AgriSense
Farmers need fast crop monitoring and tomato leaf disease support, but expert access, connectivity, and practical treatment guidance can be limited.
Role
AI and system concept builder
Team
Portfolio project
Timeline
Research and prototype direction
Problem
What this project needed to solve
- Crop disease support needs to be timely, specific, and easy to understand.
- The system combines robotics, mobile workflows, and AI diagnosis thinking.
- Computer vision outputs need practical treatment and fertilizer recommendations.
- Agriculture technology must work around field realities, not ideal lab settings.
Solution
Robert's product and technical direction
AgriSense frames crop support as a connected workflow: automated crop monitoring, tomato leaf image diagnosis with YOLO and ResNet50/MobileNetV2 directions, and AgriGuide, a RAG-based assistant that turns diagnosis results into treatment and fertilizer recommendations.
Architecture
How the idea is structured
AI support flow from visual crop evidence to retrieval, reasoning, and farmer-facing guidance.
Proof Points
What this project shows
AI + Crops
Portfolio Proof
Shows Robert's strongest resume-backed AI + agriculture project.
CV + RAG
Technical Direction
Connects computer vision diagnosis with source-grounded treatment recommendations.
Grounded
Safety Direction
Prepared for source-backed answers rather than unsupported AI claims.
Process
How Robert approached it
Domain Research
Explored agriculture support needs and disease-diagnosis workflows.
AI Framing
Planned how image evidence and knowledge retrieval could support answers.
Edge Thinking
Considered constraints around hardware, connectivity, and field usability.
Portfolio Integration
Connected the project to Robert's broader AI + agriculture direction.
Next Step
Discuss this project with Robert
Use this case study as proof for Robert's portfolio direction, then return to the assistant or contact page for a role-fit conversation.