Interaction graph

The interaction graph is Lace’s system of record, capturing UI states, transitions, and user intent across sessions.

The interaction graph captures UI states, transitions, and actions as users move through your product. Lace AI reasons against this record so its responses get sharper over time. This is what makes Lace different from general-purpose AI chat: reasoning is grounded in the product interface, not just conversation.

What gets captured

UI states

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

Interaction events

A transition between UI states.

Field	What it records
Action type	Click, scroll, keypress, navigation
Element target	Which UI element was acted on
User intent (inferred)	What the user was likely trying to do
Result type	Page change, dialog open, error, or no change
Discrepancy	Whether the result matched intent

How the graph builds over time

Pattern recognition runs against your interaction history:

1. Transitions accumulate into a map of how users move through your product.
2. Patterns emerge: loops, dead ends, hot spots, escape points.
3. Evidence is assembled with metrics, states, and UI content.
4. Context compounds: Lace AI draws on the full graph when reasoning about your product in chat.

From signal to shipped change

1. Detect. The graph identifies a pattern worth investigating.
2. Reason. You ask Lace AI about it, or Lace AI raises it during a chat grounded in screen context.
3. Decide. You log a decision in the Decision Canvas, tied to the relevant UI elements.
4. Execute. Your coding agent queries the decision through MCP and ships the fix.