Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

Cumulative metrics (since 4/1/24):

• Total books read: 40
• Total book digests created: 15
• Total blog posts published: 245
• Total audio recordings published: 103

This week’s metrics:

• Books read: 1
• Book digests created: 0
• Blog posts published: 7
• Audio recordings published: 0

What I completed this week (link to last week’s commitments):

• Read Warren Buffett: Inside the Ultimate Money Mind, a biography by Robert Hagstrom about Warren Buffett’s mentality
• Tested populating a database with data (my developer friend led this effort)
• Created sketch of UI
• Refined database tables and fields based on the test run
• Created idea bank for growth strategies
• Added to feature list based on idea bank
• Identified what I believe are the main reasons book-related applications have struggled to become part of users' daily habits and developed features to address these challenges

What I’ll do next week:

• Read a framework book or a biography or autobiography
• Update personal blog to link posts about the same book
• Get input from developers who’ve worked on similar projects
• Identify potential technologies for challenging features
• Ponder ways to communicate a founder’s journey more effectively
• Create a list of potential metrics for weekly updates that better reflect this project
• Share taxonomy drafts with one person

Asks:

• None

Week two hundred forty-five was another week of learning. Looking forward to next week!

Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

What I struggled with:

• I struggle to keep up with everything I’m learning about databases and AI. I’ll keep asking questions and researching to enhance my conceptual understanding. The joys of being a nontechnical founder! :)

What I learned:

• Using one AI model for the “book library” MVP likely won’t work. We’ll need to pick the best model for each specific task and devise a process to chain the tasks together to get the desired result.
• If the context is too large (i.e., I feed AI too much data), the quality of the results plummets. We’ve broken information down into smaller chunks that still turned out to be too large. We had to break the information down into even smaller chunks, which drastically improved AI’s output quality.
• When running an iterative addition loop with AI, we must store the results (i.e., keep snapshots along the way) to avoid results from a bad loop wiping out all the data from previous loops.  
• I can improve my AI response by asking AI to write prompts. More here.
• Launching with decent data is more important than launching when the data is perfect. More here.
• My blog posts have a much wider reach than I realized. When my blog posts are valuable, readers share them readily. I need to get this MVP launched so I can begin writing detailed posts and creating podcast episodes about what I’m learning from books.
• The vision for this project is starting to become clear: Create a world where more people can readily access and apply entrepreneurial wisdom to achieve economic mobility. See more here.
• I get excited sometimes and start thinking about cool features and the potential of this project. But creating this MVP isn’t easy. I must stay focused and get the minimum required features built and working first.

Those are my struggles and learnings from the week!

Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

Cumulative metrics (since 4/1/24):

• Total books read: 39
• Total book digests created: 15
• Total blog posts published: 238
• Total audio recordings published: 103

This week’s metrics:

• Books read: 1
• Book digests created: 0
• Blog posts published: 7
• Audio recordings published: 0

What I completed this week (link to last week’s commitments):

• Read a third book on David Ogilvy - a collection of his learnings about advertising
• Demoed first major feature for “book library” MVP
• Refined and ranked sub-feature list for “book library” MVP
• Defined data views for “book library” MVP
• Updated list of competitors for “book library” MVP
• Analyzed database sources for book data

What I’ll do next week:

• Read a framework book, biography, or autobiography
• Share taxonomy drafts with one person
• Refine list of fields for database tables
• Create idea bank for growth strategies

Asks:

• None

Week two hundred forty-four was another week of learning. Looking forward to next week!

Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

What I struggled with:

• No material struggles this week  

What I learned:

• I overestimated what I could get done during this holiday week. I need to get more realistic about where my time goes during holidays. I always think I’ll have lots of free time, but I never do.
• There’s no easy way for people to share what books they’ve read on their personal websites or blogs. You can share on platforms like Goodreads, but not your own.
• Entrepreneurs (anyone, really) can obtain books for free from many websites, but entrepreneurs don’t use them.
• Sharing what you’ve learned from books is a manual, inefficient process. If it were easier, I wonder if more people would share what they’ve learned from books they’ve read.
• Creating a tool to annotate a book isn’t as technically difficult as I’d thought.

Those are my struggles and learnings from the week!

Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

Cumulative metrics (since 4/1/24):

• Total books read: 38
• Total book digests created: 15
• Total blog posts published: 231
• Total audio recordings published: 103

This week’s metrics:

• Books read: 1
• Book digests created: 0
• Blog posts published: 7
• Audio recordings published: 0

What I completed this week (link to last week’s commitments):

• Read A Memo for the Children, a memoir by Samuel Newhouse Sr.
• Tested methods of storing parsed books in a database for my “book library” MVP

What I’ll do next week:

• Read a biography or autobiography
• Refine the sub-feature list for the “book library” MVP
• Define data views for the “book library” MVP
• Share taxonomy drafts with one person
• Create a list of competitors for the “book library” MVP

Asks:

• None

Week two hundred forty-three was another week of learning. Looking forward to next week!

Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

What I struggled with:

• No material struggles this week  

What I learned:

• The last MVP for the “book library” didn’t meet the mark. The issue was that we couldn’t get the data from the book. We think we’ve figured that part out. Now, the focus has turned to how to make data from books useful.
• Breaking down what’s needed for the next version of the “book library” MVP was helpful. I created a prioritized list of features and sub-features that crystallized what problems need solving and what needs to be built to create a superior solution.
• Making use of what someone has read in books usually involves their notes and highlights. Extracting my notes from physical books has been a painful problem since I began this project. I haven’t found an acceptable solution. Solving that problem is the highest priority because it’s the most painful problem and the biggest hurdle.
• A workflow management system for learning from books could add value for serious learners.
• Thinking through taxonomy is difficult. I’ve played with a few drafts but still haven’t landed on the right taxonomy.
• Looking at highly rated applications solving similar problems using AI gave me some great feature ideas and creative solutions to problems I hadn’t considered. After watching a founder demo his AI solution on YouTube, I borrowed some of his team’s ideas for my feature list.

Those are my struggles and learnings from the week!

Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

Cumulative metrics (since 4/1/24):

• Total books read: 37
• Total book digests created: 15
• Total blog posts published: 224
• Total audio recordings published: 103

This week’s metrics:

• Books read: 1
• Book digests created: 1 (using technology)
• Blog posts published: 7
• Audio recordings published: 0

What I completed this week (link to last week’s commitments):

• Read a second book on David Ogilvy—a collection of memos, letters, speeches, and interviews
• Created a book digest for David Allen’s Getting Things Done using the “book digest” MVP
• Tested prompts to improve the quality of digests created using the “book digest” MVP
• Tested different parsing methods as alternatives to retrieval augmented generation (RAG) for my “book library” MVP
• Tested prompts to improve the quality of responses from the “book library” MVP

What I’ll do next week:

• Read a biography or autobiography
• Test alternative setups for the “book library” MVP

Asks:

• None

Week two hundred forty-two was another week of learning. Looking forward to next week!

Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

What I struggled with:

• No material struggles this week.  

What I learned:

• Retrieval augmented generation (RAG) comes in various flavors (see here), and all of them have shortcomings. The main hurdle is that information indexing can’t be adjusted. It’s a bit of a black box. RAG might not be viable for the “book library” MVP.
• I thought Google Cloud Platform (GCP) was throttling my account last week, impacting the depth of query results from the Gemini LLM. The issue may have been that GCP’s RAG tools could not index a large data set like a book, which led to shallow responses.
• A database can structure and store information, which helps make the data more useful. A database needs a schema. A database might be a necessity for this project.
• The prepackaged solutions meant to save time are good for generic use cases. This project is individualized and may require more solutions to be built from scratch.

Those are my struggles and learnings from the week!

Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

Cumulative metrics (since 4/1/24):

• Total books read: 36
• Total book digests created: 14
• Total blog posts published: 217
• Total audio recordings published: 103

This week’s metrics:

• Books read: 1
• Book digests created: 1 (using technology)
• Blog posts published: 7
• Audio recordings published: 0

What I completed this week (link to last week’s commitments):

• Read David Ogilvy’s autobiography
• Read highlights from David Allen’s Getting Things Done
• Read highlights from Tiago Forte’s Building a Second Brain
• Read two resources on prompt engineering
• For my “book library” MVP, created a separate agent and RAG to index each book instead of one agent and RAG to index multiple books
• Tested prompts and system instructions to improve the quality of responses from the “book library” MVP
• Created one book digest using the “book digest” MVP
• Tested prompts and system instructions to improve the quality of digests created using the “book digest” MVP

What I’ll do next week:

• Read a biography or autobiography
• Test alternative agent setups with RAG for the “book library” MVP
• Ask AI developers about RAG alternatives
• Create a book digest for David Allen’s Getting Things Done using the “book digest” MVP

Asks:

• None

Week two hundred forty-one was another week of learning. Looking forward to next week!

Current Project: Reading books about entrepreneurs and sharing what I learned from them

Mission: Create a library of wisdom from notable entrepreneurs that current entrepreneurs can leverage to increase their chances of success

What I struggled with:

• No material struggles this week.  

What I learned:

• Getting the “book library” MVP to provide quality results that add value is the priority. After that’s accomplished, I can start thinking about how to put it in the hands of other users. Trying to figure out the path to allowing others to use it publicly was premature. I need to get this thing working and adding value first; then I can figure out how to share it.
• I’ve been reading up on retrieval augmented generation (RAG) because the MVP isn’t working as intended. RAG has more limitations when you feed it a ton of information (e.g., multiple books) than I initially thought. It struggles to make connections between related information, but that’s essential. If the MVP can’t do that, providing value-added responses will be hard.
• There’s a good chance that the Google Cloud Platform throttling of my account is impacting the depth of results I get. This is frustrating because you don’t get a warning or confirmation of throttling.
• AI is good at many things, but it isn’t yet good at making sense of large, unstructured text data sets like books. Creating a structure or taxonomy for this kind of data could unlock what AI can do with it.
• Google makes it easier for nontechnical people to test with and tune Gemini large-language models (LLMs). The throttling has me thinking about adding LLMs from other companies into the testing.
• The more I learn from this project, the more I respect the human brain and its ability to store and process information from books.

Those are my struggles and learnings from the week!