In June 2026, Google launched the Open Information Format (OKF), an open specification for a way AI brokers organise and change data. An OKF bundle is simply Markdown recordsdata, light-weight YAML metadata, and hyperlinks between ideas, but it challenges the idea that each AI utility wants embeddings and vector databases.
As a result of the data base is apparent textual content, it may be version-controlled in Git and navigated by following hyperlinks reasonably than retrieving disconnected chunks. On this article, we’ll discover how OKF works and when it beats a standard retrieval pipeline.
Why Conventional RAG Has Limitations
Over the previous few years, Retrieval-Augmented Technology (RAG) has turn into the usual method for offering exterior data to Giant Language Fashions. As a substitute of relying solely on the mannequin’s coaching knowledge, RAG retrieves related data from exterior paperwork throughout inference. A typical pipeline seems one thing like this:
This method works remarkably effectively for looking tens of millions of paperwork. By evaluating the semantic that means of embeddings as a substitute of tangible key phrases, RAG permits an AI system to reply questions utilizing data that was by no means a part of the mannequin’s authentic coaching knowledge.
Nonetheless, there is a crucial trade-off. Earlier than a doc may be listed, it should first be divided into smaller chunks. Whereas chunking improves retrieval effectivity, it additionally breaks aside the unique construction of the doc. Relationships that have been naturally related inside a single doc turn into distributed throughout a number of unbiased chunks.
Think about the next hospital protocol.
# Affected person Admission CoverageSufferers arriving by the Emergency Division should full an preliminary triage earlier than admission.
## Admission Necessities
- Legitimate affected person identification
- Preliminary medical evaluation accomplished
- Emergency instances obtain quick precedence## Recording and Mattress Allocation
Affected person data is recorded within the Digital Well being File (EHR) system earlier than a mattress is assigned.
Mattress allocation follows the Mattress Occupancy tips maintained by the Operations staff.
A typical RAG pipeline could cut up this doc into a number of smaller chunks earlier than indexing.
1st Chunk
Sufferers arriving by the Emergency Division should full an preliminary triage.Admission Necessities:
- Legitimate affected person identification
- Preliminary medical evaluation
- Emergency instances obtain quick precedence
2nd Chunk
Affected person data is recorded within the Digital Well being File (EHR) system.
third Chunk
Mattress allocation follows the Mattress Occupancy tips maintained by the Operations staff.
Visually, the method seems like this:
When a clinician asks,
“What’s the affected person admission course of?”
The vector database retrieves the chunks that appear most related, however the logical relationships between the admission coverage, emergency triage, the EHR system, and mattress allocation are misplaced. The mannequin has to reconstruct them on each question. This isn’t a flaw in RAG. It stays among the finest methods for looking giant, unstructured collections like PDFs, analysis papers, help tickets, and historic information.
Curated organisational data is totally different. Insurance policies, procedures, APIs, and runbooks aren’t simply textual content, they’re interconnected ideas. Rebuilding these hyperlinks from fragmented chunks on each question provides useless complexity, and that’s precisely the issue OKF was designed to resolve.
What’s the Open Information Format (OKF)?
The concepts behind OKF didn’t originate with Google. Earlier in 2026, Andrej Karpathy launched the idea of an LLM Wiki: as a substitute of repeatedly retrieving uncooked paperwork, an AI agent maintains a curated data base it could possibly constantly learn, replace, and enhance. His analogy caught on shortly within the AI group:
Obsidian is the IDE. The LLM is the programmer. The wiki is the codebase.
The thought is straightforward. People present supply materials like documentation, insurance policies, schemas, and runbooks, and the agent organises it right into a structured wiki by writing summaries, connecting associated ideas, and sustaining hyperlinks. These relationships turn into a part of the data base as a substitute of being rediscovered on each question.
Google turned this group concept into an open specification. Slightly than delivery one other framework or SDK, it centered on standardising the data itself. The result’s OKF, a light-weight format that shops data as atypical Markdown recordsdata with minimal metadata and express hyperlinks between ideas.
