As interest in large language models (LLMs) for agricultural advisory grows, developers face two critical questions: How should these tools be built to meet the specific needs of farmers? and How should they be tested?
This webinar brings together two teams building agricultural LLMs through different but complementary approaches—offering a behind-the-scenes look at how AI systems are co-designed, refined, and validated with domain experts, farmers and extensionists.
Mamoun Alaoui (ai71) will present the development journey of AgriLLM, a domain-specific agricultural LLM built using retrieval-augmented generation (RAG) and trained on curated agronomic datasets. He will walk through the co-design process: from data partnerships and ontology building, to model grounding, prompt evaluation, and iterative testing with agricultural experts across CGIAR and partner institutions.
Sulakshana Gupta (Viamo) will share lessons from Ask Viamo Anything (AVA) and Viamo’s locally trained agents—two contrasting advisory approaches now being piloted across multiple countries. She will highlight how Viamo integrates farmer feedback loops, rapid user-testing cycles, and real-time analytics to refine advisory responses and guide model improvements.
Together, the speakers will discuss what effective co-design looks like in practice: aligning technical model development with user needs, incorporating field insights early, and building evaluation frameworks that reflect real advisory contexts.
Speakers
- Mamoun Alaoui, Product Manager & Technical Lead, ai71
- Sulakshana Gupta, Director of AI and Research, Viamo
Discussant
- Jawoo Koo, Senior Research Fellow, IFPRI
Moderator
- Eliot Jones-Garcia, Senior Research Analyst, IFPRI; PhD Candidate, Wageningen University