AI-powered workflows for unstructured data
Trellis converts your unstructured data into SQL-compliant tables with a schema you define in natural language. With Trellis, you can now run SQL queries on complex data sources like financial documents, contracts, and emails. Our AI engine guarantees accurate schema and results. Leading enterprises use Trellis to: 1. Unlock hidden revenue in their customer data (e.g., Underwriting teams use Trellis to extract key features from transaction data and build better risk models.) 2. Supercharge RAG applications by enabling end-users to ask analytical questions not possible before with traditional Vector DB (e.g., what are the top three features that users are requesting) 3. Enrich their data warehouse with business-critical information (e.g., Retrieving detailed pricing and quantity information of products sold on competitor websites)
Jobs at Trellis
Active Founders
Mac Klinkachorn, Founder
Mac is the co-founder and CEO of Trellis. Previously, he worked at the Stanford AI lab on large multimodal models with the DoD and built ML infrastructure at Cresta, Moveworks, and Amazon. Mac started his first company at 15, building water leak detection systems, and grew it to six figures in ARR.
Jacky Lin, Founder
Jacky is a co-founder of Trellis and has taught hundreds of Stanford graduate students how to build, train, and deploy AI models in the Stanford School of Engineering & Graduate School of Business. Previously, he worked at Meta, the World Bank, and Wayfair.
Company Launches
Excited to launch Trellis AI Studio! Built for both operations teams and engineers, Trellis AI Studio allows you to quickly define complex document workflows through a spreadsheet-like interface and scale them across all your tasks in minutes—not weeks. Turn any documents, emails, and calls into your system of record, right at your fingertips.
Check out Trellis Studio in action below or try it out live!
Why we built this ❓
After launching our APIs and ETL solution earlier this year on HackerNews, we saw great adoption from fast-growing startups and enterprises looking to deliver best-in-class PDF and unstructured data processing experiences.
However, our users wanted more—they wanted their business teams to use Trellis to automate PDF workflows directly. To address this, we built Trellis Studio.
Why Trellis?
Existing document processing (i.e., “IDP”) and RPA solutions made big promises but failed to deliver—they lacked flexibility and required deployment processes that took months, if not years, to implement. These legacy systems are brittle, struggle with varying document formats, and, if you haven’t noticed, are nearly impossible to try out.
Here’s what makes us different:
-
Create custom extractions and auto-generate schemas for any data.
-
Best-in-class PDF processing & OCR — we combine vision language models and traditional OCR techniques to allow maximum flexibility while minimizing hallucinations.
-
Reference for every results
-
End-to-end integrations with your data sources and destinations.
Try Trellis live today at runtrellis.com or book a call with us here to learn how we help companies reduce over 95% of manual work and scale operations by 100x.