Dr G
@drguthals
Followers
3K
Following
60K
Media
3K
Statuses
19K
I'm Sarah, founding devrel engineer @tensorlake
Joined April 2009
I haven't posted yet about my new position because, no shade, I felt like the "I have a new role" just didn't do it justice. There are a lot of reasons I decided to join @tensorlake . Here's a 🧵, but a huge part is this announcement today 👇 . (1/4).
Announcing Tensorlake Cloud. Up-leveling Document Ingestion and Workflows for building agentic applications and complex business workflows.
4
1
19
RT @tensorlake: Resumes are messy. Different formats. Weird layouts. Headers in all caps. Contact info in footers. Tables pretending to be….
0
1
0
Level up your AI agent by making sure the data it references is complete and accurate. The cookbook linked below has a comparison of OpenAI answering questions based on a PDF input vs structured data and markdown chunks extracted from the PDF with Tensorlake. Check it out 👇.
Agents are only as smart as the documents they understand. If your AI agent is guessing instead of knowing, it's time to level up. @doesdatmaksense wrote a new cookbook that shows you how to feed your agents structured, searchable document data, including layouts, tables,.
0
0
2
RT @tensorlake: Need to pull tables, metadata, signatures?. Tensorlake extracts structured fields, all you have to do is provide the schema….
0
3
0
I joined @tensorlake because one thing that has always fascinated me was the intersection of data, code, and humans (and what humans are trying to achieve). Turning research papers into a natural language queryable knowledge base using @qdrant_engine and @LangChainAI? 🔥🔥🔥.
It’s time to keep up with modern RAG. Stop stuffing entire PDFs into your vector DB. With Tensorlake + @qdrant_engine, you can:.- Parse and extract only the useful parts of a doc.- Index precise segments like tables or specific sections.- Run focused, context-aware search
0
0
5
Being able to extract both and then route the contract correctly will save so much time and help us avoid the last minute scrambles or missed deadlines. 3/3.
0
0
0
The technical problem: We need detailed information extracted from documents AND the status of the contract (typically defined by the presence of signatures). 2/3.
1
0
0
What I love most about dev tools is that what you build is just a piece of the larger solution. The people problem: Humans executing contracts always have many contracts at various stages that they need to monitor and follow up on depending on status. 1/3.
Route contracts efficiently and confidently by quickly extracting key information (e.g. the buyer and seller of a property) and detecting the presence of signatures. With a single API call, your workflow just got faster.
1
0
1
Being able to extract data, reliably, from images is critical for Agentic applications reliant on unique documents like identification cards, scanned forms, pictures of receipts, you name it. Tensorlake makes it easy to extract the data you need, regardless of document type.
Structured Extraction from images power a lot of real world Agentic use cases, such as validation of license plates, driving licenses, information from invoices captured by images. Our Document Ingestion API allows you to extract data from millions of images without spinning up
0
0
1
My best friend, platonic soul mate, died today. I’m so grateful he ever came into my life. I am forever changed by him in the best ways, and would have never survived the last three years without him. If you need to rest, then fine, but I’d much prefer if you haunt me.
0
0
1
Unstructured ≠ Lack of layout. Don't miss critical information in your complex documents, make sure your document parser is extracting the correct INFORMATION, not just characters.
Checkboxes often convey source of truth in legal documents (e.g. real estate contracts, insurance policy/ACORD forms). We just shipped a new OCR Engine to consistently and accurately parses checkboxes, making it possible to build reliable agents across real estate, insurance,
0
0
1
RT @tensorlake: Most "unstructured" parses fail on when layout gets tricky:.multiple columns, fragmented text blocks, mixed reading order….
0
1
0
Over the last few weeks we have been working a ton on some huge improvements to the @tensorlake API and SDK. They are finally live 🥳. More announcements around this is coming soon, but if you didn't see the announcement in our Slack, make sure you use v2 API and SDK 0.2.20 🙌.
0
2
6
Who knew that when I learned the chorus of the Macarena as a child it was because 30 years later my child would ask me to sing it repeatedly while I drive so her toys can dance to it.
0
0
0
What are your favorite resources for learning all things AI? (Agents, MCP servers, LLMs, what have you) . I'm looking to do really deep dive.
3
0
1
RT @tensorlake: Want to see the tool in action? . Check out this quick demo or try it out in the Colab Notebook (linked in the comments) ht….
0
1
0
RT @LangChainAI: 🤖LangGraph+ Tensorlake: Unlocking Document Understanding for Agents. When creating agents that interact with data, the con….
0
42
0
This should be a *good* one.
SF 📢 join us next week at the AWS loft for a session on building Agentic Memory with MCP. 🚀. With practical demos and real-world setups from @cocoindex_io, @tensorlake, and @n8n_io. 👉 Save your spot:
0
0
5
Step 1:.pip install langchain-tensorlake. Step 2:.Attach the tool to your agent. Step 3:.Profit.
Just published 🐦⬛ langchain-tensorlake 💚. A new @LangChainAI tool to parse real-world documents (PDFs, scans, forms) with Tensorlake and feed clean, structured data right into your agents. Built for devs wrangling docs in legal, finance, healthcare & more. Blog post and.
0
0
3
I've got to say, it feels really good to have a lot to do at work but have the excited feeling of wishing you could just sit and work 24/7. It's not a negative feeling, it's very much an invigorating one 🔥.
1
0
7
I got to learn how to build a @LangChainAI agent from @doesdatmaksense, who wrote this tutorial. It's pretty amazing as an agent framework 🔥.
Build a smart real estate agent (no license required). 🧠 LangGraph (by @LangChainAI). 📝 Tensorlake Contextual Signature Detection =.✅ Knows who signed.✅ When they signed.✅ If it’s ready to close. Full tutorial + code linked below 👇.
0
0
2