Unverified50% confidenceReleaseExact time
Google introduced the environment: remote field in the Gemini API; when a developer sends a request, the backend automatically starts a cloud sandbox in which the agent can run code, create and write files, install dependencies, install custom tools, and call external APIs.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedGoogle AI Studio's 'New App' feature allows users to generate runnable web application prototypes through natural language descriptions, with the underlying Gemini model generating HTML/CSS/JavaScript code and executing it in a sandbox77% similarUnverifiedBy open-sourcing the orchestrator, Google captures developer mindshare and has the opportunity to drive adoption of Gemini models and Google Cloud services.72% similarUnverifiedGoogle has long deployed a Function Calling interface in Gemini, laying the underlying foundation for agent applications such as Spark.71% similarUnverifiedGoogle built the Agents API on top of the sandbox, with the core idea of defining an agent's configuration (underlying model, instructions, environment) as a reusable, shareable entity, where the environment can be raw (with source files) or an existing agent or environment.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1036081API
curl https://kongchang.com/api/v1/knowledge/claims/1036081MCP
get_claim(id=1036081)