Ask enough React Native devs about the Figma MCP and you'll hear the same verdict: it's useless for React Native.

On a recent project, we set out to automate a chunk of our SDLC: generate production-ready RN screens directly from Figma designs. The Figma MCP sat at the core of this pipeline, and its "s*** for RN" reputation preceded it. So we dug in and realised that the MCP was doing its job. The failures were coming from everything around it: how the designs were structured, how web-shaped output got mapped onto React Native, and the fact that the agent had no reliable way to see what it had actually built.

You'll leave knowing:
- Why frame structure, layer naming, and a disciplined design system have the biggest impact on output quality.
- How to translate web-oriented MCP output into high-quality React Native.
- How to close the agent's feedback loop, giving it both the rendered screen and the component tree so it can see what it built, diff it against the design, and fix itself.

The React Native ecosystem is changing fast, and AI is now influencing everything from code generation and testing to debugging, tooling, and app architecture. This panel brings together voices from across the community to ask what that shift really means for everyday RN developers: which AI and agent workflows are already useful, where the hype still outpaces the reality, and what skills will matter most in the next wave of mobile development. Expect a candid conversation about productivity, code quality, maintainability, and the practical changes teams will need to make as AI becomes part of the React Native workflow.