Microsoft Copilot (Microsoft 365): Now smarter with visuals: Declarative Agents leverage embedded images for richer, more accurate answers

Originally posted by Microsoft Nov 21, 2025 Uncategorized 0 Comments

Declarative Agents have been enhanced to interpret and ground responses using images embedded in files such as Word documents (.docx), PowerPoint presentations (.pptx), and PDFs. This capability allows the agent to extract insights from visual elements like charts, diagrams, and screenshots, ensuring that answers are not only text-based but also informed by graphical context. By combining textual and visual understanding, Declarative Agents deliver more comprehensive and contextually accurate responses for complex queries.

Product
Release phase General Availability
Release date December CY2025
Platform Desktop
Cloud Instance Worldwide (Standard Multi-Tenant)
Created 2025-11-21
Roadmap ID 531758
Roadmap Link https://www.microsoft.com/microsoft-365/roadmap?id=531758

Comments are closed.

Joao Ferreira

I've been working with Microsoft Technologies over the last ten years, mainly focused on creating collaboration and productivity solutions that drive the adoption of Microsoft Modern Workplace.

%d bloggers like this: