# AI in frontend development

The use of artificial intelligence tools and agents to assist frontend software development tasks such as code generation, UI design, debugging, refactoring, testing, and accessibility checks.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Inside the AI software factory: Where accessibility is won or lost

DevFeed: [Inside the AI software factory: Where accessibility is won or lost](<https://devfeed.tech/articles/inside-the-ai-software-factory-where-accessibility-is-won-or-lost-147465.md>)

Original publisher: [Read original article](<https://www.deque.com/blog/inside-the-ai-software-factory-where-accessibility-is-won-or-lost/>)

Author: Dylan Barrell

Published: 2026-11-19T13:28:07Z

Content type: article

Language: en

Sources: [Deque](<https://devfeed.tech/sources/deque.md>)

Topics: [Web Accessibility (a11y)](<https://devfeed.tech/topics/web-accessibility.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [Web Content Accessibility Guidelines](<https://devfeed.tech/topics/web-content-accessibility-guidelines.md>), [axe-core](<https://devfeed.tech/topics/axe-core.md>), [Software Process](<https://devfeed.tech/topics/software-process.md>), [Requirements](<https://devfeed.tech/topics/requirements.md>), [aria](<https://devfeed.tech/topics/aria.md>), [axe MCP Server](<https://devfeed.tech/topics/axe-mcp-server.md>), [Tech Debt](<https://devfeed.tech/topics/tech-debt.md>)

Tags: [a11y-for-developers](<https://devfeed.tech/tags/a11y-for-developers.md>), [accessibility](<https://devfeed.tech/tags/accessibility.md>), [accessibility-requirements](<https://devfeed.tech/tags/accessibility-requirements.md>), [accessibility-testing](<https://devfeed.tech/tags/accessibility-testing.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-software-factory](<https://devfeed.tech/tags/ai-software-factory.md>), [ai-workflows](<https://devfeed.tech/tags/ai-workflows.md>), [assistive-technology](<https://devfeed.tech/tags/assistive-technology.md>), [audit](<https://devfeed.tech/tags/audit.md>), [audits](<https://devfeed.tech/tags/audits.md>), [automation](<https://devfeed.tech/tags/automation.md>), [axe-core](<https://devfeed.tech/tags/axe-core.md>), [digital-accessibility](<https://devfeed.tech/tags/digital-accessibility.md>), [risk](<https://devfeed.tech/tags/risk.md>), [shift-left](<https://devfeed.tech/tags/shift-left.md>), [software-factory](<https://devfeed.tech/tags/software-factory.md>), [technical-debt](<https://devfeed.tech/tags/technical-debt.md>)

### AI overview

The article argues that accessibility should be built into AI software factories from the start, because late fixes increase rework and production fixes are reported to cost 30 times more than design fixes. It recommends accessibility criteria in UI tickets; deterministic checks such as Axe-core and lint rules wherever possible; agents steered with relevant context and integration tests; independent test records tied to the code; and monitoring, audits, and customer feedback after release. Use AI for judgment calls, such as whether a label fits its context, and rules based tools for repeatable checks. In the article's preliminary comparison, prompting was least predictable; open source tooling caught 50% of baseline audit defects, while paid tooling caught 69%, with fewer reported false positives and more consistent results. The authors say homegrown tools require maintenance and expertise. Automation still misses issues: end to end journeys, real assistive technology use, and human review remain necessary. Measure missed production issues and the share of UI changes with accessibility evidence, and feed recurring problems back into factory rules and tests.

### Source excerpt

As your organization moves development into AI software factories, you must fully embed digital accessibility, just as you must integrate privacy and security. Get it right, and your products, services, and experiences become and stay accessible. Get it wrong, and you increase risk, cost, and technical debt. The post Inside the AI software factory: Where accessibility is won or lost appeared first on Deque.

## AI Software Factory Building Blocks for 2027

DevFeed: [AI Software Factory Building Blocks for 2027](<https://devfeed.tech/articles/ai-software-factory-building-blocks-for-2027-143902.md>)

Original publisher: [Read original article](<https://hackernoon.com/ai-software-factory-building-blocks-for-2027?source=rss>)

Author: QA.tech

Published: 2026-11-19T12:17:47Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [2](<https://devfeed.tech/tags/2.md>), [2026](<https://devfeed.tech/tags/2026.md>), [2027](<https://devfeed.tech/tags/2027.md>), [3](<https://devfeed.tech/tags/3.md>), [about](<https://devfeed.tech/tags/about.md>), [acceptance](<https://devfeed.tech/tags/acceptance.md>), [addy-osmani](<https://devfeed.tech/tags/addy-osmani.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-software](<https://devfeed.tech/tags/ai-software.md>), [ai-software-building-blocks](<https://devfeed.tech/tags/ai-software-building-blocks.md>), [ai-software-factory](<https://devfeed.tech/tags/ai-software-factory.md>), [ai-testing](<https://devfeed.tech/tags/ai-testing.md>), [autonomous-software-engineerin](<https://devfeed.tech/tags/autonomous-software-engineerin.md>), [autonomy](<https://devfeed.tech/tags/autonomy.md>), [blocks](<https://devfeed.tech/tags/blocks.md>), [building](<https://devfeed.tech/tags/building.md>), [can](<https://devfeed.tech/tags/can.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [factory](<https://devfeed.tech/tags/factory.md>), [good-company](<https://devfeed.tech/tags/good-company.md>), [software](<https://devfeed.tech/tags/software.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [software-factory](<https://devfeed.tech/tags/software-factory.md>), [tools](<https://devfeed.tech/tags/tools.md>), [trust](<https://devfeed.tech/tags/trust.md>), [verification](<https://devfeed.tech/tags/verification.md>)

### AI overview

An AI software factory runs multiple coding agents in parallel on queued work, with automated checks and review gates. Because code generation can scale faster than verification, safe autonomy depends on checking the running product, not just the diff: unit tests check code, review bots inspect changes, and an independent QA agent can exercise user goals on a live app. The excerpt describes verification before a PR through MCP tools in Claude Code, Cursor, or Codex, and PR checks against a preview deployment (or staging after merge), reporting pass, fail, or unable to verify. It recommends previews, running-app checks on every PR, risk-based review gates, and increasing autonomy only as verification capacity allows. Human judgment remains important for regulated domains, legacy systems, and usability decisions; the source favors a light factory for many teams and warns that dark factories can increase comprehension debt.

### Source excerpt

Eight building blocks of an AI software factory, the tools behind them, and why verification determines how much autonomy you can trust.

## Introducing Stitch Loop: A new way to build and evolve products

DevFeed: [Introducing Stitch Loop: A new way to build and evolve products](<https://devfeed.tech/articles/introducing-stitch-loop-a-new-way-to-build-and-evolve-products-141507.md>)

Original publisher: [Read original article](<https://blog.google/innovation-and-ai/models-and-research/google-labs/stitch-loop/>)

Author: Justin Toupin

Published: 2026-11-18T17:00:00Z

Content type: release

Language: en

Sources: [Google Labs](<https://devfeed.tech/sources/google-labs.md>)

Topics: [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [Automation](<https://devfeed.tech/topics/automation.md>), [product analytics](<https://devfeed.tech/topics/product-analytics.md>), [User interface design](<https://devfeed.tech/topics/ui-design.md>), [Business, Industry, Usability, User Experience, User Research, Web Strategy](<https://devfeed.tech/topics/business-industry-usability-user-experience-user-research-web-strategy.md>), [UI/UX Design](<https://devfeed.tech/topics/ui-ux-design.md>)

Tags: [accessibility](<https://devfeed.tech/tags/accessibility.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [automate](<https://devfeed.tech/tags/automate.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [build](<https://devfeed.tech/tags/build.md>), [built-in](<https://devfeed.tech/tags/built-in.md>), [checkout](<https://devfeed.tech/tags/checkout.md>), [checkout-conversion](<https://devfeed.tech/tags/checkout-conversion.md>), [cli](<https://devfeed.tech/tags/cli.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [code](<https://devfeed.tech/tags/code.md>), [code-security](<https://devfeed.tech/tags/code-security.md>), [google-labs](<https://devfeed.tech/tags/google-labs.md>), [latency](<https://devfeed.tech/tags/latency.md>), [none](<https://devfeed.tech/tags/none.md>), [products](<https://devfeed.tech/tags/products.md>), [security](<https://devfeed.tech/tags/security.md>), [stitch](<https://devfeed.tech/tags/stitch.md>)

### AI overview

Stitch Loop is a Google Labs product agent that connects a codebase with product context and live metrics, then repeatedly proposes and builds improvements toward measurable goals. Its workflow presents evidence-backed suggestions and scoped solutions with tradeoffs, writes selected changes in an isolated cloud sandbox, and opens a GitHub pull request for human review; nothing merges without approval. It monitors results and continues watching after a goal is met. The text describes built-in security, latency, and accessibility loops, plus custom loops. Its security loop pairs Gemini 4 Carbon with CodeMender to find vulnerabilities and propose fixes in reviewable PRs. Stitch Loop can also provide persistent product context to coding agents through Stitch CLI and MCP, and supports Slack digests and loop creation. Access is via a waitlist, with eligible Google AI Ultra users receiving priority.

### Source excerpt

Arrow, reload, and message icons. At the bottom are the text "Security", "Latency", "Accessibility", "Stitch Loop"

## Microsoft launches MAI Code 2 models to challenge OpenAI and Anthropic in AI coding

DevFeed: [Microsoft launches MAI Code 2 models to challenge OpenAI and Anthropic in AI coding](<https://devfeed.tech/articles/microsoft-launches-mai-code-2-models-to-challenge-openai-and-anthropic-in-ai-coding-140729.md>)

Original publisher: [Read original article](<https://www.infoworld.com/article/4250152/microsoft-launches-mai-code-2-models-to-challenge-openai-and-anthropic-in-ai-coding.html>)

Author: Nidhi Singal

Published: 2026-11-18T11:43:31Z

Content type: news

Language: en

Sources: [InfoWorld](<https://devfeed.tech/sources/infoworld.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Microsoft](<https://devfeed.tech/topics/microsoft.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [code security](<https://devfeed.tech/topics/code-security.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-costs](<https://devfeed.tech/tags/ai-costs.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-development-tools-software-development](<https://devfeed.tech/tags/artificial-intelligence-development-tools-software-development.md>), [azure](<https://devfeed.tech/tags/azure.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [ceo](<https://devfeed.tech/tags/ceo.md>), [changes](<https://devfeed.tech/tags/changes.md>), [claude](<https://devfeed.tech/tags/claude.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [development-tools](<https://devfeed.tech/tags/development-tools.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [mai](<https://devfeed.tech/tags/mai.md>), [mai-code-2](<https://devfeed.tech/tags/mai-code-2.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [models](<https://devfeed.tech/tags/models.md>), [openai](<https://devfeed.tech/tags/openai.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>)

### AI overview

Microsoft's MAI Code 2 targets enterprise coding work such as debugging and multi-file changes; MAI Code 2 Flash is aimed at high-volume explanations, edits and routine fixes. In Microsoft's cited benchmarks, Code 2 averaged 63.2%, below GPT-6.1 Sol (64.1%) and Claude Opus 5.5 (65.3%), while Flash averaged 61%, above GPT-6 Luna (55.1%) and Claude Haiku 5.5 (53.9%) on a different, three-benchmark comparison. Microsoft reports lower average task costs, but those comparisons use 50% promotional pricing; the promotion runs through May 17, 2027 for Code 2, after which token prices double. The excerpt cautions that model fees are only part of software delivery costs, and recommends testing on an organization's own code and tools while tracking cost per merged change, failures and security findings. Microsoft model cards rate both models highly on offensive cyber capabilities, so security and reliability in production also warrant evaluation. The models are not yet tuned for fundamental science research or long-horizon agentic work.

### Source excerpt

Microsoft has launched a pair of AI coding models that it says can compete with offerings from OpenAI and Anthropic, marking its latest effort to build proprietary AI capabilities and reduce reliance on the partners that helped fuel its generative AI push. The two new models, MAI Code 2 and MAI Code 2 Flash, were launched at Ignite 2026. MAI Code 2 is designed for common enterprise coding tasks such as deep debugging, implementing changes across multiple files, repository-wide reasoning, and user interface development. MAI Code 2 Flash, meanwhile, targets high-volume tasks such as code explanations, targeted edits, routine fixes and rapid iterations. Microsoft said it built these models to prioritize the coding work its customers do every day. The new models are explicitly not yet tuned for harder problems, like fundamental science research and long-horizon agentic work, the company noted in the press statement. The launch also marks another step in Microsoft's effort to build its own AI model capabilities and reduce its reliance on external providers. With the launch of new coding models, Microsoft reduces its dependence on OpenAI and Anthropic, said Pareekh Jain, CEO at EIIRTrend & Pareekh Consulting. "Microsoft also has a major advantage through GitHub, Visual Studio and Azure, which are already used by millions of developers. Its immediate goal is to strengthen its developer ecosystem and reduce AI costs. So it doesn't have to pay OpenAI and Anthropic every time someone uses GitHub Copilot. Microsoft is protecting its profits and locking developers into its own tools," he added. Microsoft's models put to the coding test Microsoft compared MAI Code 2 with competing models across four widely used benchmarks in GitHub Copilot: DeepSWE 1.1, Terminal-Bench 2.1, SWE-Atlas and FrontierCode v1.1. In the average pass rate across these benchmarks, MAI Code 2 recorded an average score of 63.2%, compared with 64.1% for OpenAI's GPT-6.1 Sol and 65.3% for Anthropic's Claude O

## Friday Links #47: JavaScript News, Tools and Fresh Releases

DevFeed: [Friday Links #47: JavaScript News, Tools and Fresh Releases](<https://devfeed.tech/articles/friday-links-47-javascript-news-tools-and-fresh-releases-147021.md>)

Original publisher: [Read original article](<https://jsdev.space/friday/friday-47/>)

Author: anton liberant

Published: 2026-11-18T00:00:00Z

Content type: news

Language: en

Sources: [JavaScript Development](<https://devfeed.tech/sources/javascript-development.md>)

Topics: [Web Development](<https://devfeed.tech/topics/web-development.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [React](<https://devfeed.tech/topics/react.md>), [Node.js](<https://devfeed.tech/topics/node-js.md>), [releases](<https://devfeed.tech/topics/releases.md>), [performance-optimization](<https://devfeed.tech/topics/performance-optimization.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [22](<https://devfeed.tech/tags/22.md>), [2d](<https://devfeed.tech/tags/2d.md>), [articles](<https://devfeed.tech/tags/articles.md>), [developer](<https://devfeed.tech/tags/developer.md>), [developer-tools](<https://devfeed.tech/tags/developer-tools.md>), [development](<https://devfeed.tech/tags/development.md>), [explore](<https://devfeed.tech/tags/explore.md>), [framework](<https://devfeed.tech/tags/framework.md>), [friday](<https://devfeed.tech/tags/friday.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [latest](<https://devfeed.tech/tags/latest.md>), [library](<https://devfeed.tech/tags/library.md>), [links](<https://devfeed.tech/tags/links.md>), [news](<https://devfeed.tech/tags/news.md>), [releases](<https://devfeed.tech/tags/releases.md>), [the-latest](<https://devfeed.tech/tags/the-latest.md>), [tools](<https://devfeed.tech/tags/tools.md>), [updates](<https://devfeed.tech/tags/updates.md>), [web](<https://devfeed.tech/tags/web.md>), [web-development](<https://devfeed.tech/tags/web-development.md>)

### AI overview

This roundup highlights stable Solid 2.0, which adds native async reactivity and server functions while simplifying its API, and Modern Web Guidance 1.0, a locally searchable set of over 200 web standards guides for coding agents. It also reports two supply chain incidents: compromised Optimizely scripts affected at least 178 organizations, and a malicious bee-js package could steal wallet keys during installation. The text recommends CSP, monitoring third-party scripts, and checking lockfiles and CI logs as risk-reduction steps. Other releases include webpack's native CSS and HTML support, security and tooling updates, and new AI models with different performance, cost, and workload tradeoffs. This overview reflects the supplied roundup text.

### Source excerpt

Explore the latest JavaScript and web development news, framework updates, library releases, developer tools, and insightful articles in Friday Links #47.