An OKF bundle is only a listing of Markdown paperwork, every representing one idea comparable to a coverage, API, division, runbook, database desk, or metric, related by commonplace Markdown hyperlinks. In contrast to a vector database that infers relationships by embedding similarity, OKF preserves them explicitly, so an agent follows hyperlinks reasonably than guessing.
As a result of every little thing is apparent textual content, it suits present developer workflows: version-controlled in Git, reviewed by way of pull requests, and searchable with commonplace instruments. Subsequent, we’ll construct a bundle from scratch to see how it’s organised.
Construction of an OKF Bundle
Now that we’ve understood the motivation behind OKF, let’s have a look at how an OKF bundle is definitely organised. At its core, an OKF bundle is solely a listing of Markdown recordsdata. Every Markdown file represents one idea, comparable to a hospital coverage, division, process, system, or operational metric. Each idea incorporates light-weight metadata adopted by structured Markdown content material. Associated ideas are related utilizing commonplace Markdown hyperlinks, permitting each people and AI brokers to navigate the data base naturally.
The specification itself is deliberately minimal. It defines only some conventions and avoids implementing a inflexible listing construction. This offers organisations the pliability to organise data in a manner that most closely fits their area whereas nonetheless producing bundles that may be understood by any OKF-compatible agent.
A typical OKF bundle incorporates the next parts.
| Part | Function |
| index.md | Serves as the first entry level into the data base. It offers an outline of the out there ideas and helps brokers navigate the bundle. |
| CHANGELOG.md (Elective) | Information modifications made to the data base over time, making updates clear and traceable. |
| Idea Recordsdata (.md) | Every Markdown file represents a single idea comparable to a coverage, process, API, division, metric, or system. |
| YAML Entrance Matter | Shops metadata together with the idea kind, title, description, tags, possession, and final up to date timestamp. |
| Markdown Hyperlinks | Explicitly join associated ideas, remodeling the data base right into a navigable graph as a substitute of remoted paperwork. |
A Typical OKF Folder Construction
Though the OKF specification doesn’t mandate a specific listing structure, following a constant folder hierarchy makes the data base considerably simpler to take care of and navigate. The identical organisational rules apply whatever the area.
The next examples reveal how totally different organisations can construction their data whereas following the identical OKF conventions.
1: Hospital Information Base
2: Software program Engineering Information Base
3: Manufacturing Information Base
Though these examples belong to utterly totally different industries, the underlying organisation stays remarkably related. Each bundle begins with an index.md file that serves because the entry level, an elective CHANGELOG.md for monitoring revisions, and a set of directories that group associated ideas collectively.
This consistency is one in every of OKF’s largest strengths. As soon as an AI agent understands how one OKF bundle is organised, it could possibly navigate one other bundle constructed utilizing the identical conventions with little or no extra adaptation.
Constructing an OKF Bundle
Now that we’ve explored the general construction of an OKF bundle, let’s construct one from scratch.
For the rest of this text, we’ll use a fictional hospital referred to as CityCare Hospital. Think about we’re constructing an AI assistant that helps medical doctors, nurses, and hospital directors reply operational questions. The assistant ought to perceive admission insurance policies, emergency procedures, hospital departments, inside techniques, and operational metrics. As a substitute of storing this data inside a vector database, we’ll organise it as an OKF bundle.
We’ll start by creating the foundation listing.
The index.md file acts because the entry level for each people and AI brokers.
# CityCare Hospital Information Base## Insurance policies
- [Patient Admission Policy](insurance policies/patient-admission.md)
- [Discharge Policy](insurance policies/discharge-policy.md)## Procedures
- [Emergency Triage](procedures/emergency-triage.md)
- [Blood Transfusion](procedures/blood-transfusion.md)## Techniques
- [Electronic Health Record](techniques/ehr-system.md)
## Metrics
- [Bed Occupancy](metrics/bed-occupancy.md)
## Departments
- [Emergency Department](departments/emergency.md)
Slightly than looking the whole repository, an AI agent can first learn the index to grasp what ideas exist earlier than navigating to the related recordsdata. This easy design retains the bundle organised whereas lowering pointless context throughout retrieval.
