Build an OKF Brain Like Mine!

My last piece on Google’s Open Knowledge Format (OKF) was one of the most popular I’ve ever published. Since then, I have been straight down working on my own OKF structure. I actually built my own brain, and today, I want to show you how it works and why this level is so important in transitioning to a web agent.
The beauty of OKF is that it follows a very simple, standardized structure. Although many people have pointed out that markup files are nothing new, what Google is doing is creating a standard. This means that when I give the agent my OKF files, it knows exactly how to read them without needing custom software. It is the universal language of AI agents.
Watch my video showing my OKF logic:
Understanding YAML Frontmatter, Index, and Markdown Files
Every OKF file starts with what is called YAML frontmatter. This is a small block of metadata at the top of your markup file that tells the agent what to look for. In my personal mind, I use certain types of everything. I have concepts, organizations, playbooks, directions, and systems.
Here’s what my folder structure looks like in my OKF brain:
And here is the markup code for one of the concepts in my mind:

When an agent looks at my OKF, it first looks at the index file. This index.md file is actually an index of the different places the agent can access in my brain. This way, instead of my agent doing the entire RAG everything on the basis of my knowledge, it can focus mainly on the right areas.

The system I built also works to connect related concepts. When it imports a new piece of content, whether it’s a blog I’ve written, a Google announcement, or a piece of research, it finds out what other ideas we’ve created that should be linked. The result is a really cool graph of all the information we have in the brain. This idea of agents extracting concepts and making connections comes from Andrej Karpathy’s idea for the LLM Wiki.
Visualizing Your Knowledge Graph
If you use OKF correctly, you can visualize your brain as a connected graph. Every dot in my system is a tag file. You can see how my AI Overview concepts connect to my references from Google Docs and my internal playbooks. A living, breathing map of everything I know about SEO and AI.
I also automate how I import information. I have a system that checks Google docs every day. When they update something, like documents on AI Answers or Search Console features, my brain notifies me and automatically updates the relevant reference files. I don’t have to rely on my biological hardware to remember every little change. My OKF brain can access more than I could keep in my head at one time.

I can then ask my mind, and it will write me something that is compiled from my notes and other information that I have chosen to keep in my mind. If something bothers me, I can just ask the agent in my mind to fix it. Also, my agent is always looking for ways to improve and connect information in the brain.


Creating Playbooks for Saving Work Days
One of the funnest things I’ve built in my OKF brain is a collection of playbooks. For example, I have a playbook for generating customer proposals. Usually, this is a tedious process that takes a lot of manual work. Now, my agent (Antigravity) follows the steps laid out in my proposal playbook to write everything using my specific voice and logic.
I also created a playbook for analyzing the impact of a site after a Google update. I created a process checkpoint for my agent to follow when analyzing these shifts. What used to take me two days to analyze now takes a few hours, and the report produced is something I’m incredibly happy with. This is the power of writing your creativity in a way that agents can use.
I really encourage you to try this first. You don’t need to be a coder to get started. You can tell the agent to help you build your first OKF bundle based on the documentation provided by Google. It makes me more productive, and I think it’s the key to staying relevant as Search continues to evolve.
To create something similar, give these links to your agent (Claude Code/Cowork, ChatGPT Codex, or my favorite, Google’s Antigravity) and try this information:
"I want to build an OKF system similar to Marie's. Read these links and then give me some ideas of what this would look like. Then, ask me questions one at a time so that together, we can decide what we want to build: https://cloud.google.com/blog/products/data-analytics/how-the-open-knowledge-format-can-improve-data-sharing/
Additional resources:
Read Marie’s newsletter, AI News You Can Use. Register now.
Featured image: N Universe/Shutterstock



