My final piece on Google’s Open Information Format (OKF) was one of the vital common I’ve ever printed. Since then, I’ve been heads down working by myself OKF construction. I’ve basically constructed my very own private mind, and immediately, I wish to present you the way it works and why this normal is so extremely necessary for the shift towards an agentic internet.
The fantastic thing about OKF is that it follows a quite simple, standardized construction. Whereas many individuals have identified that markdown recordsdata are nothing new, what Google has carried out is create a typical. This implies if I give an agent my OKF recordsdata, it is aware of precisely find out how to learn them with no need customized software program. It’s a common language for AI brokers.
Watch the video of me exhibiting my OKF mind:
Understanding The YAML Frontmatter, Index, And Markdown Information
Each OKF file begins with what known as YAML frontmatter. It is a small block of metadata on the prime of your markdown file that tells an agent precisely what it’s taking a look at. In my private mind, I exploit particular varieties for every thing. I’ve ideas, entities, playbooks, references, and techniques.
Here’s what my folder construction appears like for my OKF mind:
And right here is the markdown code for one of many ideas in my mind:
When an agent views my OKF, it first views the index file. This index.md file is actually an index of the totally different areas the agent can entry in my mind. This manner, as an alternative of my agent having to do RAG throughout every thing in my information base, it may focus particularly on the areas which might be related.
The system I constructed additionally works to attach associated ideas. When it ingests a brand new piece of content material, whether or not it’s a weblog put up I’ve written, a Google announcement, or a bit of analysis, it finds what different ideas we’ve created that ought to be related. The result’s a extremely cool graph of the entire information we’ve within the mind. This concept of brokers extracting ideas and making connections comes from Andrej Karpathy’s LLM Wiki concept.
Visualizing Your Information Graph
Once you use OKF accurately, you possibly can visualize your mind as a related graph. Each dot in my system is a markdown file. You possibly can see how my ideas for AI Overviews connect with my references from Google’s documentation and my inside playbooks. It’s a dwelling, respiratory map of every thing I find out about web optimization and AI.
I’m additionally automating how I ingest info. I’ve a system that checks Google’s documentation day by day. In the event that they replace one thing, just like the documentation on AI Solutions or Search Console options, my mind notifies me and robotically updates the related reference recordsdata. I don’t need to depend on my organic {hardware} to recollect each small change anymore. My OKF mind has entry to excess of I may ever hold in my head without delay.
I can then question my mind, and it’ll write one thing for me that’s synthesized from my notes and the opposite info I’ve chosen to retailer in my mind. If one thing appears off to me, then I can merely ask the agent inside my mind to appropriate it. Additionally, my agent is all the time in search of methods to enhance and join the data that’s within the mind.
Constructing Playbooks To Save Days Of Work
Some of the thrilling issues I’ve inbuilt my OKF mind is a set of playbooks. For instance, I’ve a playbook for producing consumer proposals. Normally, this can be a tedious course of that takes a whole lot of guide work. Now, my agent (Antigravity) follows the steps specified by my proposal playbook to draft every thing utilizing my particular voice and logic.
I additionally constructed a playbook for analyzing website influence after a Google replace. I created a procedural checkpoint for my agent to observe when analyzing these shifts. What used to take me two days to research now takes a matter of hours, and the report produced is one thing I’m extremely pleased with. That is the facility of documenting your knowledge in a approach that brokers can truly execute.
I actually encourage you to begin experimenting with this. You don’t should be a coder to begin. You possibly can inform an agent that will help you construct your first OKF bundle based mostly on the documentation Google has supplied. It’s making me extra productive, and I believe it’s the important thing to staying related as Search continues to evolve.
To construct one thing related, give these hyperlinks to your agent (Claude Code / Cowork, ChatGPT Codex, or my favourite, Google’s Antigravity) and do this immediate:
"I wish to construct an OKF system much like Marie's. Learn these hyperlinks after which give me some concepts of what this may appear to be. Then, ask me questions one after the other in order that collectively, we will determine what we wish to construct: https://cloud.google.com/weblog/merchandise/data-analytics/how-the-open-knowledge-format-can-improve-data-sharing/ https://github.com/GoogleCloudPlatform/knowledge-catalog/blob/fundamental/okf/SPEC.md https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f https://www.mariehaynes.com/okf/ https://youtu.be/esYAIA6lU-s"
Extra Sources:
Learn Marie’s e-newsletter, AI Information You Can Use. Subscribe now.
Featured Picture: N Universe/Shutterstock
