Feature update: Trellis now supports audio file uploads! 🎉 You can now analyze sentiment, identify area for improvements, grade calls against SOPs and more from thousands of calls at the same time. 📞 ✅ Whether you're managing customer support or sales teams, this helps you uncover valuable insights from conversations at scale. 🚀
About us
Building the AI-powered data platform for Unstructured Data. Trellis AI engine transforms documents, calls, and images into structured SQL format that can be used by data and operations team. Backed by Y Combinator, General Catalyst, Telesoft Partners, Carya, & investors/execs at Google, Salesforce, and JP Morgan.
- Website
-
runtrellis.com
External link for Trellis AI
- Industry
- Data Infrastructure and Analytics
- Company size
- 11-50 employees
- Headquarters
- San Francisco
- Type
- Privately Held
Locations
-
Primary
Get directions
582 Market St
San Francisco, US
Updates
-
Trellis AI reposted this
Excited to share the latest from Trellis! 🚀 We teamed up with PostgresML to make searching through Y Combinator job listings easier and faster. Trellis transforms raw, unstructured data into a data into searchable insights, while Korvus handles lightning-fast semantic search. Together, we're turning job data into something you can quickly explore and understand. Check out the details the full article here: https://lnkd.in/gEYkcxVg
-
Trellis AI reposted this
Are you a Fintech dealing with messy data buried in PDFs, emails, or call transcripts? Think contracts, financial statements, order forms...isn't it such a headache?? 🤯 Mac Klinkachorn reached out to tell me about Trellis! His new solution uses AI to tackle this problem head-on, transforming unstructured data into clean, structured SQL formats. It handles everything from financial statements to customer support logs, making your data ready for analysis and decision-making. It’s more than just automating data entry—it’s about transforming how unstructured data is managed, making the process smoother and more efficient for everyone involved. Check out the free demo environment in the comments.
Double digits, baby! It’s our 10th edition! Have you ever walked up to an underwriter trying to explain how they made a decision on a file and they kinda look like Charlie? It's no secret that unravelling enterprise and business data for underwriters can be an exercise in futility - too much information fragmented across too many different source. Unstructured data, like phone calls, PDFs, and chats, often makes up 80% of enterprise data, yet traditional platforms struggle to handle it. This platform transforms this messy data into structured SQL format based on any schema you define in natural language, automating what was once a tedious manual process.
-
-
Trellis is super excited to be a part of #pyconus this year! Thanks Python Software Foundation, for the invite to join Startup Row. If you’re around in Pittsburgh, USA, come say hi from May 16-19, 2024. We’re already having a lot of great conversations with data teams who want to start leveraging unstructured data to automate manual financial service workflows and enhance RAG applications.
-
-
Thanks for the shout out Carya Venture Partners!
Trellis (YC W24) makes unstructured data SQL-ready with a schema you define using natural language. You can now try it live with your data at https://demo.usetrellis.co. Traditional databases are not designed for unstructured data. Trellis' AI engine combines LLMs and database query processors to guarantee correct schema and accurate results across unstructured data sources. With Trellis, data and business teams can now run SQL queries directly on unstructured data sources like financial documents, contracts, customer emails, etc. Leading companies in financial services, customer support, and insurance use Trellis to: 1. Unlock hidden revenue in their customer data 2. Supercharge RAG applications by enabling end-users to ask analytical questions not possible before with traditional Vector DB 3. Enrich their data warehouse with business-critical information Mac Klinkachorn & Jacky L. are friends from the Stanford AI Lab, where they both experienced firsthand the complexity of managing unstructured data at scale. Previously, Mac built LLM infrastructure processing terabytes of chats and sales calls for F500 companies. Jacky taught AI classes at Stanford and worked at Meta on their real-time machine learning team handling complex model deployment challenges. Learn more at https://lnkd.in/gaZq7a_f. Congrats on the launch, Mac and Jacky!