> For the complete documentation index, see [llms.txt](https://xfigura.gitbook.io/xfigura-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://xfigura.gitbook.io/xfigura-docs/generate/visione-agent.md).

# Visione Agent

Introduction to xFigura Agents and what they do.

### **Visione**

xFigura has its own built-in agent — meet Visione. It's currently in beta, and we're constantly building on it, but here's what it can do for you right now.

### **What Visione Can Do**

Visione comes loaded with a set of tools designed to keep you in flow:

* **Enhance Prompt** — refine and strengthen your text prompts for better generation results
* **Caption Image** — automatically generate descriptive captions for any image on your canvas
* **Node Selector** — intelligently identify and select the right nodes for your task
* **Workflow Generator** — build out full workflows from a simple description
* **Web Search** — pull in references and information without leaving the canvas

### **From Chat to Canvas**

Any image generated through the Visione chat can be dragged directly onto the canvas and dropped straight into your existing workflow — no exporting, no intermediary steps.