My last piece on Google Open Knowledge Format (OKF) was one of the most popular I’ve ever published. Since then, I have been working headlong on my own OKF structure. I’ve basically built my own personal brain, and today I want to show you how it works and why this standard is so incredibly important for transitioning to a Web agent.
The beauty of OKF is that it follows a very simple and standardized structure. Although many people have pointed out that markdown files are not new, what Google did was create a standard. This means that if I give my OKF files to an agent, they know exactly how to read them without the need for custom software. It is a universal language for AI agents.
Watch the video of me showing off my OKF brain:
Understanding Frontmatter, Index, and Markdown YAML Files
Every OKF file starts with what is called the YAML frontmatter. This is a small block of metadata at the top of your markdown file that tells an agent exactly what they’re looking at. In my personal brain, I use specific types for everything. I have concepts, entities, playbooks, references and systems.
This is what my folder structure looks like to my OKF brain:
And here is the markdown code for one of the concepts in my brain:
When an agent looks at my OKF, they first look at the index file. This index.md file is essentially an index of the different areas that the agent can access in my brain. This way, instead of my agent having to RAG through All in my knowledge base it can focus specifically on relevant areas.
The system I built also works to connect related concepts. When it ingests new content, whether it’s a blog post I wrote, a Google ad, or a search, it discovers what other concepts we’ve created need to be connected. The result is a really cool graph of all the knowledge we have in the brain. This idea that agents extract concepts and establish connections comes from The idea of Andrej Karpathy’s LLM wiki.
View your knowledge graph
When you use OKF correctly, you can visualize your brain as a connected graph. Every point in my system is a markdown file. You can see how my concepts for AI overviews connect to my references from Google documentation and my internal playbooks. It’s a living, breathing map of everything I know about SEO and AI.
I also automate the way I ingest information. I have a system that checks Google documentation daily. If they update anything, like the documentation on AI Answers or Search Console Featuresmy brain notifies me and automatically updates the relevant reference files. I no longer need to rely on my biological hardware to remember every little change. My OKF brain has access to way more things than I could ever hold in my head at one time.
I can then query my brain, and it will write something for me that is synthesized from my notes and other information that I have chosen to store in my brain. If something seems wrong, I can simply ask the agent in my brain to correct it. Additionally, my agent is always looking for ways to improve and connect the information in the brain.
Create playbooks to save days of work
One of the most exciting things I’ve built in my OKF brain is a set of playbooks. For example, I have a playbook for generating client proposals. This is usually a tedious process that requires a lot of manual work. Now my agent (Antigravity) follows the steps outlined in my proposal playbook to write everything using my specific voice and logic.
I also created a playbook to analyze the impact of the site after a Google update. I’ve created a procedural checkpoint for my agent to follow when analyzing these changes. What used to take me two days to analyze now takes just a few hours, and the report produced is something I’m incredibly happy with. This is the power of documenting your wisdom in a way that agents can actually execute it.
I really encourage you to start experimenting with this. You don’t need to be a coder to get started. You can ask an agent to help you create 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 research continues to evolve.
To create something similar, give these links to your agent (Claude Code / Cowork, ChatGPT Codex or my favorite, Antigravity from Google) and try this prompt:
"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/ https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/main/okf/SPEC.md https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f https://www.mariehaynes.com/okf/ https://youtu.be/esYAIA6lU-s"
More resources:
Read Marie’s newsletter, AI News You Can Use. Subscribe now.
Featured image: N Universe/Shutterstock
