Google Cloud announced the preview of Looker Data Apps on October 12, 2026, introducing AI-generated web applications hosted natively within Looker.
What Looker Data Apps Do
Google Cloud described Looker Data Apps as bespoke, interactive web applications generated by an AI agent and hosted natively within Looker. According to group product manager Ani Jain and product manager Sharon Zhang, these apps go beyond standard grid tiles to provide pixel-perfect layouts, enable parameter inputs, and connect data analysis to business execution tasks like updating source records or dispatching events to tools such as Salesforce and Jira.
Users can build interfaces using AI developer tools like Claude Code or Antigravity CLI, grounded directly by Looker’s semantic layer.
Enterprise Scale and Governance
Google Cloud stated that Looker Data Apps are designed for demanding, governed enterprises by inheriting existing semantic models, row-level security, and access controls. The company noted that calculations stay consistent across the enterprise and query inspection lets teams audit generated SQL.
The company reported that the apps are zero-code by default with no runtime token costs. LLM tokens are only consumed when designing or generating the app, and subsequent end-user interactions run on native Looker APIs and models.
Key facts and where they come from
- Google Cloud announced Looker Data Apps in preview on October 12, 2026.
Today, to bridge this gap, we are announcing Looker Data Apps (in preview)
- A data app is a bespoke, interactive web application generated by an AI agent and hosted natively within Looker.
A data app is a bespoke, interactive web application generated by an AI agent and hosted natively within Looker.
- LLM tokens are only consumed when designing or generating the app, with no runtime token costs for end-user interactions.
No runtime token costs. LLM tokens are only consumed when you’re designing or generating the app.
