正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

PDFs suck. We just raised $17,000,000 in funding to fix this problem once and for all. Extend is building the modern document processing cloud. See how Brex, Square, Checkr, and Fortune 500s use it to process millions of documents:

Kushal Byatnal

6,928 subscribers

210,985 次观看 • 1 年前 •via X (Twitter)

科学技术新闻政治

Anya Rossi• Live Now

Private livecam show

10 条评论

Kushal Byatnal 的头像

Kushal Byatnal1 年前

Extend isn’t just another document API. It’s a unified set of infrastructure and tooling, built for companies ingesting documents where precision and reliability is non-negotiable. We help you achieve the highest accuracy on your most complex documents, and deploy to production in days.

Kushal Byatnal 的头像

Kushal Byatnal1 年前

Today, we’re excited to release two key improvements that make Extend even better — Tuning schemas, crafting prompts, and debugging edge cases is one of the biggest bottlenecks We're excited to release a beta of our new automated config generation to reduce that burden Soon, we'll integrate this w/ your eval sets and deploy an agent that improves your accuracy even while you sleep

Kushal Byatnal 的头像

Kushal Byatnal1 年前

Starting today, teams can try Extend instantly with our new sandbox mode! Just sign up and start running your own documents through the platform. If you ever need help, we’re just a quick message away in the product.

Kushal Byatnal 的头像

Kushal Byatnal1 年前

We’ve built the first and only full-stack document processing cloud on the market today. In the months ahead, Extend will become even smarter, autonomous, and agentic — continuously optimizing document flows for accuracy, speed, and reliability. Our north star is simple: to eliminate every bottleneck standing between teams and their unstructured data

Kushal Byatnal 的头像

Kushal Byatnal1 年前

A huge thank you to our customers, investors, and team that have taken a bet on us from day one. We have a lot more coming soon, and we need your help! Join us to build the future of document processing:

Neel Das 的头像

Neel Das1 年前

Sorry, but I didnt really understand what Extend does. Thought doc processing is already solved

Adam Rankin (hiring) 的头像

Adam Rankin (hiring)1 年前

lfg @kushalbyatnal @ebadgio_

Alex Lee ⛷ 的头像

Alex Lee ⛷1 年前

Sick video man. Congrats!

Jeff Tang 的头像

Jeff Tang1 年前

@ebadgio_ my hero @FabioFleitas looking good

gaurav agrawal 的头像

gaurav agrawal1 年前

I checked the landing page and the video, still not able to really get a hint on what problems @ExtendHQ is solving or how it can help me ?

相关视频

how it started vs. how it's going Opendoor chose Extend to power document processing for its title and escrow operations 10s of millions of pages, 300k+ homeowners, and we're just getting started

how it started vs. how it's going Opendoor chose Extend to power document processing for its title and escrow operations 10s of millions of pages, 300k+ homeowners, and we're just getting started

Kushal Byatnal

44,165 次观看 • 2 个月前

This is CSS performance problem I see all too often. The React website has some jank due due to their use of transition. Here is how to find what causes it and how and fix it

This is CSS performance problem I see all too often. The React website has some jank due due to their use of transition. Here is how to find what causes it and how and fix it

Wes Bos

80,215 次观看 • 1 年前

Made in NYC with AWS: Kushal Byatnal, CEO & Co-founder, Extend. Byatnal talks building document processing pipelines and building a successful startup in New York. From migrating to the city to migrating to AWS, the founder discusses the need for speed and the importance of partnership.

Made in NYC with AWS: Kushal Byatnal, CEO & Co-founder, Extend. Byatnal talks building document processing pipelines and building a successful startup in New York. From migrating to the city to migrating to AWS, the founder discusses the need for speed and the importance of partnership.

