Agent Capabilities
PDFWordImagesOCRExtraction

Document Intelligence

Extract content from any file — text or scanned.

Upload PDFs, Word docs, spreadsheets, images, or scanned documents. The agent automatically detects the file type, extracts all content as clean Markdown, and falls back to AI vision for scanned or image-only files.

Try It

Drag a file here, or browse

PDF, DOCX, XLSX, XLS, PPTX, images, CSV, TXT, JSON, MD — up to 20 MB

Scanned PDFs and images are automatically handled with AI vision

See It in Action

Demo video coming soon.

How It Works

  1. 1

    Accepts PDF, DOCX, XLSX, XLS, PPTX, ODT, CSV, TXT, JSON, MD, PNG, JPG, WEBP, and GIF

  2. 2

    Extracts text-based content using native parsers for each format

  3. 3

    Automatically detects scanned or image-only PDFs and falls back to GPT-4o vision

  4. 4

    Images (photos, screenshots, charts) are always analysed with AI vision

  5. 5

    Returns clean, well-structured Markdown — ready for downstream skills or workflows