PICTURES / VISION
Teach the categories your pictures belong to.
Both picture models can also read a text column with each photo, such as an inspector’s note or a customer’s message. Rows with a note and no photo are answered from the note.
Your AI Model · Your AI Models add-on
Uses the AI your company already runs, on Amazon Bedrock, Microsoft Foundry, Google Cloud, or an OpenAI or Anthropic key. Nothing is trained: with every question it is given your categories, your labelling guide and the most similar rows your team already categorized. Try it when your company has an approved AI it wants to use, or to compare it with a trained model on the same held-out rows. Setting it up and testing it are included on Essentials and Business; publishing it needs the add-on.
AI Image Classifier Model · Vision add-on
Uses a pre-trained vision model to read pictures and learns your categories from labeled examples. Available with Vision on Essentials and Business. Train from photos in category folders or a spreadsheet of picture links. Vision classifies what pictures show; it is not OCR for extracting receipt or document text.