AWS Startups

19,746,195 次观看 • 5 个月前

GPT-4o is bad at processing PDF documents. Whoever tells you otherwise is not living in the real world. In 2024, people fill out forms using pen and paper. Try to answer questions from those forms using modern models, and you'll be disappointed. I recorded a video to show you how to fix this. The answer is simple: stop letting the model see your PDF document. Instead, preprocess it and stick to showing the model text. Watch the video. You'll go from "THIS IS CRAP" to "EXCELLENT" in no time. I'm using Unstract to turn the documents into text while keeping the original format (this is crucial!) You can use them to process up to 100 pages for free. They collaborated with me on this post. You can find the code I wrote right here:

GPT-4o is bad at processing PDF documents. Whoever tells you otherwise is not living in the real world. In 2024, people fill out forms using pen and paper. Try to answer questions from those forms using modern models, and you'll be disappointed. I recorded a video to show you how to fix this. The answer is simple: stop letting the model see your PDF document. Instead, preprocess it and stick to showing the model text. Watch the video. You'll go from "THIS IS CRAP" to "EXCELLENT" in no time. I'm using Unstract to turn the documents into text while keeping the original format (this is crucial!) You can use them to process up to 100 pages for free. They collaborated with me on this post. You can find the code I wrote right here:

Santiago

196,861 次观看 • 2 年前

Incredibly excited to share more about Reducto Studio today. We started by building the most accurate APIs, and are now building a platform to help everyone use them. Studio is a toolkit for building, evaluating, and deploying production-ready document processing pipelines.

Incredibly excited to share more about Reducto Studio today. We started by building the most accurate APIs, and are now building a platform to help everyone use them. Studio is a toolkit for building, evaluating, and deploying production-ready document processing pipelines.

Adit

22,782 次观看 • 1 年前

Building a product went from months to a weekend. Getting paid for it did not. Building is fast, marketing and growth are hard. Today we fix that. We are excited to announce CREEM 2.0 and that we have raised 7M EUR in total funding Product Hunt 😸 launch and details below 👇

Building a product went from months to a weekend. Getting paid for it did not. Building is fast, marketing and growth are hard. Today we fix that. We are excited to announce CREEM 2.0 and that we have raised 7M EUR in total funding Product Hunt 😸 launch and details below 👇

Creem 🍦

1,547,066 次观看 • 2 天前

In this brief tutorial, we demonstrate how Alphacast converts documents into an AI-powered knowledge base. You’ll see how to upload PDFs, reports, and presentations — not just structured datasets — and turn them into searchable, contextual knowledge.

In this brief tutorial, we demonstrate how Alphacast converts documents into an AI-powered knowledge base. You’ll see how to upload PDFs, reports, and presentations — not just structured datasets — and turn them into searchable, contextual knowledge.

Alphacast.io

11,115 次观看 • 7 个月前

🎬 He cheated on his husband, and it caused a huge problem… but in the midst of it all, they searched for a way to fix things. Watch till the end to see how it all unfolds.

🎬 He cheated on his husband, and it caused a huge problem… but in the midst of it all, they searched for a way to fix things. Watch till the end to see how it all unfolds.

onsoft

32,900 次观看 • 5 个月前

New course: Document AI: From OCR to Agentic Doc Extraction, built with LandingAI, where I'm executive chairman, and taught by David Park and Andrea Kropp. Much of the world's data is locked in PDFs, JPEGs, and other documents. This short course shows you how to build agentic workflows that process documents accurately: breaking them into parts, examining each piece carefully, and extracting information through multiple iterations. Traditional Optical Character Recognition (OCR) captures text but loses context from table headers, chart captions, or reading order of columns. After exploring OCR's limitations, you’ll use LandingAI's Agentic Document Extraction (ADE) framework to process documents. ADE treats pages as visually -- as images -- to parse information and extract fields. Skills you'll gain: - Build agents to convert unstructured files into structured Markdown/HTML and JSON - Use ADE to parse complex data like forms, handwriting, or equations - Map extracted information to named fields using a specified schema, with bounding boxes for grounding and validation - Deploy RAG applications with event-driven document processing Come learn about the best tools for processing documents like financial invoices, medical records, or academic papers intelligently:

