More How I AI episodes

From Figma to Claude Code and back | Gui Seiz & Alex Kern (Figma) thumbnail

From Figma to Claude Code and back | Gui Seiz & Alex Kern (Figma)

Published 11 Mar 2026

Duration: 00:40:21

Innovations in collaboration and workflow processes integrate design and code in real-time, leveraging AI tools to streamline tasks and foster creative problem-solving.

Episode Description

Most teams are still passing static design files back and forth, and most Figma files are already out of date by the time they reach engineering. Gui...

Overview

The podcast explores innovations in collaboration and workflow design, emphasizing cross-disciplinary teamwork between designers and engineers through rapid prototyping and real-time integration of design and engineering processes. Traditional linear workflows are being replaced by fluid, iterative methods, with tools like MCP (Multi-Cloud Platform) enabling synchronization between code and design states, fostering faster feedback loops and alignment. Challenges such as codebases outpacing design files are addressed through AI-driven solutions, including automated import of code-defined states into design tools like Figma and the use of functional, interactive prototypes over static wireframes. These advancements aim to streamline workflows, reduce manual effort, and align design and engineering efforts more closely.

AI and automation are highlighted as key enablers for reducing repetitive tasks, such as generating design variations, compliance checks, and experiment iterations, while also lowering costs for high-quality design and code artifacts. Platforms like Optimizely Opal are showcased for automating marketing and digital workflows, including content creation and personalization. The discussion also underscores a shift in product development priorities, moving from siloed, resource-scarce teams to AI-enabled, collaborative environments focused on solving complex problems. This transition allows for greater exploration, faster experimentation, and the reinvention of workflows to adapt to evolving feature complexity and business needs.

Looking ahead, the podcast envisions AI as a catalyst for redefining the roles of designers and engineers, enabling them to focus on strategic, creative tasks while AI handles mechanical work. The boundaries between design and code are blurring, with both becoming dynamic, interdependent elements of shared processes. Tools like Figma and Codex are highlighted for their integration capabilities, enabling seamless collaboration through real-time editing, shared workflows, and automated translation of design into code. Challenges such as divergence between design and code are addressed through solutions like Figma MCP, which pulls code components into design tools, and the use of AI to bridge gaps in alignment. The future emphasizes a hybrid approach, combining the strengths of direct manipulation in design tools with the precision of code, while fostering more strategic, upstream decision-making in product development.

Recent Episodes of How I AI

22 Jun 2026 How Claude Mythos found a 15-year-old bug in Mozilla Firefox | Brian Grinstead

Recommended: AI finds bugs

Firefox employs AI agents as "coding archaeologists" to detect and address security vulnerabilities in its massive codebase, leveraging models like Mythos and custom validation tools to identify and systematically fix nearly 500 bugs, while balancing automation with human oversight and open-source collaboration to enhance scalability and security.

15 Jun 2026 How Braintrust uses AI agents, evals, and CI to ship better software | Ankur Goyal

AI integration in software engineering enables agents to handle complex tasks through benchmarking and optimization, shifts engineers toward higher-level work, and addresses challenges like reliability, data parsing, and balancing automation with human expertise while emphasizing outcome-focused systems over procedural methods.

9 Jun 2026 Claude Fable 5 review: what the new Mythos model gets right (and very wrong)

Anthropic's Claude Fable Five excels in long-term technical tasks with strong coding, vision, and async workflow capabilities but faces high token costs, design limitations, and restricted use in cybersecurity/biology, making it suitable for precise, extended projects rather than creative or agile workflows.

More How I AI episodes