Skip to main content
The assistant keeps two useful kinds of context visible while you work in the current chat:
  • Selection context: chips identify the active slide and selected canvas element.
  • Conversation context: recent prompts and assistant results remain in the panel above the composer.
The close-up follows one request from its selected scope through the assistant response. It does not imply permanent memory across new chats, reopened presentations, browsers, or deployments.

​
Read the visible context

Before sending a follow-up prompt:
  1. Check the slide and element chips.
  2. Read the latest prompt and assistant result.
  3. Restate critical facts, source requirements, and anything that must not change.
  4. Review the result on the canvas.

Current-chat history and selected scope in the assistant panel

AI assistant panel showing recent prompts, assistant responses, Slide 1, and a selected component chip

​
Start with a clean context

Select New chat when you are moving to an unrelated task or do not want the next request to build on the visible conversation. Then select the intended slide or element again and confirm the new scope chips before prompting.