New course: Document AI: From OCR to Agentic Doc Extraction, built with LandingAI, where I'm executive chairman, and taught by David Park and Andrea Kropp. Much of the world's data is locked in PDFs, JPEGs, and other documents. This short course shows you how to build agentic workflows that process documents accurately: breaking them into parts, examining each piece carefully, and extracting information through multiple iterations. Traditional Optical Character Recognition (OCR) captures text but loses context from table headers, chart captions, or reading order of columns. After exploring OCR's limitations, you’ll use LandingAI's Agentic Document Extraction (ADE) framework to process documents. ADE treats pages as visually -- as images -- to parse information and extract fields. Skills you'll gain: - Build agents to convert unstructured files into structured Markdown/HTML and JSON - Use ADE to parse complex data like forms, handwriting, or equations - Map extracted information to named fields using a specified schema, with bounding boxes for grounding and validation - Deploy RAG applications with event-driven document processing Come learn about the best tools for processing documents like financial invoices, medical records, or academic papers intelligently:

Andrew Ng

200,844 次观看 • 8 个月前

Agentic Document Extraction just got much faster! From previous 135sec median processing time down to 8sec. Extracts not just text but diagrams, charts, and form fields from PDFs to give LLM-ready output. Please see the video for details and some application ideas.

Agentic Document Extraction just got much faster! From previous 135sec median processing time down to 8sec. Extracts not just text but diagrams, charts, and form fields from PDFs to give LLM-ready output. Please see the video for details and some application ideas.

Andrew Ng

290,979 次观看 • 1 年前

"IVAN WHERE IS BITCOIN GOING IN 2026?" We got the top exactly in October Made a fortune in this bear (while your other KOL told you constantly to keep buying) And we will make a fortune in the next bull today I am launching a very affordable book about how I trade, what works for me (millions and millions of $ in profits) - see below for book

"IVAN WHERE IS BITCOIN GOING IN 2026?" We got the top exactly in October Made a fortune in this bear (while your other KOL told you constantly to keep buying) And we will make a fortune in the next bull today I am launching a very affordable book about how I trade, what works for me (millions and millions of $ in profits) - see below for book

Ivan on Tech 🍳📈💰 Head Trader @ Bullmania

370,450 次观看 • 5 个月前

A state that takes every chance to kill its youth for demanding their rights is a despicable state m, and we will not tolerate it. We have everything it takes to fix it, and fix it we shall. It is time to begin a national process that brings together all stakeholders to rebuild this republic and restore the dignity of our land.

A state that takes every chance to kill its youth for demanding their rights is a despicable state m, and we will not tolerate it. We have everything it takes to fix it, and fix it we shall. It is time to begin a national process that brings together all stakeholders to rebuild this republic and restore the dignity of our land.

Kasmuel McOure

99,183 次观看 • 1 年前

This is Tesla's biggest marketing problem & how to solve it. The problem is Autopilot. And not just in Europe... And the solution is simple. Let Elon Musk see this please.

This is Tesla's biggest marketing problem & how to solve it. The problem is Autopilot. And not just in Europe... And the solution is simple. Let Elon Musk see this please.

robot*irl

175,562 次观看 • 1 年前

We’re voting today to extend premium health care tax credits so millions of Americans don’t see their premiums skyrocket. We can fix this together: Call your Republican members of Congress and tell them to support this so we can get it done.

We’re voting today to extend premium health care tax credits so millions of Americans don’t see their premiums skyrocket. We can fix this together: Call your Republican members of Congress and tell them to support this so we can get it done.