## Giving AI Agents a Better Way to Debug CSS

DevFeed: [Giving AI Agents a Better Way to Debug CSS](<https://devfeed.tech/articles/giving-ai-agents-a-better-way-to-debug-css-140309.md>)

Original publisher: [Read original article](<https://freek.dev/3225-giving-ai-agents-a-better-way-to-debug-css>)

Author: Freek Van der Herten (freek@spatie.be)

Published: 2026-11-17T12:30:30Z

Content type: tutorial

Language: en

Sources: [Freek](<https://devfeed.tech/sources/freek-dev-all-blogposts.md>)

Topics: [CSS](<https://devfeed.tech/topics/css.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [Tool](<https://devfeed.tech/topics/tool.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [browser](<https://devfeed.tech/tags/browser.md>), [cascade](<https://devfeed.tech/tags/cascade.md>), [chrome-devtools-mcp](<https://devfeed.tech/tags/chrome-devtools-mcp.md>), [codex](<https://devfeed.tech/tags/codex.md>), [css](<https://devfeed.tech/tags/css.md>), [debug](<https://devfeed.tech/tags/debug.md>), [diagnose](<https://devfeed.tech/tags/diagnose.md>)

### AI overview

Chrome DevTools MCP exposes a `get_css_styles` tool that lets Codex inspect the matched CSS rules and overridden declarations for an element in the browser. The article says this gives agents evidence about the styles actually applied, helping them diagnose cascade and specificity issues instead of guessing from source files. The supplied text is an excerpt, so it does not establish setup details or broader coverage.

### Source excerpt

Amit Merchant shows how to connect Chrome DevTools MCP to Codex and use its get_css_styles tool to inspect matched CSS rules and overridden declarations in the browser. This lets agents diagnose cascade and specificity issues using the styles actually applied to an element instead of guessing from source files. Read more

## AI Sped Up The Build: How Can Accessibility Testing Keep Up?

DevFeed: [AI Sped Up The Build: How Can Accessibility Testing Keep Up?](<https://devfeed.tech/articles/ai-sped-up-the-build-how-can-accessibility-testing-keep-up-138598.md>)

Original publisher: [Read original article](<https://smashingmagazine.com/2026/11/ai-sped-up-build-how-can-accessibility-testing-keep-up/>)

Author: hello@smashingmagazine.com (Andrew Chung)

Published: 2026-11-17T08:00:00Z

Content type: article

Language: en

Sources: [Smashing Magazine](<https://devfeed.tech/sources/articles-on-smashing-magazine-for-web-designers-and-developers.md>)

Topics: [Web Accessibility (a11y)](<https://devfeed.tech/topics/web-accessibility.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Web Content Accessibility Guidelines](<https://devfeed.tech/topics/web-content-accessibility-guidelines.md>), [aria](<https://devfeed.tech/topics/aria.md>)

Tags: [accessibility](<https://devfeed.tech/tags/accessibility.md>), [accessibility-testing](<https://devfeed.tech/tags/accessibility-testing.md>), [ai](<https://devfeed.tech/tags/ai.md>), [human-judgment](<https://devfeed.tech/tags/human-judgment.md>), [testing](<https://devfeed.tech/tags/testing.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

AI accelerated planning, design, and development more often than QA: in a survey of more than 2,500 professionals, 58%, 61%, and 51% reported gains in those stages, versus 30% in QA and testing. The article argues that AI adoption alone did not distinguish organizations improving across accessibility measures; training, communication, and accessibility culture did. It recommends embedding human judgment into existing handoffs, pull requests, fixes, and reviews: specify accessibility behavior at design handoff, automate repeatable checks in CI, assign owners, use AI-generated fixes only as drafts, verify behavior with people, and preserve evidence through regression tests and PR notes. Automated checks can miss usability problems, and survey findings show correlation rather than causation.

### Source excerpt

AI has sped up how teams design and build, but quality assurance (QA) testing hasn't kept pace, and the web may be getting less accessible. Drawing on new research, Andrew Chung explains what separates the teams whose accessibility efforts are keeping up, and how to embed human judgment into AI-enabled workflows without slowing delivery.

## AI Is Dividing Product Designers: Exploring vs. Building

DevFeed: [AI Is Dividing Product Designers: Exploring vs. Building](<https://devfeed.tech/articles/ai-is-dividing-product-designers-exploring-vs-building-136901.md>)

Original publisher: [Read original article](<https://hackernoon.com/ai-is-dividing-product-designers-exploring-vs-building-aytom8l?source=rss>)

Author: Andrii Bondar

Published: 2026-11-17T06:45:35Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [AI-enhanced product development](<https://devfeed.tech/topics/ai-enhanced-product-development.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [UI/UX Design](<https://devfeed.tech/topics/ui-ux-design.md>), [implementation](<https://devfeed.tech/topics/implementation.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [Figma](<https://devfeed.tech/topics/figma.md>), [Tool](<https://devfeed.tech/topics/tool.md>)

Tags: [adoption](<https://devfeed.tech/tags/adoption.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [ai-product-development](<https://devfeed.tech/tags/ai-product-development.md>), [ai-prototyping](<https://devfeed.tech/tags/ai-prototyping.md>), [ai-trends](<https://devfeed.tech/tags/ai-trends.md>), [ai-workflow-automation](<https://devfeed.tech/tags/ai-workflow-automation.md>), [building](<https://devfeed.tech/tags/building.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [design](<https://devfeed.tech/tags/design.md>), [design-engineer](<https://devfeed.tech/tags/design-engineer.md>), [design-engineering](<https://devfeed.tech/tags/design-engineering.md>), [design-ux](<https://devfeed.tech/tags/design-ux.md>), [designers](<https://devfeed.tech/tags/designers.md>), [engineer](<https://devfeed.tech/tags/engineer.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [exploring](<https://devfeed.tech/tags/exploring.md>), [figma](<https://devfeed.tech/tags/figma.md>), [product](<https://devfeed.tech/tags/product.md>), [product-design](<https://devfeed.tech/tags/product-design.md>), [product-development](<https://devfeed.tech/tags/product-development.md>), [push-ux-2026](<https://devfeed.tech/tags/push-ux-2026.md>), [ux](<https://devfeed.tech/tags/ux.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

The article argues that AI adds lasting value to product design when it improves how teams work and the products they deliver, rather than merely speeding up tasks or accumulating pilots. At PUSH UX, an IKEA speaker warned against an "AI first, AI everything" approach; the author recommends identifying workflow friction and handoffs where AI could help. AI-assisted development can let designers build, test, and iterate closer to production, as the author's shift from Figma to Claude Code illustrates, while interactive prototypes can also be made for specific hardware without production coding. The author says designers need not become full-time engineers, and deep specialization remains important. Faster exploration still requires critical judgment: AI research can be shallow or generic, so teams must guide and evaluate its output and maintain quality, security, and reliability.

### Source excerpt

Design Engineer Andrii Bondar about PUSH UX and how AI is transforming product design, UX workflows, and design engineering, from Figma to Claude Code.

## Axe MCP Server now has a free plan

DevFeed: [Axe MCP Server now has a free plan](<https://devfeed.tech/articles/axe-mcp-server-now-has-a-free-plan-144205.md>)

Original publisher: [Read original article](<https://www.deque.com/blog/axe-mcp-server-now-has-a-free-plan/>)

Author: Harris Schneiderman

Published: 2026-11-16T14:02:00Z

Content type: release

Language: en

Sources: [Deque](<https://devfeed.tech/sources/deque.md>)

Topics: [axe MCP Server](<https://devfeed.tech/topics/axe-mcp-server.md>), [axe-core](<https://devfeed.tech/topics/axe-core.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>)

Tags: [a11y-for-developers](<https://devfeed.tech/tags/a11y-for-developers.md>), [accessibility](<https://devfeed.tech/tags/accessibility.md>), [accessibility-testing](<https://devfeed.tech/tags/accessibility-testing.md>), [axe](<https://devfeed.tech/tags/axe.md>), [axe-core](<https://devfeed.tech/tags/axe-core.md>), [axe-mcp-server](<https://devfeed.tech/tags/axe-mcp-server.md>), [company-news-and-updates](<https://devfeed.tech/tags/company-news-and-updates.md>), [free-plan](<https://devfeed.tech/tags/free-plan.md>), [model-context-protocol-mcp](<https://devfeed.tech/tags/model-context-protocol-mcp.md>)

### AI overview

Deque's Axe MCP Server Free plan lets coding agents run unlimited scans of rendered web apps in a real browser using standard Axe-core rules, then rescan after fixes. This checks issues that source-code reasoning alone cannot measure, such as computed color contrast, component relationships, and script-added ARIA references. Axe-core reports detected violations and flags uncertain cases for review; its standard rules catch up to 57% of accessibility issues by volume. Deque says the paid Axe DevTools for Web plan, which includes the full server, adds advanced rules and automated Intelligent Guided Tests for up to 80% coverage, remediation guidance based on Deque's proprietary sources, and organization-wide configuration, user management, and SSO.

