Declarative Agents can now interpret embedded images in Word, PowerPoint, and PDF files to ground their responses.
Getting answers from documents where the important information is in charts, diagrams, or screenshots, not just text
You're building a Declarative Agent that needs to reason about visual content in enterprise docs, not just extract text
Teams using Copilot Studio to build custom agents. Requires Declarative Agent setup.
Pick a topic and leave with something you created.
Get new module drops and weekly AI strategy.