.
• Normal RAG isn’t great for a large data set like a book. It struggles to make connections when presented with a lot of data.  
• RAG’s results are better when you feed it relationships in a data set via a schema. GraphRAG, StructRAG, and LightRAG try to make up for this by using a knowledge graph to index the information better, which leads to understanding the data better and providing better results.

I’m realizing that how the information gets indexed in large data sets is critical, especially if I want to query across lots of dense data sets like books. Thinking about why entrepreneurs with photographic memories have an edge, I decided that their minds have done a superior job of indexing everything they’ve consumed and making nonobvious connections across the data. Those connections lead to unique insights that lead to creative solutions to problems or actions to get closer to their goal.

This weekend highlighted that I need to focus on and understand how information gets indexed as I evaluate RAG and other alternatives.

Today I read an article about a hack that helps you learn better. It suggests writing a one-page summary after you’ve read ten pages of a book because this increases your retention by 50%. The idea is that to learn, you must stretch yourself. You’re forced to do that if you have to process and organize what you consumed and then express your understanding in writing.

A few months back, I was writing a series of five or so blog posts for every biography or autobiography I read. I created a digest of each book and then shared the important parts via the blog series. Then, I began using the blog series to create a podcast series.

I was doing multiple levels of distillation, which helped me uncover insights from each book and retain more about each founder’s journey that I’d read about. Doing all of this weekly wasn’t sustainable, and I want to find a more sustainable process for doing the same thing. That’s why I’ve created an MVP to help me create book digests.

I’m a fan of writing. It’s a powerful practice that helps me organize my thoughts. When I write about what I’ve read, it feels like a superpower. I identify core concepts and insights I wouldn’t have found by reading passively, I retain them, and I can share them with others.

Writing about what you’ve read is something everyone can do, but most won’t. It’s more work, but I think the reward is worth the effort.

I’m using Google AI Studio to run one of the MVPs for my book project. Google’s AI is called Gemini, and there are eight different Gemini large-language models (LLMs). Determining which would yield the best result was a concern. Google had thought it through, though: AI Studio has a compare feature: you can ask a question and select two LLMs, and Gemini will provide responses from both of them in a side-by-side view.

I’ve been testing prompting and system instructions this week, and the compare feature has been helpful. Seeing how the different LLMs respond to the same question is helping me narrow my choices faster.

Google AI Studio has limitations, but it’s a good tool for someone who is nontechnical and wants to fine-tune their AI experience.