Coding agents are usually built as cloud-first abstractions. But for developing trustworthy, production-ready edge systems, we’ve found that coding agents should be designed from the edge outward—where privacy, bandwidth and real-time requirements are real constraints. In this talk, we’ll show how we’re reimagining coding agents for heterogeneous edge AI/computer vision development: separating reasoning from execution, routing capabilities explicitly, checking runtime constraints, validating actions against observed device behavior and providing inspectable evidence and fallbacks. We’ll then make it concrete with Ambarella’s Cooper Developer Platform, which unifies hardware and software bring-up, optimized models and multimodal pipelines and low-code/no-code agentic blueprints that turn high-level intent into deployable edge workflows. Attendees will leave with a practical model for edge-native, governed agentic development and a road map for building physical AI that can ship.