What gets captured
- UI states
- Interaction events
A snapshot of what’s on screen at a point in time.
| Field | What it records |
|---|---|
| App name | Which application is in focus |
| Window title | Title of the active window |
| Element summary | Detected text, buttons, inputs |
| Visual state | Screenshot hash for change detection |
| Timestamp | When this state was observed |
How the graph builds over time
Pattern recognition runs against your interaction history:- Transitions accumulate into a map of how users move through your product.
- Patterns emerge: loops, dead ends, hot spots, escape points.
- Evidence is assembled with metrics, states, and UI content.
- Context compounds: Lace AI draws on the full graph when reasoning about your product in chat.
From signal to shipped change
- Detect. The graph identifies a pattern worth investigating.
- Reason. You ask Lace AI about it, or Lace AI raises it during a chat grounded in screen context.
- Decide. You comment in the Review canvas and resolve it into a decision, tied to the relevant UI elements.
- Execute. Your coding agent queries the decision through MCP and ships the fix.