Cursor introduces Design Mode, enabling developers to modify and update their application's user interface by pointing, drawing, or using voice commands.

// 1h agoPRODUCT UPDATE

Cursor introduces Design Mode, enabling developers to modify and update their application's user interface by pointing, drawing, or using voice commands.

Cursor has introduced Design Mode, a new feature allowing developers to update their user interface dynamically by pointing, drawing, or speaking. The tool is designed to streamline front-end workflows, especially for "vibe coders" who rely heavily on AI to build projects with minimal manual coding. It translates visual gestures and voice commands into codebase changes, reducing the need for raw styling and layout programming.

// ANALYSIS

Visual design via natural language and drawing is a significant step towards full UI automation, but the generated layout code will still require developer guardrails.

* Directly manipulating UIs by pointing and drawing dramatically reduces front-end iteration times.

* This feature empowers visual designers and non-technical stakeholders to make codebase changes directly.

* Precision is a potential issue, as translating freeform drawings and voice cues into CSS grids or flexbox can produce bloated styling.

* Developers will need to maintain vigilance over the quality, structure, and maintainability of the generated UI code.

// TAGS

`["ai""devtool""ui-design""front-end""vibe-coding"]`-→-`["ai""ai-coding"]`

DISCOVERED

1h ago

2026-06-07

PUBLISHED

2h ago

2026-06-07

RELEVANCE

8/ 10

AUTHOR

toolfolio

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

NEWS1h ago

OpenAI Codex CLI criticized over exit prompts

Developer Kun Chen highlights a design flaw in the OpenAI Codex CLI harness, where typing "exit" does not terminate the session locally but is instead sent to the LLM as a prompt. This lack of local interception results in an unnecessary API call and inference cycle, wasting energy and user tokens.

MODEL1h ago

Boson AI launches Higgs Audio v3

Boson AI has launched Higgs Audio v3, a 4B parameter text-to-speech model built on a Qwen3-4B backbone and optimized for real-time conversational streaming and zero-shot cloning across 100+ languages. The model supports inline style tags for prosody and emotion control, and integrates with the newly released SGLang-Omni inference framework for low-latency deployment.

RESEARCH1h ago

Stability AI releases Stable-Layers, a reinforcement learning framework that trains image layer decomposition models without paired supervision data using Flow-GRPO and VLM feedback.

Stability AI has introduced Stable-Layers, a reinforcement learning framework designed to train image layer decomposition models without requiring paired training datasets. Traditionally, splitting a flat image into editable, multi-layer components required intensive human annotation. Stable-Layers bypasses this by adapting Group Relative Policy Optimization (GRPO) for flow-matching models (Flow-GRPO) to optimize image decomposition. The training is guided by a Vision-Language Model (VLM) serving as a judge, using a structured scoring and grid-based calibration pipeline to provide high-quality reward signals. This approach significantly reduces color bleed and blank layer artifacts, producing cleaner semantic separation.

Cursor introduces Design Mode, enabling developers to modify and update their application's user interface by pointing, drawing, or using voice commands.