The engineering world (manufacturing, construction, industrials) relies heavily on 2-dimensional PDF and CAD drawings as a way to communicate between companies. Engineers spend hundreds of hours to count and measure things on drawings to estimate costs and quote work- resulting in missed revenue and cost overruns. Unfortunately, LLMs and VLMs are still quite bad at analyzing these drawings.

Outerport is building a foundation model and platform for turning technical engineering documents into structured data to solve this problem. Our mission is to convert every technical document into a knowledge graph that can then be queried to help tasks like quoting or used as a knowledge base for Q&A. We also build interactive interfaces for engineers to quickly validate the analyses from the AI models. Outerport is already used at Fortune 500 enterprise companies in manufacturing & industrials.

Our team consists of experts in computer vision, computer graphics, systems software, and AI from NVIDIA, LinkedIn, Meta, Embark Trucks, Tulip Interfaces, and more. With backing from Y Combinator and top-tier venture capital firms and angels, we're looking to expand our team to accelerate product development.

We work in-person in SF, and we're a team that enjoy playing sports together and debating about the latest LLM and VLM papers.