The foundational model used in Microsoft Copilot is part of OpenAI's GPT family (such as GPT-4 or GPT-4o Mini), securely hosted and managed by Microsoft within an enterprise-compliant environment.
The model powers Copilot's natural language understanding and generation capabilities, enabling it to interpret user prompts, retrieve relevant organizational and public information, and generate contextually appropriate responses, summaries, or recommendations within Microsoft 365 applications.
In essence, the model functions as the AI reasoning and language engine behind Copilot, transforming user intent expressed in natural language into actionable insights or content, while operating entirely within Microsoft's security, compliance, and privacy boundaries.