### Source excerpt

Deque is thrilled to announce that Axe MCP Server now has a free plan! The Axe MCP Server is a Model Context Protocol (MCP) server that integrates enterprise-grade accessibility testing directly into your development workflow. The post Axe MCP Server now has a free plan appeared first on Deque.

## DesignSpecs: A DESIGN.md Dataset of Visual Design Specifications for AI Agents

DevFeed: [DesignSpecs: A DESIGN.md Dataset of Visual Design Specifications for AI Agents](<https://devfeed.tech/articles/designspecs-a-design-md-dataset-of-visual-design-specifications-for-ai-agents-136507.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17713>)

Author: Jialiang Wei, Walid Maalej

Published: 2026-11-16T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [User interface design](<https://devfeed.tech/topics/ui-design.md>), [Design system](<https://devfeed.tech/topics/design-system.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [managing large-scale text data in AI](<https://devfeed.tech/topics/managing-large-scale-text-data-in-ai.md>), [json lines format](<https://devfeed.tech/topics/json-lines-format.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [design-tokens](<https://devfeed.tech/tags/design-tokens.md>), [visual-design](<https://devfeed.tech/tags/visual-design.md>)

### AI overview

DesignSpecs provides a curated dataset of 36,906 DESIGN.md files from 15,794 public, non-fork GitHub repositories, containing 17,240 unique file contents. The authors collected 613,207 files with that name in October 2026, then filtered for YAML front matter, a design-system name, at least one recognized design token, and zero errors under the official linter to exclude unrelated design documents. The JSON Lines release offers file-level and deduplicated views of the original Markdown, links entries to repositories, paths, and commits, and includes related scripts. The format captures visual identity through design tokens and Markdown prose; the dataset is intended to support research on visual design knowledge and design-aware AI agents.

### Source excerpt

arXiv:2611.17713v1 Announce Type: new Abstract: While AI agents increasingly generate and modify user interfaces, they rarely rely on a visual design specification for a certain project. The DESIGN.md format, which originated from Google's AI design tool Stitch and which was open-sourced in April 2026, addresses this gap by describing a visual identity through design tokens (such as named colors, text styles) and Markdown prose. To our knowledge, no large-scale research dataset of such design specification files exists. We present DesignSpecs, a dataset of 36,906 DESIGN.md files from 15,794 public, non-fork GitHub repositories, representing 17,240 unique file contents. We collected 613,207 files named DESIGN.md in October 2026. Because the same file name also denotes architectural plans and other design documents, we filtered those with YAML front matter, a design-system name, at least one recognized design token, and zero errors under the official linter. Our JSON Lines dataset provides file-level and deduplicated views of the original Markdown, links files to repositories, paths, and commits, and is released with related scripts. We outline research opportunities on visual design knowledge and design-aware AI agents. Dataset is available at: https://huggingface.co/datasets/Jl-wei/DesignSpecs

## JoyFrontBench: Evaluating Front-End Coding Agents through Goal-Oriented Acceptance Contracts

DevFeed: [JoyFrontBench: Evaluating Front-End Coding Agents through Goal-Oriented Acceptance Contracts](<https://devfeed.tech/articles/joyfrontbench-evaluating-front-end-coding-agents-through-goal-oriented-acceptance-contracts-131701.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.14952>)

Author: Xiaoyi Qiao, Yicheng Wang, Jianan Lin, Xiaoyang Ji, Dongyi Lv, Yidan Huang, Shi Suo, Shiying Fan, Nan Duan, Jiaqi Wang

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Front end](<https://devfeed.tech/topics/frontend.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [Software Testing](<https://devfeed.tech/topics/software-testing.md>), [test](<https://devfeed.tech/topics/test.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>)

Tags: [acceptance](<https://devfeed.tech/tags/acceptance.md>), [agents](<https://devfeed.tech/tags/agents.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [contracts](<https://devfeed.tech/tags/contracts.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [front-end](<https://devfeed.tech/tags/front-end.md>), [performance](<https://devfeed.tech/tags/performance.md>), [tasks](<https://devfeed.tech/tags/tasks.md>)

### AI overview

JoyFrontBench distinguishes graded task performance from application success using acceptance contracts defined before generation. A core task passes only when all mandatory criteria and a shared completion threshold are met; an application succeeds only when every core task passes on the same operational artifact in one run. The benchmark contains 100 problems, 764 tasks, and 2,596 criteria, with reviewed links between user goals and required evidence. Its evaluation combines evidence-grounded judgments with deterministic record audits and fixed scoring rules. Across five models, the reported mean Average Task Score under OpenHands was 87.69%, while mean Application Success Rate was 51.52%, showing that high task scores can coexist with failures on essential workflows. The study also reports model ranking changes between OpenHands and OpenCode and variation in application success across repeated runs.

### Source excerpt

arXiv:2611.14952v1 Announce Type: new Abstract: Front-end coding agents are expected to produce applications that fulfill user goals, yet high task scores can coexist with failures in essential workflows. Evaluating these agents therefore requires an explicit distinction between partial implementation and application success. We introduce JoyFrontBench, a benchmark that makes this distinction through goal-oriented acceptance contracts. Each contract identifies core tasks and mandatory criteria before generation: a core task passes only when all mandatory criteria are satisfied and a shared completion threshold is met, while application success requires every core task to pass on the same operational artifact within a single run. Derived from practitioner requirements, JoyFrontBench comprises 100 front-end development problems, 764 tasks, and 2,596 atomic criteria, with reviewed annotations linking user goals to core tasks and evidence requirements. The evaluation framework combines evidence-grounded judgments with deterministic record auditing and fixed scoring rules, preserving graded task assessment alongside explicit core-task and application-level acceptance. We evaluate five coding models under two agent harnesses, OpenHands and OpenCode, on the 70-problem test set; the remaining 30 problems form a public set for validation and diagnostic analyses. Under OpenHands, the mean Average Task Score (ATS) across models is 87.69%, while the mean Application Success Rate (ASR) is 51.52%. Further analyses reveal changes in model rankings across harnesses and variation in application success across repeated runs. These findings highlight the limitations of aggregate task scores in characterizing application success and motivate explicit assessment of core-goal fulfillment alongside graded task performance.

## Giving AI Agents a Better Way to Debug CSS

DevFeed: [Giving AI Agents a Better Way to Debug CSS](<https://devfeed.tech/articles/giving-ai-agents-a-better-way-to-debug-css-133541.md>)

Original publisher: [Read original article](<https://www.amitmerchant.com/giving-ai-agents-a-better-way-to-debug-css/>)

Author: Amit Merchant

Published: 2026-11-13T00:00:00Z

Content type: tutorial

Language: en

Sources: [Amit Merchant](<https://devfeed.tech/sources/amit-merchant.md>)

Topics: [CSS](<https://devfeed.tech/topics/css.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [Front end](<https://devfeed.tech/topics/frontend.md>), [Agent Browser](<https://devfeed.tech/topics/agent-browser.md>), [Web Development](<https://devfeed.tech/topics/web-development.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [browser](<https://devfeed.tech/tags/browser.md>), [chrome-devtools](<https://devfeed.tech/tags/chrome-devtools.md>), [codex](<https://devfeed.tech/tags/codex.md>), [css](<https://devfeed.tech/tags/css.md>), [debug](<https://devfeed.tech/tags/debug.md>), [debugging](<https://devfeed.tech/tags/debugging.md>)

### AI overview

Chrome DevTools MCP lets Codex diagnose CSS using the browser's live style information instead of inferring behavior from source files alone. After connecting the MCP server and starting the app locally, Codex can use `take_snapshot` to locate an element and `get_css_styles` to inspect matched and inherited rules, inline styles, custom properties, applicable context, and overridden declarations. The example explains that `#main .card h2` wins over `.card h2` because it has greater specificity. The article also suggests using the tool to audit potential overrides and investigate dark mode, responsive layouts, and media query conflicts. Findings and proposed changes still need review and browser verification.

### Source excerpt

Have you ever written a CSS rule, only to find out that it doesn't seem to have any effect on the element you're trying to style? You inspect the stylesheet, find the declaration, and everything looks perfectly fine. But the browser has other plans.

