"We report technical learnings from five AI agricultural advisory minimum viable products (MVPs) deployed in Kenya and Bihar under the AIEP Initiative. A 800-farmer study found high user satisfaction (net promoter score ∼60). All solutions implement a modular two-part architecture: (i) an interface component (Interactive Voice Response (IVR) / WhatsApp / app) with automated speech recognition (ASR) → machine translation (MT) → Text-to-Speech (TTS) model for multilingual voice access; and (ii) a reasoning component combining LLMs capabilities with query orchestration, external data (weather/soil/markets), and Retrieval Augmented Generation (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." (Abstract)