product updateGoogle

Google Antigravity adds Knowledge Work interface for non-coding tasks, with the same agent underneath

TL;DR

Google is rolling out a Knowledge Work user experience in Antigravity, designed for research, data analysis, documents and presentations. The underlying agent is unchanged; the interface hides developer controls and uses plain-language permission prompts. Google says tens of thousands of Googlers outside software engineering use Antigravity weekly.

3 min read
0

Google is rolling out a "Knowledge Work" interface in Antigravity, adding a second experience alongside the existing Software Engineering interface, according to 9to5Google. The underlying Antigravity agent is unchanged.

Why Google built it

Antigravity launched with a coding focus. Google says it has seen people, including employees internally, use it for "far more than code." Alongside software engineering, more daily sessions now center on deep research, data analysis, drafting documents and presentations, prototyping designs, and automating everyday workflows.

Google states that "tens of thousands of Googlers outside software engineering (across sales, finance, legal, product, design, research, marketing, and operations) now rely on Antigravity every week alongside engineers to get their work done." That is Google's own claim about internal usage.

What stays the same

The agent keeps "full access to frontier models, local files, plugins, skills, rules, custom agents, and MCP servers." Only the interface changes.

What changes in the UI

With Knowledge Work enabled:

  • Projects and folders: The agent runs directly in the project's folders, with no worktree or Git branch prompts. GitHub and Open in IDE controls are hidden. Forks stay in the current folder ("Fork conversation in this folder"). The Software Engineering view instead offers Local or New worktree mode on Git repos, Git branch pickers, GitHub controls and Open in IDE.
  • Conversation and approvals: A live progress line shows while the agent works and clears once the response finishes, keeping focus on replies and artifacts. Permission prompts present plain-language summaries. The Software Engineering view keeps expandable "Worked for" tool groups, inline code diffs, line counts, subagent cards and raw command-rule editors in permission prompts.
  • Overview panel: It stays hidden until the conversation produces output. It omits Review, Terminal and Customize Sections, labels the Files sidebar tree "Folders," and focuses on Documents, Artifacts, Links, Uploads and Background Tasks.
  • Customizations (Installed tab): Only installed Plugins are listed. Installed skills, rules, custom agents and MCP tools remain active in the background.
  • Settings: Advanced permission rules and developer subsections (Terminal, Workspaces, Labs) move behind Advanced Settings in Settings > General and project settings. The Appearance > Conversation Steps toggle and code syntax preview are hidden.

How to enable it

Go to Settings > General > Interface Layout. A new onboarding flow appears on first launch. The rollout follows what 9to5Google describes as last week's big Antigravity update.

Pricing, availability by plan or region, and model details were not part of the announcement coverage.

What this means

The change is a presentation layer, not a new model or agent. Because the agent and its access to files, plugins, skills, rules, custom agents and MCP servers are the same, existing configurations continue to work in the new view; they are simply hidden from the Installed tab or settings. For non-engineers, the practical differences are removal of Git and worktree concepts, plain-language permission prompts, and an output-focused Overview. For engineers, the Software Engineering interface is retained, so the two views can be switched through the Interface Layout setting. Google's usage figure comes from internal employees and is the company's own claim, not an independent measurement.

Related Articles

product update

Google Gemini adds 'Memory summary' to view, edit and delete what the app remembers about you

Google is rolling out a "Memory summary" in the Gemini app that lists what Gemini Apps understands about a user and lets them edit or delete it. Per 9to5Google, it is available to Google AI subscribers in US English with Keep Activity and Memory enabled.

product update

Qianwen Office 2.0 adds "Collaboration" so teams and Agents work in one shared space

Qianwen Office (千问办公) released version 2.0 on November 9, its largest upgrade in the three months since launch. The headline feature, "Collaboration," puts multiple people and digital employees in one shared workspace, and all new features are live in the client.

product update

Google Antigravity 2.29 adds cloud Remote Agents for Google AI Pro and Ultra subscribers

Google's Antigravity 2.29 adds Remote Agents that run in isolated cloud virtual machines for Google AI Pro and Ultra subscribers. The update also brings a Gemini Live-powered Voice Mode, a redesigned conversation page, and changes to Automations and the built-in browser.

product update

Google AI Studio adds Maps Platform app building, with 100 free demo calls per API daily

Google announced on November 9, 2026 that developers can build location-aware apps with Google Maps Platform inside Google AI Studio. Setup is automated, previews are live, and a free demo allowance covers 100 calls per API each day.

Comments

Loading...