## AI Is Dividing Product Designers: Exploring vs. Building

DevFeed: [AI Is Dividing Product Designers: Exploring vs. Building](<https://devfeed.tech/articles/ai-is-dividing-product-designers-exploring-vs-building-131030.md>)

Original publisher: [Read original article](<https://hackernoon.com/ai-is-dividing-product-designers-exploring-vs-building?source=rss>)

Author: Andrii Bondar

Published: 2026-11-12T22:18:32Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [AI-enhanced product development](<https://devfeed.tech/topics/ai-enhanced-product-development.md>), [UI/UX Design](<https://devfeed.tech/topics/ui-ux-design.md>), [designer developer handoff](<https://devfeed.tech/topics/designer-developer-handoff.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [product mindset](<https://devfeed.tech/topics/product-mindset.md>), [implementation](<https://devfeed.tech/topics/implementation.md>), [Figma](<https://devfeed.tech/topics/figma.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>)

Tags: [adoption](<https://devfeed.tech/tags/adoption.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [ai-coding-tools](<https://devfeed.tech/tags/ai-coding-tools.md>), [ai-generated-research](<https://devfeed.tech/tags/ai-generated-research.md>), [ai-in-product-design](<https://devfeed.tech/tags/ai-in-product-design.md>), [ai-in-ux-design](<https://devfeed.tech/tags/ai-in-ux-design.md>), [ai-trends](<https://devfeed.tech/tags/ai-trends.md>), [ai-workflow-automation](<https://devfeed.tech/tags/ai-workflow-automation.md>), [building-with-ai](<https://devfeed.tech/tags/building-with-ai.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [design](<https://devfeed.tech/tags/design.md>), [design-engineer](<https://devfeed.tech/tags/design-engineer.md>), [design-engineering](<https://devfeed.tech/tags/design-engineering.md>), [designers](<https://devfeed.tech/tags/designers.md>), [engineer](<https://devfeed.tech/tags/engineer.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [exploring](<https://devfeed.tech/tags/exploring.md>), [figma](<https://devfeed.tech/tags/figma.md>), [product](<https://devfeed.tech/tags/product.md>), [product-design](<https://devfeed.tech/tags/product-design.md>), [product-development](<https://devfeed.tech/tags/product-development.md>), [ux](<https://devfeed.tech/tags/ux.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

The article describes two approaches to AI in product design: cautious experimentation within existing processes and integrating AI across research, prototyping, design, and implementation. It argues that tool adoption and faster cycles alone do not create value; teams should identify workflow friction and apply AI where it improves existing work. The author reports shifting from mostly Figma to roughly 90% Claude Code, enabling more direct building and iteration with fewer handoffs, while emphasizing that designers need not become full-time engineers. AI can also help create interactive prototypes for specific devices without production code. The article cautions that AI-assisted research can be generic or shallow, so designers must guide and critically evaluate results. Lasting gains depend on shared workflows, quality standards, and attention to technical rigor, security, and reliability.

### Source excerpt

Design Engineer Andrii Bondar about PUSH UX and how AI is transforming product design, UX workflows, and design engineering, from Figma to Claude Code

## Introducing Gemini 4 Hydrogen

DevFeed: [Introducing Gemini 4 Hydrogen](<https://devfeed.tech/articles/introducing-gemini-4-hydrogen-130707.md>)

Original publisher: [Read original article](<https://deepmind.google/blog/introducing-gemini-4-hydrogen/>)

Author: Koray Kavukcuoglu

Published: 2026-11-12T18:00:50Z

Content type: release

Language: en

Sources: [Google DeepMind News](<https://devfeed.tech/sources/google-deepmind-news.md>)

Topics: [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [design to code tools](<https://devfeed.tech/topics/design-to-code-tools.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-tasks](<https://devfeed.tech/tags/agentic-tasks.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-studio](<https://devfeed.tech/tags/ai-studio.md>), [airtable](<https://devfeed.tech/tags/airtable.md>), [android-studio](<https://devfeed.tech/tags/android-studio.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [api](<https://devfeed.tech/tags/api.md>), [app](<https://devfeed.tech/tags/app.md>), [argon](<https://devfeed.tech/tags/argon.md>), [business](<https://devfeed.tech/tags/business.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [daily](<https://devfeed.tech/tags/daily.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-hydrogen](<https://devfeed.tech/tags/gemini-4-hydrogen.md>), [hydrogen](<https://devfeed.tech/tags/hydrogen.md>), [none](<https://devfeed.tech/tags/none.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

Gemini 4 Hydrogen is presented as a fast, efficient model for everyday coding and agentic work, available across Google developer, enterprise, consumer, and Search products. The article says it exceeds Argon on the Artificial Analysis Intelligence Index at high thinking (51 vs. 50), costs $1.50 per million input tokens and $7.50 per million output tokens across its 1M-token context window, and offers low, medium, high, and xhigh reasoning levels. In Google Antigravity, Orchestrator can switch between Carbon and Hydrogen; on Terminal-Bench 4.0 it reached near-Carbon success while using 24% less quota and finishing 19% faster on average. Against Gemini 3.8 Flash, Hydrogen is reported to finish tasks 2.5 times faster and score 57% vs. 18.2% on Terminal-Bench 4.1. The article also describes gains in coding, multimodal knowledge work, Search, and agent safety, while noting these performance and safety figures are company-reported.

### Source excerpt

Today, we're introducing Gemini 4 Hydrogen, our daily driver for agentic workflows

## Introducing Gemini 4 Hydrogen

DevFeed: [Introducing Gemini 4 Hydrogen](<https://devfeed.tech/articles/introducing-gemini-4-hydrogen-131400.md>)

Original publisher: [Read original article](<https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/>)

Author: Koray Kavukcuoglu

Published: 2026-11-12T18:00:00Z

Content type: release

Language: en

Sources: [Gemini Models](<https://devfeed.tech/sources/gemini-models.md>)

Topics: [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [google-antigravity](<https://devfeed.tech/topics/google-antigravity.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [function calling](<https://devfeed.tech/topics/function-calling.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-studio](<https://devfeed.tech/tags/ai-studio.md>), [airtable](<https://devfeed.tech/tags/airtable.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [android](<https://devfeed.tech/tags/android.md>), [android-studio](<https://devfeed.tech/tags/android-studio.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [api](<https://devfeed.tech/tags/api.md>), [arena-ai](<https://devfeed.tech/tags/arena-ai.md>), [argon](<https://devfeed.tech/tags/argon.md>), [artificial-analysis](<https://devfeed.tech/tags/artificial-analysis.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-hydrogen](<https://devfeed.tech/tags/gemini-4-hydrogen.md>), [gemini-models](<https://devfeed.tech/tags/gemini-models.md>), [hydrogen](<https://devfeed.tech/tags/hydrogen.md>), [none](<https://devfeed.tech/tags/none.md>)

### AI overview

Gemini 4 Hydrogen is presented as a fast model for everyday coding and agentic work, with four thinking levels (low, medium, high by default, and xhigh) to vary reasoning depth, latency, and cost. Google says it exceeds Argon on the Artificial Analysis Intelligence Index at high (51 vs. 50), reaching 54 at xhigh, and is priced at $1.50 per million input tokens and $7.50 per million output tokens across its 1-million-token context window. In Antigravity, Orchestrator can switch between Carbon and Hydrogen; on Terminal-Bench 4.0 it reportedly approached Carbon's task success while using 24% less quota and finishing 19% faster. Hydrogen is also positioned as a standalone upgrade from 3.8 Flash: Google reports 2.5x faster task completion and Terminal-Bench 4.1 scores of 57% vs. 18.2%. The article describes developer, enterprise, Gemini app, and Search availability, alongside claimed safety improvements. These are the company's reported results and rollout details.

