Claude Design First Impression
A designer tests Claude Design and finds it impressive for incorporating design systems as first-class citizens, but immediately hits credit limits and finds the iteration speed much slower than Figma due to LLM processing delays.
Summary
The speaker provides their first impressions of Claude Design, a new AI-powered design tool. They begin by highlighting what they see as the tool's main advantage: its treatment of design systems as first-class citizens, which addresses a common complaint about prototyping tools not matching brand guidelines. The speaker attempted to import their design system into Claude Design as their first action. However, their experience quickly turned problematic when they ran out of credits after only performing two or three basic tasks, getting blocked until Saturday despite it being Tuesday. After spending an additional $200 to continue using the tool, they identified a fundamental limitation compared to Figma. The speaker argues that Figma's strength lies in immediate, direct manipulation capabilities - dragging, changing fonts, and modifying elements without waiting for AI model processing or credit top-ups. They emphasize that many design tasks don't require AI involvement and that the speed of iteration is crucial for design work. The slow cycles caused by LLM processing in Claude Design represent a significant barrier to effective design workflow compared to traditional tools like Figma.
Key Insights
- The speaker identifies that Claude Design makes design systems a first-class citizen, which addresses the common complaint that prototyping tools never match brand guidelines
- The speaker hit their credit limit after performing only two or three basic tasks in Claude Design, getting blocked until Saturday despite it being Tuesday
- The speaker had to spend $200 to continue using Claude Design after hitting the initial credit limit
- The speaker argues that Figma wins because of direct manipulation capabilities - dragging and changing elements without waiting for LLM calls or credit top-ups
- The speaker claims that many design tasks don't need AI model involvement and that slow LLM cycles significantly hinder the iteration speed crucial for design work
Topics
Transcript
[0:00] The number one complaint I know people have about using prototyping in the product development life cycle is it never matches my brand. What I think makes Claw Design really interesting is they're making the design system a first class citizen of this design tool. So the first thing I did was actually go in and just import my design system. And we ran out of credits. Okay, I immediately hit my limit. I've only done about two or three things in claw design and I am blocked until Saturday and it is [0:30] Tuesday. $200 later we are back. This is where Figma really wins. Just your ability to drag things, change things, change the font without having…
Full transcript available for MurmurCast members
Sign Up to AccessMore from How I AI
GPT-5.6's video editing via Codex is genuinely one of my favorite new workflows
A product manager describes using GPT-5.6 with Codex to automate video editing for social media clips. By simply dragging a file and providing natural language instructions, the AI generated five polished, fast-paced hype videos from a long conference talk recording, dramatically reducing the time-intensive manual clipping process.
Theoretically Intelligent vs. Practically Effective: Why GPT-5.6 Sol Beats Fable for Product Work
An executive contrasts two AI models (Fable and Soul/GPT-5.6 Sol), arguing that Soul is superior for product work because it prioritizes practical effectiveness over theoretical intelligence. The speaker values the ability to ship products to customers and understand end-user goals over theoretical sophistication.
Build a harness when the same workflow needs the same setup and the same outcomes, every time
Building a harness for repetitive workflows allows you to be more prescriptive about job execution, resulting in greater efficiency, consistency, and better outcomes. Rather than explaining requirements to an AI agent each time, a harness lets you use a simpler interface like pasting a link while the agent already understands the intended task.
GPT 5.6-Sol vs. Claude Fable: Why OpenAI’s new model crushes my benchmark
Claire Vo compares OpenAI's new GPT 5.6 models (Soul, Terra, Luna) against Claude's Fable using her custom "How I AI" benchmark, finding that GPT 5.6 Soul excels at practical product work, prototyping, and natural communication, while Fable is theoretically intelligent but pedantic and difficult to collaborate with.
Context offloading is an underrated AI use case
The speaker highlights context offloading as an underrated AI use case, where AI serves as a safety net for routine cognitive tasks like email management and personal finances. Rather than adding new capabilities, AI reduces anxiety about missing important information or making mistakes by handling monitoring tasks, thereby freeing up mental bandwidth.