AI lowers the barrier to coding, allowing non-technical people to submit pull requests. Instead of rejecting imperfect code, view these contributions as high-fidelity prompts that clearly articulate the desired feature or fix, which can then be refined by a senior developer.

At Notion, engineers build features to 80-90% completion. Designers then take over, shipping small, focused pull requests for the final visual polish, animation, and craft. This "last mile" is a designer's superpower where LLMs currently fall short.

At Perplexity, the design system lives in the codebase, not Figma. Designers contribute directly to the frontend, creating a single source of truth that eliminates drift between design files and production code, forcing a highly practical and collaborative process.

For designers who code but aren't senior engineers, submitting pull requests can be daunting. Using an integrated AI code review agent provides an extra layer of validation. It catches potential issues and suggests improvements, boosting confidence before the code undergoes human review.

To keep pace with AI development, the barrier between design and engineering must fall. Intercom made it a non-negotiable job requirement for every product designer to ship code to production. This empowers them to fix UI bugs directly and accelerates the entire development cycle.

With AI generating 1,300 pull requests weekly at Stripe, the critical path is shifting. When coding becomes a commodity, the bottleneck moves to human review and validation. Engineering teams must refocus from pure creation to oversight and quality assurance at scale.

To ensure its design team embraces modern tooling, Shopify requires every new designer to commit at least two pull requests to the main codebase during onboarding. This establishes coding as a core, non-negotiable responsibility from day one.

Instead of getting bogged down in production constraints like failing tests, designers are encouraged to use code to render the most desirable version of an idea. The prototype's value is in communicating the full vision to engineering, not in being a mergeable pull request.

To avoid wasting time on code with flawed architecture, designers should first create a written plan (e.g., an MD file) outlining their intended approach. Getting engineering sign-off on this plan ensures the fundamental logic is sound before using an LLM to generate the front-end code.