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

TL;DR

Kissan-Dost is a multilingual conversational system that translates live farm sensor data into plain language guidance via WhatsApp, improving last-mile adoption of precision agriculture tools for smallholders.

Contribution

The paper introduces a modular, sensor-grounded conversational platform that effectively integrates existing Agri-IoT data into accessible guidance, demonstrating high accuracy and engagement in real-world settings.

Findings

Chatbot usage was nearly daily and led to concrete actions.

Sensor query correctness exceeded 90% with low latency.

Careful last-mile integration enhances existing IoT value for smallholders.

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.