Launch HN: Midship (YC S24) – Turn unstructured documents into usable data

Midship, a startup by Max, Kieran, and Aahel, offers a solution to extract data from unstructured documents like PDFs and images. The team initially aimed to create an AI natural language workflow builder as an alternative to Zapier or Make.com, but pivoted to focus on document extraction after observing user interest. The tool combines OCR with language models to extract specific fields and tables from documents, correcting OCR mistakes and understanding context.

Midship serves two main types of users: non-technical users who extract data via the web app and developers who use the extraction API. The company charges a monthly SaaS fee per seat for the web app and a volume-based pricing for the API. The team is eager to share their product and is open to feedback from the community.

Key takeaways

Midship is a tool that simplifies the extraction of data from unstructured documents like PDFs and images.
The tool combines OCR with language models to extract specific fields and tables that users care about, correcting OCR mistakes and understanding context.
Midship caters to two main types of users: non-technical users who extract data via the web app and developers who use the extraction API.
Midship charges a monthly SaaS fee per seat for the web app and a volume-based pricing for the API.

Launch HN: Midship (YC S24) – Turn unstructured documents into usable data

Key takeaways

Discussion (0)