### Source excerpt

an image of carbon with the number 4 around it

## Gemini 4 Carbon is now available

DevFeed: [Gemini 4 Carbon is now available](<https://devfeed.tech/articles/gemini-4-carbon-is-now-available-128943.md>)

Original publisher: [Read original article](<https://deepmind.google/blog/gemini-4-carbon-is-now-available/>)

Author: Koray Kavukcuoglu

Published: 2026-11-10T16:03:47Z

Content type: release

Language: en

Sources: [Google DeepMind News](<https://devfeed.tech/sources/google-deepmind-news.md>)

Topics: [Frontier AI](<https://devfeed.tech/topics/frontier-ai.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [Data analysis](<https://devfeed.tech/topics/data-analysis.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>)

Tags: [0-day](<https://devfeed.tech/tags/0-day.md>), [3d](<https://devfeed.tech/tags/3d.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-mode](<https://devfeed.tech/tags/ai-mode.md>), [ai-studio](<https://devfeed.tech/tags/ai-studio.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [alphafold](<https://devfeed.tech/tags/alphafold.md>), [alphafold-3](<https://devfeed.tech/tags/alphafold-3.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [android-studio](<https://devfeed.tech/tags/android-studio.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [developers](<https://devfeed.tech/tags/developers.md>), [enterprises](<https://devfeed.tech/tags/enterprises.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4-carbon](<https://devfeed.tech/tags/gemini-4-carbon.md>), [none](<https://devfeed.tech/tags/none.md>)

### AI overview

Gemini 4 Carbon is Google's higher-reasoning model for complex, long-running work, including multi-step coding, dense multimodal document analysis, scientific research, and cybersecurity. It uses more tokens than Gemini 4 Argon for deeper exploration and verification; Google positions Argon as the better fit for most software engineering and knowledge work. Carbon is available to paying developers and enterprises through the Gemini API and Gemini for business at Argon's introductory price, and is rolling out to Google AI Ultra subscribers in Antigravity, the Gemini app, and Search AI Mode. Google reports top benchmark results in several coding and automation evaluations, and #2 on its new multimodal knowledge benchmark at over six times lower average task cost than the top model. Its preview `/swarm` feature in Antigravity coordinates agents across isolated workspaces. Access for researchers and cyber defenders is subject to program eligibility and selection. Google reports stronger safeguards than Argon in several tests, while acknowledging that resistance to sophisticated prompt injection still needs improvement.

### Source excerpt

Today, we're making Gemini 4 Carbon available to developers, enterprises, scientists, and consumers.

## Gemini 4 Carbon is now available

DevFeed: [Gemini 4 Carbon is now available](<https://devfeed.tech/articles/gemini-4-carbon-is-now-available-129307.md>)

Original publisher: [Read original article](<https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-4-carbon-now-available/>)

Author: Koray Kavukcuoglu

Published: 2026-11-10T16:00:00Z

Content type: release

Language: en

Sources: [Gemini Models](<https://devfeed.tech/sources/gemini-models.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [Automated reasoning](<https://devfeed.tech/topics/automated-reasoning.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [3D](<https://devfeed.tech/topics/3d.md>)

Tags: [0-day](<https://devfeed.tech/tags/0-day.md>), [3d](<https://devfeed.tech/tags/3d.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-mode](<https://devfeed.tech/tags/ai-mode.md>), [ai-studio](<https://devfeed.tech/tags/ai-studio.md>), [android-studio](<https://devfeed.tech/tags/android-studio.md>), [antigravity](<https://devfeed.tech/tags/antigravity.md>), [api](<https://devfeed.tech/tags/api.md>), [argon](<https://devfeed.tech/tags/argon.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [artificial-analysis](<https://devfeed.tech/tags/artificial-analysis.md>), [asset-management](<https://devfeed.tech/tags/asset-management.md>), [carbon](<https://devfeed.tech/tags/carbon.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-carbon](<https://devfeed.tech/tags/gemini-4-carbon.md>), [gemini-models](<https://devfeed.tech/tags/gemini-models.md>), [none](<https://devfeed.tech/tags/none.md>)

### AI overview

Gemini 4 Carbon is presented as Google's model for demanding, long-horizon work that benefits from deep reasoning and repeated verification. Argon remains the stated choice for most software engineering and knowledge work; Carbon uses more tokens to handle complex coding, research, and other intensive tasks. The source reports strong benchmark results across agentic workflows, multimodal knowledge work, cybersecurity, and scientific reasoning, alongside examples from financial analysis, vulnerability research, formal verification, and protein sequence search. Developers and enterprises can access Carbon through paid API offerings at Argon's introductory token prices; Google AI Ultra subscribers are receiving access in Antigravity, the Gemini app, and Search AI Mode. The `/swarm` preview in Google Antigravity coordinates agents across workspaces, with Carbon assigned to roles needing deeper reasoning. Google describes added safeguards for cyber misuse and prompt injection, while acknowledging that robustness against sophisticated injection attacks still needs improvement. Research access and the Fairwind cybersecurity program have separate eligibility and selection processes.

### Source excerpt

an illustrated carbon with several number 4's around it

## LiveWorkspace: Externalizing Visual Understanding as Persistent Shared State for Screenshot-to-Code Agents

DevFeed: [LiveWorkspace: Externalizing Visual Understanding as Persistent Shared State for Screenshot-to-Code Agents](<https://devfeed.tech/articles/liveworkspace-externalizing-visual-understanding-as-persistent-shared-state-for-screenshot-to-code-agents-127262.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.12112>)

Author: Shijun Xiao, Zonghui Yang, Xinrong Chen, Hao Liu, Wensheng Zhang, Yongqiang Tang

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Image](<https://devfeed.tech/topics/image.md>), [screenshot](<https://devfeed.tech/topics/screenshot.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [alignment](<https://devfeed.tech/tags/alignment.md>), [browser](<https://devfeed.tech/tags/browser.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [repair](<https://devfeed.tech/tags/repair.md>), [screenshot](<https://devfeed.tech/tags/screenshot.md>), [state](<https://devfeed.tech/tags/state.md>)

### AI overview

LiveWorkspace keeps visual understanding as a persistent Shared Visual State: it builds a Target representation from screenshots, recovers the Current representation from browser execution, and uses structured differences and implementation bindings to guide code changes. User edits update the Target and reuse the same alignment loop. With GPT-5.2 and matched model-call counts and stagewise budget limits, it improves end-to-end average scores by 1.8 points on Design2Code and 2.0 on ScreenBench over a control. The abstract also reports reuse across coders, better iterative repair, and 93.0% success across 100 controlled editing cases.

### Source excerpt

arXiv:2611.12112v1 Announce Type: new Abstract: Screenshot-to-Code requires coding agents to sustain visual understanding across code generation, execution, and revision. We introduce LiveWorkspace, a visual coding harness that externalizes this understanding as Shared Visual State (Shared VS), an implementation-independent representation of visual hierarchy, node attributes, and layout relations. LiveWorkspace constructs and retains \textit{Target} from screenshots and recovers \textit{Current} from browser execution in the same schema. Structured Diff and implementation bindings guide code modifications; user edits update \textit{Target} and reuse the alignment loop. Using GPT-5.2 for both methods, LiveWorkspace improves end-to-end Avg by 1.8 points on Design2Code and 2.0 on ScreenBench over a control with matched model-call counts and stagewise budget limits. Further experiments demonstrate reuse of constructed Shared VS across coders and improvements in iterative repair. LiveWorkspace also achieves 93.0\% edit success across 100 controlled editing cases. These findings support treating visual understanding as a persistent shared working state throughout code generation, execution, and modification.

## AnimWeb-Bench: Benchmarking Animated Webpage Code Generation from Videos

DevFeed: [AnimWeb-Bench: Benchmarking Animated Webpage Code Generation from Videos](<https://devfeed.tech/articles/animweb-bench-benchmarking-animated-webpage-code-generation-from-videos-124037.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09769>)

Author: Zhongyi Zhang, Jingyu Xiao, Shuqing Li, Michael R. Lyu

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [web animation](<https://devfeed.tech/topics/web-animation.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [screenshot-testing](<https://devfeed.tech/topics/screenshot-testing.md>), [Image](<https://devfeed.tech/topics/image.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [appearance](<https://devfeed.tech/tags/appearance.md>), [assets](<https://devfeed.tech/tags/assets.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [code-generation](<https://devfeed.tech/tags/code-generation.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [css-animation](<https://devfeed.tech/tags/css-animation.md>), [dataset](<https://devfeed.tech/tags/dataset.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [feedback](<https://devfeed.tech/tags/feedback.md>), [multimodal](<https://devfeed.tech/tags/multimodal.md>), [size](<https://devfeed.tech/tags/size.md>), [state](<https://devfeed.tech/tags/state.md>), [structure](<https://devfeed.tech/tags/structure.md>), [text](<https://devfeed.tech/tags/text.md>), [ui-components](<https://devfeed.tech/tags/ui-components.md>), [velocity](<https://devfeed.tech/tags/velocity.md>), [video](<https://devfeed.tech/tags/video.md>), [videos](<https://devfeed.tech/tags/videos.md>)

### AI overview

AnimWeb-Bench evaluates how well multimodal language models and coding agents can recreate animated webpages from videos. Its 124 real-world pages cover seven application domains and 33 animation types; 91.9% combine multiple types. The benchmark pairs each page's reference video with its original static assets and scores both static appearance on aligned keyframes and animation fidelity across frames, including component position, size, velocity, and appearance. Evaluation of 14 models and three coding agents found animation harder to reproduce than static appearance. For coding agents, explicit frame inspection and render feedback improved results, while rapid continuous changes proved harder to recreate than discrete state transitions.

