Kissan-Dost: Bridging the Last Mile in Smallholder Precision Agriculture with Conversational IoT

2026-02-09

AI Summary

This study addresses the “last-mile” barrier that often prevents smallholder farmers from effectively leveraging agricultural Internet of Things (Agri-IoT) data. The authors propose a hardware-free, multilingual conversational system delivered via WhatsApp, which transforms commercial soil and weather sensor data into actionable agronomic advice through text or voice messages. The system innovatively integrates retrieval-augmented generation (RAG) with a modular messaging pipeline to ensure data-grounded, traceable recommendations and proactive alerts. A 90-day field pilot demonstrated consistent daily user engagement and on-farm actionability; across 99 sensor-driven crop queries, the system achieved over 90% recommendation accuracy, end-to-end latency under one second, and high-quality translation performance.

Technology Category

• Multiagent Systems: Agent Communication
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We present Kissan-Dost, a multilingual, sensor-grounded conversational system that turns live on-farm measurements and weather into plain-language guidance delivered over WhatsApp text or voice. The system couples commodity soil and climate sensors with retrieval-augmented generation, then enforces grounding, traceability, and proactive alerts through a modular pipeline. In a 90-day, two-site pilot with five participants, we ran three phases (baseline, dashboard only, chatbot only). Dashboard engagement was sporadic and faded, while the chatbot was used nearly daily and informed concrete actions. Controlled tests on 99 sensor-grounded crop queries achieved over 90 percent correctness with subsecond end-to-end latency, alongside high-quality translation outputs. Results show that careful last-mile integration, not novel circuitry, unlocks the latent value of existing Agri-IoT for smallholders.

Problem

• precision agriculture
• smallholder farmers
• last-mile delivery
• Agri-IoT
• conversational AI

Innovation

• Conversational IoT
• Retrieval-Augmented Generation
• Precision Agriculture
• Last-Mile Integration
• Sensor-Grounded AI