DESIGN.md: format specification for communicating visual identity to coding agents
Google Labs has published a format specification called DESIGN.md, a structured file format for describing a visual identity and design system to coding agents. The spec aims to give agents persistent, structured context about design systems so they can produce visually consistent code. The project has accumulated over 15,000 GitHub stars, indicating significant community interest.
Related guides (1)
Related events (8)
OpenAI Codex and Figma Launch Code-to-Design Integration
OpenAI and Figma have announced a partnership integrating Codex into Figma's design platform, enabling bidirectional movement between code and design canvas. The integration aims to accelerate product development workflows by allowing teams to iterate between implementation and design artifacts more fluidly. This represents a deployment of Codex capabilities into a major design toolchain.
Anthropic Launches Claude Design: AI-Powered Visual Design and Prototyping Tool
Anthropic has launched Claude Design, a new product under its Anthropic Labs umbrella that enables collaborative visual design work including prototypes, slides, wireframes, and marketing collateral. Powered by Claude Opus 4.7, the tool supports brand system ingestion, inline editing, multi-user collaboration, and direct handoff to Claude Code for implementation. It is available in research preview for Claude Pro, Max, Team, and Enterprise subscribers, with integrations including Canva and PPTX export. The product targets both professional designers seeking faster exploration and non-designers needing to produce visual work.
Jane Street engineer: Claude Code replacing Figma in design workflow
A Jane Street engineer describes shifting their design workflow to rely primarily on Claude Code rather than Figma. The post documents a practitioner's experience using LLM-assisted coding tools as a design medium, suggesting meaningful workflow displacement of traditional design tooling. With 157 HN points and 118 comments, the post is generating notable community discussion.
sqlite AGENTS.md
Simon Willison publishes an AGENTS.md file for the SQLite project, a convention for providing AI coding agents with project-specific instructions and context. This follows the emerging practice of including agent-readable documentation files in codebases to guide LLM-based tools. The post reflects the growing ecosystem of conventions around agentic coding workflows.
Hugging Face Blog: Model Cards
This Hugging Face blog post discusses model cards as a documentation standard for machine learning models, covering their purpose, structure, and adoption within the ML community. Model cards provide structured metadata and transparency information about a model's intended use, limitations, training data, and evaluation results. The post likely outlines best practices and tooling support for creating and maintaining model cards on the Hugging Face Hub.
Introducing the Model Spec
OpenAI published its Model Spec, a document outlining the intended values, behaviors, and decision-making principles for its AI models. The spec defines a hierarchy of priorities—safety, ethics, adherence to OpenAI's principles, and helpfulness—and is intended to guide how models should behave across a wide range of situations. This represents OpenAI's formal attempt to codify alignment goals and behavioral norms into a publicly accessible framework.
Coding and Design with GPT-5
OpenAI published a blog post highlighting GPT-5's capabilities in coding and design workflows. The post appears to be a use-case showcase demonstrating how GPT-5 enables new possibilities in these domains. As a Tier 1 source announcement, it signals continued OpenAI promotion of GPT-5 for developer and creative audiences. Specific technical details are not provided in the body excerpt.
Introducing IDEFICS: An Open Reproduction of State-of-the-art Visual Language Model
Hugging Face released IDEFICS, an open-weights reproduction of DeepMind's Flamingo visual language model. The release aims to provide the research community with an accessible, open alternative to proprietary multimodal models. IDEFICS supports image-text interleaved inputs and is available on the Hugging Face Hub.