Building AI-based advisory services for smallholder farmers: Technical learnings from the AIEP Initiative

TL;DR

This paper shares technical insights from deploying AI advisory services for smallholder farmers in Kenya and India, highlighting architecture, challenges, and evaluation methods to improve accessibility and effectiveness.

Contribution

It introduces a modular AI system architecture for agricultural advice and discusses key challenges and enablers, including multilingual voice access and corpus curation, with evaluation benchmarks.

Findings

High user satisfaction (NPS ~60) among farmers.

Latency reduction strategies achieved consistent under 5 seconds.

Identified key challenges in language coverage and corpus curation.

Abstract

We report technical learnings from five AI-based agricultural advisory MVPs deployed in Kenya and Bihar, India, under the AIEP Initiative. A 800-farmer study found high user satisfaction (NPS ~60). All solutions implement a modular two-part architecture: (i) an interface component (IVR /WhatsApp / app) with ASR-MT-TTS for multilingual voice access; and (ii) a reasoning component combining LLMs capabilities with query orchestration, external data (weather/soil/markets), and RAG over curated agricultural corpora. We describe key challenges: (a) latency, especially for voice; reductions were achieved via in-country hosting and audio minimization, but consistent <5s remains challenging; (b) language coverage: low-resource ASR/MT integration and nonstandard scripts hinder end-to-end quality; and (c) corpus curation: access, validation, and maintenance are labor-intensive, as well as provide recommendations on how to develop similar systems. We discuss common enablers including (a) data sharing, (b) common corpora, (c) better language AI and (d) evaluation and benchmarking. We also present golden Q&A sets to evaluate LLM capabilities for smallholder agriculture.