Most parsers strip all tracked changes when you extract the text. That means: ❌ Lost audit trails ❌ Manual review of revision history ❌ No programmatic access to reviewer comments ❌ Workflows that can't route based on specific edits

OCR has it's limitations when it comes to document layout/structure. When you need to have an accurate representation of the document (e.g. header levels), you need something more than OCR. Tensorlake fixes OCR results, detecting and correcting header levels when parsing. 👇

OCR engines constantly mess up document hierarchy. Section 2.2 becomes a top-level header (##) instead of nested (###). We just shipped automatic header correction. 🧵 How it works:

Anyone else notice that Chloe’s address number is 101? (She’s the Dalmatian) Or just my kid?

Anyone else notice that Chloe’s address number is 101? (She’s the Dalmatian) Or just my kid?

How do you handle citations in RAG? Being able to add spatial information from the original parse api call makes it super easy, but I'm curious how others are also handling it?

Citations. When users ask "where did this come from?" your system should point to the exact page fragment...not just "file_name.pdf". Built citation-aware RAG with spatial metadata has: → Parse docs with bounding boxes → Embed citation anchors in chunks → Return page numbers + coordinates A 🧵

"Because the AI said so" is exactly the kind of future we don't want to move towards. Those of us working in the space know that the bar is set *much* higher than that. AI is a tool. You wouldn't just hammer everything and shrug when a window breaks. Use tools intelligently.

I was listening to Mondays AI Daily Brief about infra costs/investment wrt AI and it got me wondering: How are smaller companies deciding between what to build, what infra to pay directly for, and what tools to just leverage?

Back in my day you had to take seeds out of watermelon unless you wanted a watermelon to grow in your stomach

You can now login into Tensorlake using Microsoft and Azure SSO credentials. This is the beginning of better integration with Microsoft Azure and Tensorlake. If you are using Azure, and need better Document Ingestion and ETL for unstructured data reach out to us!

Humans will always be in the loop, our tools should make data extracted with AI easily verifiable.

Just noticed this on the checkout notification I get from the Chicago Public Library. I think it’s new and I love it!

Always happy when something I've been thinking about, someone else actually writes, posts, and shares! I'm glad to see this conceptual shift from "vibe coding" to context engineering with AI-enabled developer tools! 🥳 Great article by @guthals.com. dev.to/drguthals/th...

"If Brooks were writing today, I think he’d smile at the idea of The Mythical Vibe-Month. But he’d also remind us that engineering discipline is what makes software scale." It's why I love this industry is because it's really all about learning 🤓 Regardless of my title or how tech evolves

RAG isn’t dead. It was fun coming up with the colab notebooks for this one: Compare the claims made in news articles about Tesla with actual Tesla SEC filings 👀 Check out the thread and blog (with notebooks) 👇

Genuinely curious…why are people over 30 on Snapchat?

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

Most "unstructured" parses fail on when layout gets tricky: multiple columns, fragmented text blocks, mixed reading order Tensorlake doesn't. ✅ Authors parsed as one clean chunk ✅ Abstract follows, exactly as it should Unstructured ≠ unordered Preserve reading order. Parse with Tensorlake.

The best days are the ones where kiddo comes homeeeeeeeee

Over the last few weeks we have been working a ton on some huge improvements to the @tensorlake.ai 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 🙌

Just did my first EMDR session and wow...

If Sinners doesn’t win all the awards…

drowning in various incarnations of paperwork and need to skip the stream today 😭😭 but I’ll be in with @jovidecroock.com on Thursday to talk about @preactjs.com! codetv.dev/series/learn...

When you schedule a callback with Apple and they have you on hold while they connect you, they give you an option of what type of music to listen to, or to just have silence 😅

This is a really beautiful way to blend AI, Tech, and Art in a way that is additive AND preservative (if that's a word)

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

The best part about a mini-vacay with your only kiddo as a single parent is you just pack things that bring you joy, don’t make plans, and go. You’ll have fun no matter what as long as you’re together ☺️

The reason you don't have time to write unit tests is because you didn't write unit tests.

I have launched 14 apps, but the PageAI launch has been by far the WILDEST 🥵 in my life! Y'all are the best, thank you for all the support!!! 😱 1880 websites made, 796 total signups. And PageAI is only 1 week old!!! You'll wanna read this:

I really love this video by @whitep4nth3r.com because this is something I've been thinking about since I learned assembly...every layer of abstraction creates messy bloat. The tools and abstraction layers that succeed are the ones where the messy bloat is "ok".

What are your favorite resources for learning all things AI? (Agents, MCP servers, LLMs, what have you) I'm looking to do some learnin'

Want to see the tool in action? Check out this quick demo or try it out in the Colab Notebook (linked in the comments)

Step 1: pip install langchain-tensorlake Step 2: Attach the tool to your agent Step 3: Profit

THIS is what the internet needs (But actually, learning through examples like this is what helps what you learn stick.)

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 🔥

I got to learn how to build a @langchain.bsky.social agent from @doesdatmaksense.bsky.social, who wrote this tutorial. It's pretty amazing as an agent framework 🔥

My algorithm has picked up on the fact that I’m a wannabe farmer and started showing me ads for tractors

what surprised me this week is how hard it is to find a component that can do these app store buttons and has options for size and dark mode basically gave up and added them to Shipixen myself Enjoy! 🙌

Contextual Signature Detection is where you can, yes, detect whether a signature is present in a document, but more than that - extract contextual data (structured) so that your agentic applications can actually take the next steps (e.g. ping the people that didn't sign). youtu.be/VNVsRF9Eljk?...

i was born to make websites, fun websites, silly websites, curious websites, websites that bend, delight, amuse and entertain, websites for people on planet earth and there will be no shareholder value, but the websites will be built, and they will be enjoyed

There is something about the spring/summer in WA that makes me have to get the early 2000s music going

Just “signature detected” really isn’t enough anymore tbh You need the additional context so that your agentic apps and workflows can actually be automated It’s easy, and included out of the box, with Tensorlake 👇

😮🤯

I was hyping up my kiddo for her impressive drawing skills and she said she’s only “good” and not “good good” and I mentioned practice and said “why do you think I play the piano every day?” And her response was “because you like to fill the house with music so I have something to listen to” 🥹

new Web Dev Challenge available now for supporters! (join for $5/month) see @danielroe.dev, @whitep4nth3r.com, @strange.website, @jzhao.xyz, @prkrlndn.bsky.social, and Ludo build websites with absolutely zero business value using @nordcraft.com watch: codetv.link/wdc/s2e4

This perforated ear drum is causing me to wake up with a headache and this is no fun 😢

look it's @henrihelvetica.bsky.social #GoogleIO

Woah, huge news, Copilot is going open source: www.youtube.com/watch?v=GMma...

Perforated ear drums are fun