Claude Code is Anthropic's agentic coding tool: a Claude-powered agent that works in the terminal and editor, reading the codebase, running commands, and making changes under human review. We use it daily across our projects, with every change reviewed and committed through our normal git workflow. For a studio that publishes open research on LLM behavior, using the tools we study is the only honest way to work.
How We Use It
- Feature development and refactoring under human review
- Codebase-wide audits: accessibility, SEO, dependency hygiene
- Content operations: publishing, migrations, structured-data upkeep
AI / LLM
Why this matters: Controversial, misunderstood, and overhyped though they may be, AI and LLMs are transforming industries and society. Used carefully and responsibly, they are still a valuable tool for innovation and progress. We design and deploy LLM-powered features with a focus on safety, performance, and maintainability, leveraging managed model providers and an SDK-first approach for rapid iteration. Preferred defaults: Vercel AI SDK + AI Gateway for multi-model orchestration; Anthropic and OpenAI as primary model providers.