Within the subsequent part, we’ll create particular person idea recordsdata and look at how YAML metadata, Markdown content material, and hyperlinks work collectively to make the data base comprehensible for each people and AI brokers.
Creating an OKF Idea File
The constructing blocks of an OKF bundle are idea recordsdata. Every idea represents precisely one piece of data, comparable to a coverage, process, division, system, metric, or API. Preserving ideas centered makes them simpler to take care of whereas permitting AI brokers to retrieve solely the data they want.
Each idea file consists of two elements:
- YAML Entrance Matter, which shops metadata concerning the idea.
- Markdown Content material, which incorporates the precise data together with hyperlinks to associated ideas.
Let’s create an idea file for the hospital’s affected person admission coverage.
---
kind: coverage
title: Affected person Admission Coverage
description: Pointers for admitting sufferers into CityCare Hospital
tags:
- admissions
- patient-care
up to date: 2026-06-15
---# Affected person Admission Coverage
Sufferers arriving by the Emergency Division should full an preliminary triage earlier than admission.
## Admission Necessities
- Legitimate affected person identification
- Preliminary medical evaluation accomplished
- Emergency instances obtain quick precedence## Associated Ideas
- [Emergency Triage](../procedures/emergency-triage.md)
- [Electronic Health Record](../techniques/ehr-system.md)
Discover that the file incorporates rather more than plain textual content. The YAML part describes what sort of data this file represents, whereas the Markdown physique explains the idea intimately. Most significantly, the idea hyperlinks to different associated ideas contained in the data base. These hyperlinks rework remoted paperwork into an interconnected data graph that an AI agent can navigate.
Though OKF solely requires the sort discipline, including extra metadata makes the bundle simpler to organise and keep.
| Subject | Description |
| kind | Identifies the kind of idea, comparable to coverage, process, system, or metric. That is the one required discipline within the present specification. |
| title | Human-readable title of the idea. |
| description | Abstract describing the idea. |
| tags | Key phrases that assist organise associated ideas. |
| up to date | Signifies when the idea was final modified. |
For the reason that metadata is saved in YAML, each people and AI brokers can shortly perceive what a doc represents earlier than studying its full content material.
One of many largest variations between OKF and conventional doc storage is that ideas are explicitly related utilizing Markdown hyperlinks.
For instance, the admission coverage references the emergency triage process and the Digital Well being File (EHR) system.
These relationships are deliberately created by the writer. The agent doesn’t should infer them by semantic similarity as a result of they exist already contained in the data base.
One other Instance: Hospital Metric
Idea recordsdata aren’t restricted to insurance policies. The identical construction can describe operational metrics, inside techniques, departments, APIs, or runbooks.
Beneath is an idea describing the hospital’s Mattress Occupancy Charge.
---
kind: metric
title: Mattress Occupancy Charge
description: Share of inpatient beds at present occupied
tags:
- operations
- hospital
up to date: 2026-06-15
---# Mattress Occupancy Charge
The Mattress Occupancy Charge measures the share of inpatient beds at present occupied.
## Method
Occupied Beds / Complete Accessible Beds × 100## Information Supply
Hospital Info System
## Proprietor
Operations Division
## Associated Ideas
- [Emergency Department](../departments/emergency.md)
- [Patient Admission Policy](../insurance policies/patient-admission.md)
As a result of each idea follows a constant construction, an AI agent can shortly perceive what the metric represents, how it’s calculated, the place the info comes from, and which different ideas are associated to it.
How AI Brokers Traverse an OKF Bundle
As soon as the data base is organised into interconnected idea recordsdata, retrieval turns into a lot less complicated than conventional doc search.
As a substitute of looking hundreds of doc chunks, an AI agent follows a structured navigation course of.
