Guardado en:
Detalles Bibliográficos
Autores principales: Collis, Stewart, Kinyua, Florence, Kumar, Vikram, Lakougna, Howard, Merz, Christian, Pandey, Kirti, Resch, Christian
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2601.11537
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917207166943232
author Collis, Stewart
Kinyua, Florence
Kumar, Vikram
Lakougna, Howard
Merz, Christian
Pandey, Kirti
Resch, Christian
author_facet Collis, Stewart
Kinyua, Florence
Kumar, Vikram
Lakougna, Howard
Merz, Christian
Pandey, Kirti
Resch, Christian
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_11537
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Building AI-based advisory services for smallholder farmers: Technical learnings from the AIEP Initiative
Collis, Stewart
Kinyua, Florence
Kumar, Vikram
Lakougna, Howard
Merz, Christian
Pandey, Kirti
Resch, Christian
Human-Computer Interaction
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.
title Building AI-based advisory services for smallholder farmers: Technical learnings from the AIEP Initiative
topic Human-Computer Interaction
url https://arxiv.org/abs/2601.11537