Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.botbrains.io/llms.txt

Use this file to discover all available pages before exploring further.

Vision lets your AI agent see and understand images that customers share during conversations. When someone sends a screenshot, product photo, or error message, the AI analyzes the content and responds with context-aware assistance.

​
How It Works

When a customer uploads an image, the AI extracts text (error codes, labels, serial numbers), recognizes objects and UI elements, and combines this visual context with conversation history and your knowledge base to respond.

​
Supported Formats

FormatExtensions
JPEG.jpg, .jpeg
PNG.png
WebP.webp
HEIC/HEIF.heic, .heif
GIF.gif

​
Enabling Vision

Enable image upload per frame:
  1. Open your frame configuration
  2. Go to General Settings
  3. Toggle Allow Image Upload
  4. Save
Frame General Settings panel with Allow Image Upload toggle enabled Add guidance to instruct your AI on how to handle specific image types (product defects, error screenshots, receipts).

​
Safety

  • The system scans all uploads for malware before processing
  • The system reports suspected CSAM to German authorities (LKA NRW) per German law
  • The system encrypts images at rest and transmits them over HTTPS