- Learn the index.md file to grasp the general data base.
- Determine essentially the most related idea primarily based on the consumer’s query.
- Open that idea file.
- Comply with hyperlinks to associated ideas each time extra context is required.
- Generate the ultimate response utilizing solely the related ideas.
The traversal course of may be visualised as follows.
In contrast to a RAG pipeline, the agent doesn’t start by looking an embedding index. It begins from a curated entry level and progressively explores solely the ideas which might be related to the present process.
This method preserves the relationships between ideas whereas maintaining the quantity of context despatched to the language mannequin comparatively small.
Why This Works Properly for AI Brokers
The largest benefit of OKF is that it permits builders to organise data in the identical manner people naturally give it some thought. A physician studying the hospital’s documentation doesn’t randomly bounce between unrelated paragraphs. They start with a coverage, comply with references to procedures, seek the advice of the related techniques, after which arrive on the data they want. OKF allows AI brokers to comply with this identical workflow.
As a substitute of reconstructing relationships from fragmented doc chunks each time a query is requested, the agent navigates an express data graph the place these relationships have already been outlined. This makes the retrieval course of extra deterministic, simpler to audit, and considerably less complicated to take care of.
The place RAG Nonetheless Excels
At this level, OKF feels like a great resolution for organising data. It preserves relationships between ideas, retains every little thing version-controlled, and permits AI brokers to navigate curated documentation with out counting on semantic search.
Nonetheless, OKF has an necessary limitation. Somebody has to curate each idea.
Each coverage, process, system, metric, and division have to be written, reviewed, and maintained. This works effectively for authoritative organisational data, nevertheless it turns into impractical when the data base grows to tens of millions of paperwork.
Think about a hospital that has collected years of operational knowledge.
- Thousands and thousands of Digital Well being File (EHR) entries
- Medical analysis papers
- Medical notes
- Affected person suggestions
- Incident stories
- Inside emails
- Assembly transcripts
- Gear upkeep logs
Organising each one in every of these paperwork into rigorously curated OKF idea recordsdata would require an infinite quantity of guide effort. Even when AI brokers assisted with the curation course of, a lot of this data modifications constantly and is best fitted to semantic search.
That is the place Retrieval-Augmented Technology (RAG) continues to be the popular resolution.
RAG Resolution
Slightly than requiring paperwork to be manually organised, RAG indexes giant collections of unstructured knowledge utilizing embeddings. When a query is requested, the system retrieves essentially the most semantically related paperwork and offers them as context to the language mannequin.
For instance, contemplate the next questions:
- Has anybody encountered this MRI scanner error earlier than?
- Discover earlier incident stories involving delayed laboratory outcomes.
- Summarise discussions concerning the new EHR rollout.
- Seek for all assembly notes mentioning affected person switch delays.
These questions can’t be answered from a small curated data base. As a substitute, they require looking by hundreds and even tens of millions of paperwork the place the reply might exist anyplace. That is precisely the kind of drawback RAG was designed to resolve.
The strengths of every method turn into a lot clearer when seen facet by facet.
| Function | OKF | RAG |
| Finest for | Curated organisational data | Giant collections of unstructured paperwork |
| Information Supply | Markdown idea recordsdata | Uncooked paperwork |
| Retrieval | Deterministic navigation | Semantic similarity search |
| Infrastructure | File system + Git | Embeddings + Vector Database |
| Model Management | Native Git help | Requires re-indexing after updates |
| Relationships | Express hyperlinks between ideas | Inferred from retrieved chunks |
| Scalability | Average | Wonderful |
| Explainability | Excessive | Average |
Neither method is universally higher than the opposite. They merely clear up totally different issues. OKF offers construction and precision. RAG offers scale and adaptability. This naturally raises one other query.
Do we actually have to decide on one over the opposite?
Happily, the reply is no.
Hybrid Information Structure: Combining OKF and RAG
In apply, the best AI techniques use each OKF and RAG collectively.
