Replies: 2 comments
-
|
Yes, I also think this task would be the top priority if I were to take on the next project. I'll try to schedule it soon. |
Beta Was this translation helpful? Give feedback.
0 replies
-
|
@jezweb @cgoinglove I have a project where this is needed, happy to help contribute. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
Summary
Add a side-panel preview for AI-generated content, similar to Claude Artifacts or Google Gemini's canvas view.
Current State
All content (text, tool outputs, visualizations) renders inline within the chat message flow. This works well for conversational interfaces but limits the ability to view and interact with generated artifacts.
Desired Behavior
Implement a split-view layout:
When the AI generates an artifact (code, document, visualization, etc.), it appears in the preview panel where users can:
Use Cases
Content Creation:
Code Generation:
Data Visualization:
Analysis & Reports:
UI Layout Mockup
Technical Implementation Suggestions
Layout Changes:
/src/app/(chat)/layout.tsxto support three-column layout<ArtifactPanel>componentMessage System:
artifacttool-uipart typeComponent Structure:
Supported Artifact Types
Phase 1 (MVP):
Phase 2 (Future):
Acceptance Criteria
Inspiration / References
Notes
This is a more significant architectural change than Enable Agents to Generate Downloadable Files but would greatly enhance the user experience for content generation, code creation, and document editing workflows.
The existing inline visualization system (charts, tables, code execution) would continue to work as-is. Artifacts would be opt-in for specific use cases where side-panel viewing is beneficial.
Beta Was this translation helpful? Give feedback.
All reactions