Claude Sonnet 4.6 is the backbone of our entire platform, Humans.Team. Over 85 development sessions, Claude Code (powered by Sonnet) built 90% of our Next.js application — from Supabase database architecture and Row Level Security policies to AI journal integration, real-time notifications, PWA offline support, and a bilingual FR/EN system across 30+ pages.
What sets Sonnet 4.6 apart is its ability to hold deep context across long sessions. It remembers architectural decisions from hours ago, understands our codebase patterns, and writes production-ready TypeScript that rarely needs fixing. The reasoning is exceptional — it debugs complex issues by tracing through multiple files and connections.
We also use Claude Desktop daily for content strategy, press releases, blog articles, and bilingual copywriting. The nuance in both French and English is remarkable.
honestly the design system auto-apply is the part that gets me most excited here. been prototyping landing pages with Claude for a while now and the biggest pain was always manually fixing brand colors and spacing after generation. if this actually learns your team's tokens and applies them consistently that's a massive time save. curious how it handles edge cases tho - like does it respect component-level overrides or just global styles?
I've tried this and found that I can create a marketing video from reading my codebase in 10 minutes. 🤔 But just to do this, it costs me 46% of my weekly limit. 😂
I have a question....Would this be capable of creating a walkthrough to a newly created app? And if so, can Claude Code leverage Claude Design for this task, through an available MCP?
I've answered this myself. I was able to create a fairly interactive walkthrough using screenshots. It did a rather impressive work. Absolutely love it. Unfortunately, the limits are not enough. It's already using extra credit off my account and I'm on the Max Plan
Athena
I heard it uses double tokens compared to working with Claude Code via Figma MCP. What are the main benefits of this?
The description targets designers, founders, AND marketers as separate audiences. Does the prompting experience actually adapt to those different skill levels, or is it the same interface regardless? A founder who's never opened Figma and a senior designer asking for the same output are going to need very different feedback loops.
Hey, can this send my creation to Figma so I can make adjustments there and then send it back to Claude?