Lifestyle
Google Cloud Launches Looker Data Apps Preview: Ask AI in Plain Language to Build Internal Data Tools
Google Cloud has announced Data Apps for its business intelligence tool Looker, now in preview. Google says users describe what they need in everyday language and an AI agent builds an interactive app that reuses the data definitions and permissions a company already has in Looker. This article summarizes Google's claims and what they mean for Looker customers.
About 5 min read
What happened
Google Cloud announced Looker Data Apps on its official blog. The feature is currently in preview, meaning a trial version that is not yet generally available. Looker is Google Cloud's business intelligence tool, which companies use to turn data into reports and dashboards. According to Google Cloud, users describe what they need in natural language (the way people normally speak), and an AI agent builds a production-ready application that runs inside Looker.
Google Cloud notes that tools written by an LLM (large language model, an AI that can generate text and code) are just prototypes that never launch if they lack governed data (data whose definitions and permissions are managed centrally by the company), row-level security (limiting which rows of data a user can see based on identity), an infrastructure owner, or a clear path through security review. Looker Data Apps is presented as addressing this gap.
What is a data app, and how does it differ from a dashboard?
Google Cloud defines a data app as a custom interactive web application generated by an AI agent and run directly inside Looker. According to the company, a dashboard gives top-down visibility so people can see the overall numbers, while a data app is a system designed around a specific operational workflow so people can take action directly.
| Aspect | Dashboard | Data app |
|---|---|---|
| Main purpose | Aggregated visibility and passive reporting | Active execution; users can change parameters and trigger follow-on business tasks |
| Layout and components | Standardized chart library | Custom web components and specialized interactions |
| Data governance | Based on the Looker semantic layer | Also governed centrally through the LookML semantic layer |
The "semantic layer" in the table is a set of configurations that defines uniformly how each metric is calculated, so different reports produce consistent numbers. Google calls Looker's semantic layer the LookML semantic layer. Google Cloud says data apps do not replace dashboards but widen what can be built on top of existing dashboards and the semantic layer.
What Google says it can do
- According to Google Cloud, users can enter parameters, test scenarios, run live simulations and update underlying records.
- Google says a data app can connect data analysis to business execution tasks, such as updating source records or sending events to tools like Salesforce and Jira.
- Google says each app directly inherits the existing semantic model, row-level security and access controls, and that built-in query inspection lets teams check the AI-generated SQL (database query language) line by line.
- Google says no coding is required by default: React apps (React is a technology for building web interfaces) generated by the AI agent can be deployed directly in Looker, or built with tools such as Claude Code or Antigravity CLI and then deployed.
- Google says LLM tokens (the unit AI models use to measure usage) are consumed only when designing or generating the app. Later user interactions go through Looker's native APIs and models, so the marginal cost is the same whether it serves 50 or 5,000 people.
- Google says data apps can be deployed to external portals using the same process used to embed a dashboard, with no new data pipeline, custom application code or second permission model.
What this means for companies and users
For companies that use Looker, Google's claim is that people without an engineering background can build custom tools in natural language, without setting up a separate permission system or a different way of calculating metrics. If true, the barrier to moving internal analytics tools from prototype to production could be lower. However, it is only a preview for now, and details still need to be confirmed by official documentation and real-world use.
Frequently asked questions
Is Looker Data Apps generally available now?
Google Cloud says Looker Data Apps is currently in preview and is not yet a generally available release.
Will data apps replace dashboards?
According to Google Cloud, no. They are positioned as extending what existing dashboards and the semantic layer can do, leaning toward actively executing tasks.
How is data security handled in these apps?
Google says apps directly inherit the existing semantic model, row-level security and access controls, and the generated SQL can be inspected line by line. This is the vendor's own claim, and real-world results remain for users to evaluate.
Do AI costs rise as more people use an app?
Google says LLM tokens are consumed only during design or generation, and end-user interactions go through Looker's native APIs and models, so the marginal cost is the same whether it serves 50 or 5,000 people.
Browse the latest news in this topic
Lifestyle
Intel Unveils Data Center AI Inference GPU "D-series" Specs and New Xeon Rack Designs, Targeting Enterprise AI Deployment
At the OCP Global Summit on October 12, 2026, Intel disclosed specifications for the Intel GPU D-series (formerly code-named Crescent Island) and new Xeon rack designs. Aimed at data centers and enterprises, Intel says they make AI inference easier and cheaper to deploy; all specs are Intel's claims.
Lifestyle
Meta Launches Muse Wonder and Muse Wonder Full: AI Models Built to Complete Real Tasks for Users
On October 12, 2026, Meta announced Muse Wonder and Muse Wonder Full, which it calls its most capable models yet, built for "agentic tasks" in which AI completes real work for users step by step. Developers can use Muse Wonder now, Muse Wonder Full is open to Muse Code subscribers, and Muse Wonder will reach Muse subscribers first. Meta also outlined its privacy and safety training.
Lifestyle
Google Cloud Previews TimesFM 3.0 in BigQuery: Multivariate Time-Series Forecasting in SQL
Google Cloud has announced a preview of the TimesFM 3.0 forecasting model in its BigQuery analytics service, letting data teams forecast multiple targets in one SQL query and factor in external drivers such as weather and holidays. This article summarizes what is new versus earlier versions.
Lifestyle
NVIDIA Opens Its Vera Rubin Rack Design at OCP and Unveils Open AI Factory Standards with Partners
At the OCP Global Summit, NVIDIA announced it is opening its next-generation Vera Rubin server rack design to the industry, and shared progress on networking, power and software with partners including Meta, Google and Cisco. This is data-center-level news that mainly affects equipment makers and data center operators; the content comes from NVIDIA's official blog.