Deploying Strands Agents as AWS IoT Greengrass components on a Raspberry Pi 5 enables an edge AI system for smart agriculture, combining camera-based plant analysis through Amazon Bedrock, real-time soil moisture sensing, device monitoring, and a local web dashboard, all orchestrated by an AI agent running on the device. Manual crop monitoring is slow, inconsistent, and doesn’t scale across multiple growing sites, requiring repetitive tasks like walking rows, checking soil moisture by hand, and logging observations. Scaling this process across multiple greenhouses or farm sites compounds the problem, as hiring trained agronomists for every location is expensive, and periodic inspections mean issues like early-stage disease, pest damage, or irrigation failures go undetected between visits. Cloud-based monitoring systems address some challenges but introduce constraints: every sensor read and image analysis requires a network round-trip, and in rural agricultural environments with limited or intermittent connectivity, this dependency creates blind spots, while latency between capturing an image and receiving an analysis result makes real-time decision-making impractical. AI agents that interact with the physical world need to run where the sensors are, as a cloud-hosted agent can’t read a GPIO pin, capture a camera frame, or check CPU temperature. Strands Agents is an open source Python SDK for building AI agents, providing a tool-based architecture where each agent capability is a Python function decorated with @tool, and the agent decides which tools to call based on the user’s query, chains multiple tool