AI coding agents can generate React Native code quickly, but they still need a reliable way to see, touch, debug, and verify the app they are changing. This talk introduces Agent Device, Callstack’s agent-native automation layer for mobile apps, and shows how it gives coding agents a practical feedback loop on iOS, Android, TV, and desktop targets.
We’ll look at what that means in practice: how agents inspect the UI, interact with the app, collect evidence, profile React Native behavior, and turn exploratory work into replayable checks. Then we’ll show practical workflows for React Native teams: letting an agent implement and verify a feature, debugging a broken screen, turning exploratory QA into deterministic checks, and supporting AI-assisted migrations where implementation and testing feed into each other.
The goal is to show how agent-assisted coding changes when the agent can work against the real app, not just the source code.
This talk has been presented at React Summit 2026, check out the latest edition of this React Conference.























