AI Agricultural Assistant
A conversational assistant that gives farmers practical, crop-specific guidance, recommendations and information through a simple chat interface.
Overview
An AI-powered assistant designed for people who grow crops and need quick, practical answers: what to plant, how to handle a pest, when to irrigate, what a symptom on a leaf might mean. Questions are asked in everyday language and answered in the same way.
Challenge
Farming advice is local and seasonal, so generic answers are not enough. The assistant has to ask clarifying questions, keep answers short enough to act on, and work well on low-end phones with patchy connectivity.
Process
- 01
Collected the kinds of questions growers actually ask and grouped them by crop stage: planning, sowing, growth, harvest and storage.
- 02
Built a knowledge layer of crop guides that the model draws on, so recommendations follow known good practice.
- 03
Designed the conversation to gather crop, location and stage before giving guidance.
- 04
Optimised the interface as a lightweight, installable web app for mobile use.
Solution
A React front end talking to a Node.js and Express API, with MongoDB for conversations and crop guides. The language model is prompted with the relevant guide and the details gathered in the chat, so each recommendation is specific to the crop and its stage.
Features
Muse
A concept interface for a creative AI companion: conversation on one side, a living canvas of generated ideas, moodboards and drafts on the other.
Open case study