Artifacts & Visualization
When the agent calls a tool, the result is rendered as a visual artifact rather than plain text. Artifacts give you interactive, scannable views of your ideas — and in graph mode, they animate directly onto the mind map.
Artifact Types
Section titled “Artifact Types”| Type | Produced by | Description |
|---|---|---|
idea_grid | search_ideas (browse or search) | Grid of idea cards with title, status, and tags |
idea_card | get_idea, create_idea, update_idea | Single idea in detail or compact view |
mini_graph | discover_connections | Small force graph showing newly discovered connections |
mermaid | Any tool returning Mermaid syntax | Rendered Mermaid diagram |
brainstorm_cluster | brainstorm | Clustered display of generated idea variations |
comparison | Agent-generated comparisons | Side-by-side view of two ideas |
tag_cloud | suggest_tags | Tag suggestions with applied/unapplied state |
summary | summarize | Summary text with extracted themes |
insights | Agent-generated insight lists | Bulleted insight cards |
connection_line | link_ideas | Animated edge drawn on the mind map |
score_cards | score_idea (Pro) | Radar chart cards for each scored idea |
document | draft_document (Pro) | Full document with formatted sections |
How Artifacts Render
Section titled “How Artifacts Render”Neural Canvas
Section titled “Neural Canvas”In the Neural Canvas (split-pane view), artifacts appear in the canvas panel on the right. Each artifact is wrapped in a collapsible artifact card with:
- A header showing the artifact type icon, a title, and collapse/pin/dismiss controls
- A pin button (📌) to keep the artifact visible even as the conversation continues
- A dismiss button (×) to remove the artifact from the canvas
Multiple artifacts accumulate in the canvas as the conversation progresses. Pinned artifacts stay at the top; unpinned artifacts can be scrolled through.
Mind Map Chat Panel
Section titled “Mind Map Chat Panel”In the mind map chat panel, artifacts render differently depending on their type:
Graph mutations — tool calls that change the graph animate onto the canvas:
| Artifact | Graph effect |
|---|---|
connection_line | New edge draws with animation between source and target nodes |
idea_card (created) | New node appears with a pulse animation |
idea_card (updated) | Existing node highlights briefly to show the change |
mini_graph | New nodes and edges for all discovered connections |
Non-graph artifacts render as collapsible ToolResultCards in the chat message:
- A single header line shows the tool icon and a summary (e.g., “Found 5 ideas for ‘auth’”)
- Clicking the chevron expands to show idea reference chips, detail content, or a grid
Idea Reference Chips
Section titled “Idea Reference Chips”When an artifact references specific ideas, they appear as color-coded chips with the idea title. Clicking a chip in the mind map chat panel highlights that node on the graph and scrolls it into view.
Graph Mutations in Detail
Section titled “Graph Mutations in Detail”Graph mutations are tracked in the useAgentMindMap hook and applied via the parent component’s mutation ref. Each mutation type has a corresponding handler:
| Mutation | What happens |
|---|---|
add_node | Adds node to graph data; triggers soft refresh |
add_edge | Adds edge; animates draw from source to target |
highlight_nodes | Pulses specified nodes with a highlight color |
reheat | Re-runs the force simulation (used after semantic_layout) |
dim_except | Dims all nodes except the specified IDs (used after search) |
clear_dim | Removes all dim effects |
Undo Stack
Section titled “Undo Stack”Every graph mutation that creates data (new ideas, new relations) is recorded in an undo stack in the chat panel. The undo button in the chat header label reverses the most recent agent action:
- For created ideas: deletes the idea
- For created relations: removes the relation
- For layout changes: restores previous positions
The undo stack is per-session and cleared when the page reloads.
ToolResultCard
Section titled “ToolResultCard”Non-graph artifacts in the mind map panel render using the ToolResultCard component. The card has:
- Icon — a monospace emoji or symbol indicating the tool type
- Summary — a single-line description of the result (e.g., “Merged 3 tags → machine-learning”)
- Expand chevron — click to reveal the full detail view
- Idea reference chips — clickable chips for each idea referenced in the result
The card uses the NeuralRepo brand green (#39ff14) for icons and a dark translucent background to sit cleanly over both the canvas and the mind map.