The GitHub Copilot SDK turns the Copilot CLI into a cross-platform agent host with Model Context Protocol support.

Gemini 3 Flash adds active vision with Python code execution, lifting accuracy by 5 to 10%, so you can trust verified results.

The new capabilities combine visual reasoning with Python code to improve image analysis and enable active investigations.

Google DeepMind has added Agentic Vision to Gemini 3 Flash, enabling active image exploration through Python code execution with 5-10% quality improvements.