Gemini 3.5 Flash Integrates Built-in Computer Use for Enhanced Agent Development

Jun 24, 2026

AI Summary

Gemini 3.5 Flash now includes built-in computer use capabilities, allowing developers to create agents that can operate across various platforms. This integration enhances performance for tasks such as software testing and knowledge work, while also incorporating safety measures against prompt injection risks.

Gemini 3.5 Flash has integrated computer use as a built-in tool, improving agentic tasks performance.
Previously, computer use was only available in the standalone Gemini 2.5 model.
The new capabilities allow for the development of custom agents that can function across browser, mobile, and desktop environments.
Gemini 3.5 Flash excels in function calling and utilizing built-in tools like Search and Maps grounding.
Developers can access these features through the Gemini API and Gemini Enterprise Agent Platform.
The system can analyze its own app and audit documentation for accessibility issues.
To address prompt injection risks, targeted adversarial training is employed, along with optional enterprise safeguard systems.
A defense-in-depth approach is recommended, combining these features with secure sandboxing and strict access controls.
Customers are already reporting value from using the computer use capabilities in Gemini 3.5 Flash.

geminilanguage modelsai researchcomputer useflash

Gemini 3.5 Flash Integrates Built-in Computer Use for Enhanced Agent Development

Related Stories

OpenAI says GPT 5.6 is the ‘preferred model’ for Microsoft Copilot amid breakup chatter

OpenAI introduces GPT-5.6 models with enhanced efficiency and cybersecurity features

OpenAI Releases GPT-5.6 Model with Enhanced Capabilities

OpenAI launches GPT-5.6 Sol, improving token efficiency for coding tasks