Click any tag below to further narrow down your results
Links
Google Labs is launching Stitch Loop, an agent that connects to your codebase and live metrics, finds problems after code ships, and proposes fixes as GitHub pull requests for your approval. It runs on loops for security, latency, accessibility, and custom goals like checkout conversion.
- Stitch Loop runs four steps per loop: surface suggestions from product data, offer solutions with tradeoffs, build the fix in a cloud sandbox and open a PR, then monitor live metrics to see if the goal holds.
- The security loop combines Gemini 4 Carbon's cybersecurity capabilities with CodeMender, DeepMind's autonomous code-security agent, and flags each issue with evidence and a proposed fix.
- It plugs into existing tools: coding agents like Google Antigravity can pull its product context through the Stitch CLI and MCP, and teams can get daily insight digests in Slack. The waitlist opened globally, with Google AI Ultra users getting priority.
@IATheYoker on X
Google Labs released DESIGN.md, a free open standard that lets AI agents read a project's design system, covering color and typography tokens, WCAG accessibility checks, and portability across tools. The post frames it as a direct response to Anthropic's restricted, paid Claude Design.
- DESIGN.md is a single file that describes design tokens (colors, typography, spacing) in natural language so an AI can understand what each value is for, not just its value.
- The standard has agents check their design decisions against WCAG accessibility rules without a person reviewing every detail by hand.
- Rules can be exported and imported between projects and tools, including Anthropic's own, which the post presents as the sharpest part of the move.