Event Moment: Acumant’s Senthamil Selvan Describes Copilot Architecture

In this moment, excerpted from the session “The Fusion of Azure AI and Microsoft’s Technological Ecosystem,” Senthamil Selvan, Power Platform Consultant, Acumant, reviews the architecture of Microsoft Copilot, focused on prompting, grounding, and output.

AI Agent & Copilot Summit is an AI-first event to define opportunities, impact, and outcomes with Microsoft Copilot and agents. Building on its 2025 success, the 2026 event takes place March 17-19 in San Diego. Get more details.

Key Takeaways

• Copilot in Microsoft platforms: Selvan explains that users must understand a specific Copilot category and its architecture, including how Microsoft Copilot differs from ChatGPT and the advantages of using it within the Microsoft platform.
• Prompting and grounding: When a prompt or keyword is entered, a processing engine grounds the query in Microsoft context, and sends it to an Azure-hosted LLM for processing.
• Output: Copilot delivers the final output tailored by leveraging Microsoft Graph for contextual relevance.

---