12 lines
685 B
Markdown
12 lines
685 B
Markdown
# Visual Task Assistant
|
|
Use your phone's camera to identify objects and help with physical tasks.
|
|
|
|
## Overview
|
|
A bridge between the physical world and your AI agent, using the mobile camera to provide visual context for instructions, troubleshooting, or organization.
|
|
|
|
## Features
|
|
- **Object Identification**: Use `camera_snap` to identify parts, tools, or ingredients.
|
|
- **Instructional Overlay**: Agent provides step-by-step guidance based on what it sees.
|
|
- **Visual Inventory**: Scan shelves or pantries using `camera_clip` to update your [RAG Knowledge Hub](../ai-knowledge/rag-hub.md).
|
|
- **Remote Eyes**: Allow the agent to "see" what you see when you're stuck on a DIY project.
|