Senator Mark Kelly

77,158 次观看 • 9 个月前

Introducing LiteParse - the best model-free document parsing tool for AI agents 💫 ✅ It’s completely open-source and free. ✅ No GPU required, will process ~500 pages in 2 seconds on commodity hardware ✅ More accurate than PyPDF, PyMuPDF, Markdown. Also way more readable - see below for how we parse tables!! ✅ Supports 50+ file formats, from PDFs to Office docs to images ✅ Is designed to plug and play with Claude Code, OpenClaw, and any other AI agent with a one-line skills install. Supports native screenshotting capabilities. We spent years building up LlamaParse by orchestrating state-of-the-art VLMs over the most complex documents. Along the way we realized that you could get quite far on most docs through fast and cheap text parsing. Take a look at the video below. For really complex tables within PDFs, we output them in a spatial grid that’s both AI and human-interpretable. Any other free/light parser light PyPDF will destroy the representation of this table and output a sequential list. This is not a replacement for a VLM-based OCR tool (it requires 0 GPUs and doesn’t use models), but it is shocking how good it is to parse most documents. Huge shoutout to Logan Markewich and Clelia Bertelli (🦀/acc) for all the work here. Come check it out: Repo:

Introducing LiteParse - the best model-free document parsing tool for AI agents 💫 ✅ It’s completely open-source and free. ✅ No GPU required, will process ~500 pages in 2 seconds on commodity hardware ✅ More accurate than PyPDF, PyMuPDF, Markdown. Also way more readable - see below for how we parse tables!! ✅ Supports 50+ file formats, from PDFs to Office docs to images ✅ Is designed to plug and play with Claude Code, OpenClaw, and any other AI agent with a one-line skills install. Supports native screenshotting capabilities. We spent years building up LlamaParse by orchestrating state-of-the-art VLMs over the most complex documents. Along the way we realized that you could get quite far on most docs through fast and cheap text parsing. Take a look at the video below. For really complex tables within PDFs, we output them in a spatial grid that’s both AI and human-interpretable. Any other free/light parser light PyPDF will destroy the representation of this table and output a sequential list. This is not a replacement for a VLM-based OCR tool (it requires 0 GPUs and doesn’t use models), but it is shocking how good it is to parse most documents. Huge shoutout to Logan Markewich and Clelia Bertelli (🦀/acc) for all the work here. Come check it out: Repo:

Jerry Liu

257,364 次观看 • 6 个月前

Claude can now create and edit files from spreadsheets and documents to PDFs and slide decks. What coding agents have been doing for software engineering is soon expanding to all knowledge work - this is just the beginning.

Claude can now create and edit files from spreadsheets and documents to PDFs and slide decks. What coding agents have been doing for software engineering is soon expanding to all knowledge work - this is just the beginning.

Alex Albert

347,433 次观看 • 1 年前

One of the hardest problems with using AI agents to automate meaningful document work (contracts, KYC, diligence, claims, and more) is not actually building the agent, but building the UI/UX audit trail so the human can understand decisions linking back to the source documents - in PDFs, Powerpoint, Word, etc. This requires really good layout detection and segmentation, that you need to surface as *metadata context* to the AI agent, beyond any document -> markdown conversion. We've built really-nice VLM-capabilities to identify and segment all the elements within your document: from tables to charts to form boxes. You can use this metadata to directly provide experiences where humans can analyze the source document even as decisions are being made. Come check out LlamaParse!

One of the hardest problems with using AI agents to automate meaningful document work (contracts, KYC, diligence, claims, and more) is not actually building the agent, but building the UI/UX audit trail so the human can understand decisions linking back to the source documents - in PDFs, Powerpoint, Word, etc. This requires really good layout detection and segmentation, that you need to surface as metadata context to the AI agent, beyond any document -> markdown conversion. We've built really-nice VLM-capabilities to identify and segment all the elements within your document: from tables to charts to form boxes. You can use this metadata to directly provide experiences where humans can analyze the source document even as decisions are being made. Come check out LlamaParse!

Jerry Liu

19,283 次观看 • 6 个月前

A lot of people still don’t know how to use condoms properly. Let’s fix that today, once and for all 👇🏾

Sensitive content

A lot of people still don’t know how to use condoms properly. Let’s fix that today, once and for all 👇🏾

Elizabeth Adewale

177,746 次观看 • 10 个月前