### Source excerpt

arXiv:2611.09769v1 Announce Type: new Abstract: Animation is pervasive on the Web, the CSS animation property alone appears on over three-quarters of webpages. Yet existing webpage code generation benchmarks target static screenshots, user-triggered interactions, or isolated motion graphics, leaving the ability of multimodal large language models (MLLMs) and coding agents to reconstruct complete animated webpages largely unexplored. To fill this gap, we introduce AnimWeb-Bench, the first benchmark for animated webpage code generation from videos. It comprises 124 real-world webpages spanning 7 application domains and 33 animation types, with 91.9% of pages combining multiple types, each paired with a reference video and the static assets of the original webpage. We further propose a human-aligned, two-dimensional evaluation protocol: Static Appearance Fidelity measures structure, text, color, and visual similarity on aligned keyframes, while Animation Fidelity tracks UI components across frames and compares their position, size, velocity, and appearance with those in the reference video. Evaluating 14 MLLMs and three coding agents reveals: (1) reproducing webpage animations is substantially more difficult than reproducing static appearance; (2) explicit frame inspection and render feedback improve the reconstruction quality of coding agents; and (3) rapid, continuous changes are harder to reproduce than discrete state transitions. Our code and dataset are available at https://starry1001.github.io/AnimWeb-Bench-website/ .

## 18 Agent Skills Design Frontends, Brands and Themes With Real Taste

DevFeed: [18 Agent Skills Design Frontends, Brands and Themes With Real Taste](<https://devfeed.tech/articles/18-agent-skills-design-frontends-brands-and-themes-with-real-taste-121755.md>)

Original publisher: [Read original article](<https://hackernoon.com/18-agent-skills-design-frontends-brands-and-themes-with-real-taste?source=rss>)

Author: Iconography Technology

Published: 2026-11-06T18:27:29Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [design to code tools](<https://devfeed.tech/topics/design-to-code-tools.md>), [Figma](<https://devfeed.tech/topics/figma.md>)

Tags: [accessibility](<https://devfeed.tech/tags/accessibility.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-design-skills](<https://devfeed.tech/tags/agent-design-skills.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [art](<https://devfeed.tech/tags/art.md>), [audits](<https://devfeed.tech/tags/audits.md>), [brand](<https://devfeed.tech/tags/brand.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cli](<https://devfeed.tech/tags/cli.md>), [code](<https://devfeed.tech/tags/code.md>), [codex](<https://devfeed.tech/tags/codex.md>), [design](<https://devfeed.tech/tags/design.md>), [design-skills](<https://devfeed.tech/tags/design-skills.md>), [figma](<https://devfeed.tech/tags/figma.md>), [frontend-design](<https://devfeed.tech/tags/frontend-design.md>), [frontend-skills](<https://devfeed.tech/tags/frontend-skills.md>), [skills](<https://devfeed.tech/tags/skills.md>), [skills-with-real-taste](<https://devfeed.tech/tags/skills-with-real-taste.md>), [themes](<https://devfeed.tech/tags/themes.md>), [translation](<https://devfeed.tech/tags/translation.md>), [ui-design](<https://devfeed.tech/tags/ui-design.md>)

### AI overview

An 18-skill Design & UI plugin packages frontend design, brand-consistent themes, Figma-to-code translation, accessibility audits, SwiftUI patterns and generative art. Seven skills are from Anthropic, nine from Tech Leads Club, and Matt Pocock and Thomas Ricouard contribute one each. They follow the open Agent Skills standard and are described as usable in Claude Code, Codex CLI and 30+ other tools. Install through Cuttlefish.MD with its marketplace commands, or copy the repository's skills folder into a compatible agent's skills directory; the two frontend-design skills use different folder names and can coexist. Each skill retains its license and an ATTRIBUTION.md naming its author and source commit.

### Source excerpt

Eighteen open-licensed agent skills give an AI agent design judgment: distinctive frontends, brand-consistent themes, Figma-to-code translation & accessibility.

## WebStorm 2026.3: New Design-Code-Production Workflow, JetBrains Air in WebStorm, and More

DevFeed: [WebStorm 2026.3: New Design-Code-Production Workflow, JetBrains Air in WebStorm, and More](<https://devfeed.tech/articles/webstorm-2026-3-new-design-code-production-workflow-jetbrains-air-in-webstorm-and-more-119346.md>)

Original publisher: [Read original article](<https://blog.jetbrains.com/webstorm/2026/11/webstorm-2026-3/>)

Author: Valeriya Masyachenko

Published: 2026-11-05T13:27:56Z

Content type: release

Language: en

Sources: [JetBrains](<https://devfeed.tech/sources/the-jetbrains-blog.md>)

Topics: [webstorm](<https://devfeed.tech/topics/webstorm.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [design to code tools](<https://devfeed.tech/topics/design-to-code-tools.md>), [Storybook](<https://devfeed.tech/topics/storybook.md>), [Test automation](<https://devfeed.tech/topics/test-automation.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [2026-3](<https://devfeed.tech/tags/2026-3.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [air](<https://devfeed.tech/tags/air.md>), [browser](<https://devfeed.tech/tags/browser.md>), [building](<https://devfeed.tech/tags/building.md>), [coding](<https://devfeed.tech/tags/coding.md>), [design](<https://devfeed.tech/tags/design.md>), [figma](<https://devfeed.tech/tags/figma.md>), [jetbrains](<https://devfeed.tech/tags/jetbrains.md>), [jetbrains-air](<https://devfeed.tech/tags/jetbrains-air.md>), [news](<https://devfeed.tech/tags/news.md>), [production](<https://devfeed.tech/tags/production.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [release](<https://devfeed.tech/tags/release.md>), [releases](<https://devfeed.tech/tags/releases.md>), [story](<https://devfeed.tech/tags/story.md>), [storybook](<https://devfeed.tech/tags/storybook.md>), [webstorm](<https://devfeed.tech/tags/webstorm.md>), [webstorm-2026-3](<https://devfeed.tech/tags/webstorm-2026-3.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

WebStorm 2026.3 brings AI-assisted frontend work into an IDE workflow linking design, components, and browser verification. Figma Connect exposes selected layers and their CSS values, colors, and design tokens to agents; Storybook Connect lets developers browse stories and uses AI-assisted tools to generate missing ones (as a separate plugin requiring Storybook 10 or later); Chrome DevTools Connect lets agents inspect and interact with a real browser, including DOM, logs, and network requests, and confirm fixes. JetBrains Air runs JetBrains and third-party ACP-compatible agents, supports parallel sessions and in-IDE review with line-specific feedback, and works with existing provider subscriptions, API keys, and custom base URLs without requiring a JetBrains AI subscription. Junie Lite provides a free agent configuration requiring a JetBrains Account. The release also adds stable TypeScript 7 support for React and Angular without a project migration, plus fixes and accessibility sound cues. The excerpt notes that Air migration does not carry over chat mode history.

### Source excerpt

WebStorm 2026.3 is now available! Building a UI feature with an AI agent often involves more switching between tools than actual coding. You copy values out of Figma, hunt for the right story in Storybook, write the prompt, wait for the agent, and then check the result in the browser and find yourself starting the [...]

