> For the complete documentation index, see [llms.txt](https://docs.openagrinet.global/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.openagrinet.global/technical/ai-layer.md).

# AI Layer

Role of Artificial Intelligence in OpenAgriNet (OAN)

<mark style="color:$primary;">**OpenAgriNet (OAN)**</mark> is designed as an open, interoperable digital public infrastructure that enables farmers to discover information, services, and entitlements across agriculture ecosystems in a unified manner. While the underlying network protocols and registries enable interoperability and decentralisation, Artificial Intelligence (AI) acts as the primary interface layer that translates farmer intent into actionable outcomes across the network.

The AI module in OAN is not a standalone chatbot or conversational feature. Instead, it functions as an intelligent orchestration layer that sits between user-facing applications and the underlying data sources, APIs, and network services. Its core purpose is to reduce complexity for end users, particularly farmers, by enabling natural language and voice-based interactions while preserving the modular, open-network architecture of OAN.

#### <mark style="color:$primary;">Why AI Is Central to OAN</mark>

Agricultural information and services worldwide are deeply fragmented across institutions, programmes, and data systems. Farmers often have to navigate multiple, disconnected sources to access critical information, ranging from government support schemes and advisory services to real-time market and weather data.

A key compounding challenge is that information is frequently not available in farmers’ language of choice. Even where digital services exist, they are often delivered in limited languages or technical formats, creating a digital and informational divide that disproportionately affects small and marginal farmers. This gap is not merely technological, but structural. It is driven by fragmented service delivery, inconsistent standards, and limited interoperability across systems.

In India, these global challenges are particularly pronounced due to the scale and diversity of the agricultural ecosystem. Farmers are required to navigate:

* Multiple schemes across central and state governments
* Advisory content dispersed across agricultural universities, research institutions, and KVKs (Krishi Vigyaan Kendras)
* Real-time data sources such as weather forecasts, mandi prices, warehouse availability, and soil testing services
* Status tracking and grievance redressal systems that are often programme-specific and siloed

Much of this information is spread across different portals, applications, and offices, often with limited language support and inconsistent user experiences. As a result, farmers frequently rely on intermediaries or informal networks, reinforcing existing inequities in access to information and services.

OAN addresses this fragmentation at the network and protocol layer. The AI module complements this by addressing fragmentation at the user interaction layer.

By enabling farmers to ask questions in their own language—using text or voice, the AI module:

* Interprets user intent
* Identifies the correct service or data source
* Makes tool calls to retrieve the right information
* Presents responses in a contextual, understandable manner

In this sense, AI becomes the primary discovery and access mechanism for OAN-powered services.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.openagrinet.global/technical/ai-layer.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
