I design with Claude more than Figma now — Jane Street designer workflow

Edwin Morris, a designer at Jane Street, describes how Claude Code has largely replaced Figma in his design workflow. Instead of spec docs, Figma mockups, and proposal reviews, he now builds prototype features directly in the codebase using Claude Code. The workflow: write a problem description and proposal → open editor with Claude → prompt with the description → get a working prototype → iterate → push to dev environment → get user feedback → submit a feature (PR).
Key quote: “A prototype feature in the actual codebase has felt better in almost every way compared to mockups and docs.” Morris reports that Claude Code gives “free, unlimited iteration” — he refined a Submit button, added keyboard shortcuts, tweaked copy, adjusted prompts, and added confirmation messages. These workflow improvements “would have taken days or weeks of engineering and design back-and-forth” at his previous job.
The switch happened gradually. When he joined Jane Street in summer 2025, he used AI only for small UX papercut fixes. For bigger ideas, he still used Figma and docs. But “in the past 2 months the situations where I’ve reached for Figma have fallen off a cliff.” He now uses Claude for bigger work: “a half dozen other prototypes that make user-facing, data model, and library changes, including some that are 2000+ line diffs.” For some new apps, he even skips Figma entirely, “iterating on the visual design from the beginning with Claude.”
The one downside: reviewers receive a fully baked feature instead of a mockup, which can reduce design input. The team’s solution: write a reminder in the description that “prototypes are living proposal docs, the code is disposable, and a reviewer’s job is to give feedback about the design and user experience.” The reviewer eventually takes over the idea and implements production code in a separate feature.
📖 Read the full source: HN AI Agents
👀 See Also

HuggingFace Agent Skills: Standardized AI Task Definitions for Coding Agents
HuggingFace Skills are self-contained folders with YAML frontmatter and guidance for AI agents to perform specific ML tasks like dataset creation, model training, and evaluation. They're interoperable with OpenAI Codex, Anthropic's Claude Code, Google Gemini CLI, and Cursor.

Open-source Claude Code reimplementation patched for local model compatibility
A developer patched the open-source Claude Code reimplementation to work with Ollama and local models by removing hardcoded Anthropic client dependencies. The CLI now auto-detects providers from model names and environment variables.

rawq: Local CLI Tool for AI Agent Semantic Code Search
rawq is an open-source CLI tool that helps AI agents find relevant code using semantic search with a 33MB local model via ONNX runtime and BM25 lexical search via tantivy. In testing, AI agents using rawq consumed 4x fewer tokens and completed tasks 2x faster compared to blind read/grep tools.

Ollama Update Adds OpenClaw Support for Kimi k2.5 Cloud Model
Ollama has released an update that integrates OpenClaw support for cloud models, including free access to the Kimi k2.5 model with web search functionality, running on NVIDIA data centers.