Compares a set of the latest sovereign and private models for their responses being similar to our golden QnA of common small shareholder farmer questions and answers (in English) from ClearGlobal and Opportunity Intl. What makes a good golden eval QnA? Click here to read the case study.

Aimed at French farmers and Extension Agents, this copilot uses a collection of documents representing best practices from the French Ministry of Agriculture. We load these documents into a vector database and with each question, we search the DB and add the results to create an answer to the farmer's questions. Additionally, the copilot features WhatsApp follow-up and location buttons plus agentic web search to get local weather and prices. It also leverages ISDA's Africa soil API to look up soil information based on the user's location.

Aimed at Indian farmers and Extension Agents, this copilot uses a collection of documents and transcripts of 100s of videos representing best practices from the Indian Ministry of Agriculture and Digital Green's video transcripts & FAQs to answer common questions from Indian farmers. We load these documents + transcripts into a vector database and with each question, we search the DB and add the results to create an answer to the farmer's questions. Additionally, the copilot features WhatsApp follow-up and location buttons plus agentic web search to get local weather and prices. It also leverages ISDA's Africa soil API to look up soil information based on the user's location.

Click here to read the case study.

FarmerAI in Kenya - English + Swahili. This is an example of a low-latency, agentic IVR bot for agriculture with support for RAG, docs weather and pricing (via Web Search), location sharing, and look-ups to ISDA for soil analysis based on location. Click here to read the case study.

Takes a precise African location as lat/long as input and returns a JSON object representing the soil's "nitrogen_total", "phosphorous_extractable", "potassium_extractable", "pH" and "texture_class" using the ISDA Soil API. When used with small shareholder advisory tools, this provides the basis of personalized fertilizer recommendations that shown to yield season on season yield improvements of 16-46%. Read more on Gooey.AI Agriculture work

This evaluation compares private and open-source models to determine which can best identify and diagnose plant diseases from uploaded images.

AI-powered voice agronomist helping African farmers with locally relevant crop and fertilizer advice. It uses Omnilingual ASR, farmer data and ISDA soil analysis to understand each farm and deliver practical recommendations through voice or text.

Aimed at Kenyan farmers and extension agents, Farmer.CHAT can analyze crop photos, provide precise weather, price and soil analysis based on the user's lat /long. It understands audio messages in most languages, including English and Swahili. More info and technical walkthroughs can be found here

Aimed at Indian farmers and extension agents, this copilot uses a collection of documents and transcripts of 100s of videos representing best practices from the Indian Ministry of Agriculture and Digital Green's video transcripts & FAQs to answer common questions from Indian farmers. We load these documents + transcripts into a vector database and with each question, we search the DB and add the results to create an answer to the farmer's questions. Additionally, the copilot features WhatsApp follow-up and location buttons plus agentic web search to get local weather and prices. It also leverages ISDA's Africa soil API to look up soil information based on the user's location. It uses Meta's Omnilingual speech recognition model, supporting 1400+ languages and ai71's Qwen3 based AgriLLM(https://huggingface.co/AI71ai/agrillm-Qwen3-30B-A3B)

More info and technical walkthroughs can be found here