## Merge builds product and business tools with OpenAI technology

DevFeed: [Merge builds product and business tools with OpenAI technology](<https://devfeed.tech/articles/merge-builds-product-and-business-tools-with-openai-technology-120967.md>)

Original publisher: [Read original article](<https://openai.com/index/merge-builds-with-openai>)

Published: 2026-11-05T08:00:00Z

Content type: article

Language: en

Sources: [OpenAI News](<https://devfeed.tech/sources/openai-news.md>)

Topics: [OpenAI](<https://devfeed.tech/topics/openai.md>), [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>), [gpt-6-astra](<https://devfeed.tech/topics/gpt-6-astra.md>), [codex](<https://devfeed.tech/topics/codex.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [AI tools for developers](<https://devfeed.tech/topics/ai-tools-for-developers.md>), [AI-enhanced product development](<https://devfeed.tech/topics/ai-enhanced-product-development.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [also](<https://devfeed.tech/tags/also.md>), [astra](<https://devfeed.tech/tags/astra.md>), [builds](<https://devfeed.tech/tags/builds.md>), [business](<https://devfeed.tech/tags/business.md>), [business-tools](<https://devfeed.tech/tags/business-tools.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [code](<https://devfeed.tech/tags/code.md>), [codex](<https://devfeed.tech/tags/codex.md>), [executive](<https://devfeed.tech/tags/executive.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [gpt-6](<https://devfeed.tech/tags/gpt-6.md>), [gpt-6-astra](<https://devfeed.tech/tags/gpt-6-astra.md>), [marketing](<https://devfeed.tech/tags/marketing.md>), [merge](<https://devfeed.tech/tags/merge.md>), [openai](<https://devfeed.tech/tags/openai.md>), [product](<https://devfeed.tech/tags/product.md>), [technology](<https://devfeed.tech/tags/technology.md>), [tools](<https://devfeed.tech/tags/tools.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

Merge uses GPT-6 Astra, ChatGPT, and Codex across product development and business operations. Codex reviewed code for a new Merge for Workforce setup interface; engineers validated and shipped changes. GPT-6 Astra supports testing and marketing, while a dinner-planning bot connects to Salesforce, Gong, Google Sheets, Gmail, the CRM, and Apollo to find and track guests, draft outreach, and propose seating. Ding reviews drafts and curates invitees using relationship context the bot lacks; employees still host and handle logistics. Merge reported that guest-list, outreach, and tracker work fell from dozens of company hours to about 30 minutes per event over the preceding three months. Sales workflows prepare deal approvals, forecast updates, and renewal-call follow-ups for human review. Merge says its connector tool calls succeed 99.9% of the time, compared with around 60% for public MCP servers. These are company-reported results and comparisons.

### Source excerpt

Merge uses GPT-6 Astra, ChatGPT, and Codex to review product code and support marketing. Its teams also use AI to plan executive dinners and prepare sales updates.

## Healthcare can't govern the AI tools it hasn't found yet

DevFeed: [Healthcare can't govern the AI tools it hasn't found yet](<https://devfeed.tech/articles/healthcare-can-t-govern-the-ai-tools-it-hasn-t-found-yet-118027.md>)

Original publisher: [Read original article](<https://www.helpnetsecurity.com/2026/11/05/healthcare-ai-governance-patient-data/>)

Author: Anamarija Pogorelec

Published: 2026-11-05T06:11:25Z

Content type: news

Language: en

Sources: [Help Net Security](<https://devfeed.tech/sources/help-net-security.md>)

Topics: [shadow AI](<https://devfeed.tech/topics/shadow-ai.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-coding-assistants](<https://devfeed.tech/tags/ai-coding-assistants.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [can](<https://devfeed.tech/tags/can.md>), [code](<https://devfeed.tech/tags/code.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-assistants](<https://devfeed.tech/tags/coding-assistants.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [covers](<https://devfeed.tech/tags/covers.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [data](<https://devfeed.tech/tags/data.md>), [found](<https://devfeed.tech/tags/found.md>), [handling](<https://devfeed.tech/tags/handling.md>), [healthcare](<https://devfeed.tech/tags/healthcare.md>), [here](<https://devfeed.tech/tags/here.md>), [here-s](<https://devfeed.tech/tags/here-s.md>), [heres](<https://devfeed.tech/tags/heres.md>), [it](<https://devfeed.tech/tags/it.md>), [news](<https://devfeed.tech/tags/news.md>), [paubox](<https://devfeed.tech/tags/paubox.md>), [report](<https://devfeed.tech/tags/report.md>), [survey](<https://devfeed.tech/tags/survey.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

Healthcare leaders report both routine review of AI-written code that handles patient data and discovery of AI-built tools outside IT or security's view. These findings can coexist: code review covers only submitted code, and vendor agreement checks depend on someone reporting the connection. The survey did not establish that reviewed code caused problems. Respondents also report real patient information reaching AI coding assistants during development, while only half have a written policy. Paubox recommends synthetic data for testing and enforcing that rule in the tools, since training alone has not kept real data out. More than half say AI-generated code has contributed to hardcoded credentials, and about half report patient-data exposure or insecure storage. The article also cites the need for HIPAA risk analysis to identify threats and vulnerabilities to ePHI.

### Source excerpt

Nearly nine in ten healthcare leaders say security or compliance staff always or usually review AI-written code that touches patient data before it goes live, and seven in ten have still found an AI-built tool handling that data without IT or security knowing, according to Paubox. Source: Paubox These are the scripts, automations, and integrations staff put together with AI coding assistants. Here's the catch: a code review only covers what someone submits, and a ... More -> The post Healthcare can't govern the AI tools it hasn't found yet appeared first on Help Net Security.

## RefCraft: Benchmarking Visual-Reference-Conditioned Agentic Generation through Web Development

DevFeed: [RefCraft: Benchmarking Visual-Reference-Conditioned Agentic Generation through Web Development](<https://devfeed.tech/articles/refcraft-benchmarking-visual-reference-conditioned-agentic-generation-through-web-development-118279.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.26826>)

Author: Yuchi Wang, Rongyao Fang, Weihao Yu, Xilin Wei, Tiancheng Gu, Dingkang Yang, Hang Zhang, Dayiheng Liu, Hongsheng Li, Shuai Bai

Published: 2026-11-05T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Front end](<https://devfeed.tech/topics/frontend.md>), [Website](<https://devfeed.tech/topics/website.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [artifacts](<https://devfeed.tech/tags/artifacts.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarking](<https://devfeed.tech/tags/benchmarking.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [coding](<https://devfeed.tech/tags/coding.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-cv](<https://devfeed.tech/tags/cs-cv.md>), [developing](<https://devfeed.tech/tags/developing.md>), [development](<https://devfeed.tech/tags/development.md>), [examples](<https://devfeed.tech/tags/examples.md>), [generation](<https://devfeed.tech/tags/generation.md>), [instructions](<https://devfeed.tech/tags/instructions.md>), [llms](<https://devfeed.tech/tags/llms.md>), [reference](<https://devfeed.tech/tags/reference.md>), [web](<https://devfeed.tech/tags/web.md>), [web-development](<https://devfeed.tech/tags/web-development.md>)

### AI overview

RefCraft evaluates whether agents can build webpages from natural-language instructions and screenshots of one to five reference sites, a workflow the authors say existing benchmarks often overlook. Its 300 tasks require agents to interpret references selectively, render pages, inspect them visually, and refine their work. Outputs are scored using independently verifiable keypoints alongside programmatic and vision-language-model judges. Across nine frontier models, the top system scores 52.12/100, indicating substantial remaining difficulty in this setting.

### Source excerpt

arXiv:2610.26826v2 Announce Type: replace-cross Abstract: Beyond basic tool use and coding skills, effectively incorporating visual references into agentic generation is equally essential for applying AI agents to real-world productivity tasks. We study this crucial capability through webpage development, a practical and readily evaluable setting in which existing benchmarks remain largely idealized: they typically focus on reconstructing visual targets or generating webpages from textual instructions alone, overlooking the more common workflow of developing from visual examples. Specifically, we introduce RefCraft, a benchmark comprising 300 realistic multimodal webpage-development tasks that combine natural-language instructions with screenshots from one to five reference webpages. Agents must selectively interpret and utilize these references while rendering, visually inspecting, and iteratively refining their outputs. We evaluate the resulting open-ended artifacts using independently verifiable keypoints and complementary programmatic and VLM judges. Across nine frontier (M)LLMs, the strongest system achieves an overall score of only 52.12 out of 100, revealing that visual-reference-conditioned agentic generation remains a substantial challenge for current models in practical webpage-development settings.

[Next page](<https://devfeed.tech/topics/ai-in-frontend-development.md?cursor=WyIyMDI2LTExLTA1VDA1OjAwOjAwKzAwOjAwIiwgIjU2MDJlZWRkLWVkYWUtNDM0NC1iZGYzLTZiNjQyYmM0MDY3OSJd>)