Roast my startup: Document data extraction with GPT

I've just launched Airparser, a document parser powered by GPT. I created it to solve the problem of parsing human-written, semi-structured, and unstructured documents. It extracts structured data from PDFs, emails, HTML, txt, scanned images to JSON that you can export anywhere via webhooks or Zapier/Make. I would love to hear your thoughts and feedback on the tool itself and the landing page (design and tool presentation)! Link: https://airparser.com