As a substitute of treating them as competing applied sciences, trendy agent architectures use every one the place it performs finest.
A easy manner to consider that is the 80/20 precept.
- The 20% of organisational data that’s crucial, secure, and incessantly referenced is saved as an OKF bundle.
- The remaining 80% of huge, unstructured data stays inside a standard RAG pipeline.
This creates a layered data structure.
The router determines which data supply is most acceptable for the incoming question.
Questions requiring authoritative and deterministic solutions are routed to the OKF bundle.
Examples embrace:
- What’s the affected person admission coverage?
- How is the Mattress Occupancy Charge calculated?
- Which system shops affected person medical information?
- What’s the emergency blood transfusion process?
Every of those questions has a single authoritative reply maintained by the organisation.
However, exploratory questions are routed to the RAG pipeline.
For instance:
- Has anybody encountered this MRI scanner error earlier than?
- Discover earlier incident stories involving delayed laboratory outcomes.
- Summarise discussions concerning the EHR migration undertaking.
- Search assembly notes discussing affected person discharge delays.
These questions require looking giant collections of historic paperwork reasonably than consulting curated data.
This hybrid structure permits every system to give attention to its strengths.
| OKF Strengths | RAG Strengths |
| Deterministic retrieval | Semantic retrieval |
| Curated and authoritative data | Large doc collections |
| Express relationships between ideas | Finds data utilizing semantic similarity |
| Model-controlled with Git | Constantly indexes new paperwork |
| Straightforward to audit and keep | Extremely scalable |
Maybe the most important benefit of this structure is that the language mannequin doesn’t must know the place the data comes from. The agent merely requests the data it wants.
The routing layer decides whether or not that data ought to come from the OKF bundle or the vector database. Frameworks comparable to LangGraph, LangChain, or LlamaIndex make this routing simple by permitting builders to construct workflows that select the suitable retrieval technique primarily based on the consumer’s question. Consequently, AI brokers achieve the precision of curated data with out sacrificing the power to go looking huge collections of unstructured data.
In different phrases, the long run just isn’t OKF versus RAG. It’s OKF plus RAG, working collectively as complementary layers in a single data structure.
Conclusion
The Open Information Format gives a easy, clear approach to organise data for AI brokers. By representing it as interconnected Markdown paperwork, OKF retains organisational data simple to grasp, keep, and version-control in Git.
It fits curated data like insurance policies, runbooks, and API docs, with out changing RAG, which nonetheless excels at semantic search throughout giant, unstructured collections.
Used collectively, the 2 cowl much more floor than both alone. In the end, understanding the place every method suits is what lets builders construct brokers which might be correct, explainable, and production-ready.
Incessantly Requested Questions
A. It’s an open specification Google launched in June 2026 for a way AI brokers organise and change data. An OKF bundle is a listing of Markdown recordsdata with light-weight YAML metadata and express hyperlinks between ideas, so data lives as plain textual content alongside your code reasonably than as vectors in a database.
A. RAG splits paperwork into chunks, embeds them, and retrieves essentially the most semantically related items at question time. OKF shops data as interconnected idea recordsdata and lets an agent navigate by following author-defined hyperlinks. RAG infers relationships; OKF retains them express.
A. No. They clear up totally different issues. OKF is finest for curated, authoritative data like insurance policies, runbooks, and API docs. RAG is finest for looking giant, unstructured collections comparable to EHR entries, incident stories, and assembly notes. The article recommends utilizing them collectively.
GenAI Intern @ Analytics Vidhya | Last Yr @ VIT Chennai
Captivated with AI and machine studying, I am desperate to dive into roles as an AI/ML Engineer or Information Scientist the place I could make an actual impression. With a knack for fast studying and a love for teamwork, I am excited to carry modern options and cutting-edge developments to the desk. My curiosity drives me to discover AI throughout varied fields and take the initiative to delve into knowledge engineering, making certain I keep forward and ship impactful tasks.
Login to proceed studying and luxuriate in expert-curated content material.
