F.A.R.M.E.R.

F.A.R.M.E.R. (Futuristic Agriculture & Resource Management Ecosystem Router) is a multi-agent AI system that routes smallholder farmers' queries, text and crop images, to the right specialist agent and escalates uncertain or high-severity cases to a human extension officer.

Smallholder farmers in rural Khyber Pakhtunkhwa have limited access to agricultural extension officers, which delays crop disease response and reduces yields. The system mirrors a routing problem the author documented in his own published research on AI routing for Lady Health Workers in the same region.

A deterministic router sends image queries to a Gemini-powered diagnosis agent, weather and market questions to an MCP-backed data agent, and everything else to an advisory agent. A confidence gate escalates any low-confidence or high-severity case to a human. The router and gate use no LLM calls, so routing decisions stay inspectable and stable across model versions.

Built for the Kaggle × Google AI Agents Intensive Vibe Coding Capstone, Agents for Good track.