Loading video...

Video Failed to Load

Go Home

We've spent years building LlamaParse into the most accurate document parser for production AI. Along the way, we learned a lot about what fast, lightweight parsing actually looks like under the hood. Today, we're open-sourcing a light-weight core of that tech as LiteParse 🦙 It's a CLI + TS-native...

llama_index's profile picture

LlamaIndex 🦙

119,096 subscribers

581,748 views • 5 months ago •via X (Twitter)

EducationHealth & WellnessScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

LiteParse Samples 📄🧑‍🏫 LiteParse is our free and fast document parser that can parse text with bounding boxes from any document. I’ve created a new repository that contains some demos on how you can make use of its outputs! ✅ Comparison against PyPDF and PyMuPDF ✅ Visual Citations: search for any keyword and see joined bounding boxes pop up in the source images It should be a default tool to help AI agents OCR any document type (supports PDF, Word, Powerpoint + dozens of other formats), before heavier-weight VLM-based document parsing solutions (like our own LlamaParse). LiteParse Samples repo: LiteParse:
0:33

LiteParse Samples 📄🧑‍🏫 LiteParse is our free and fast document parser that can parse text with bounding boxes from any document. I’ve created a new repository that contains some demos on how you can make use of its outputs! ✅ Comparison against PyPDF and PyMuPDF ✅ Visual Citations: search for any keyword and see joined bounding boxes pop up in the source images It should be a default tool to help AI agents OCR any document type (supports PDF, Word, Powerpoint + dozens of other formats), before heavier-weight VLM-based document parsing solutions (like our own LlamaParse). LiteParse Samples repo: LiteParse:

Jerry Liu

13,196 views • 4 months ago

Our OSS engineer Clelia Bertelli (🦀/acc) recently built 𝗹𝗶𝘁𝗲𝘀𝗲𝗮𝗿𝗰𝗵, a fully local document ingestion and retrieval CLI/TUI application powered by LiteParse ⚡ litesearch demonstrates how developers can assemble a high-performance, local-first retrieval pipeline using open tools from across the ecosystem: • Parsing: LiteParse, the fast and accurate document parser we recently open sourced • Chunking: @ChonkieAI • Embeddings: A local Nomic model via Hugging Face transformers.js • Vector storage: A local Qdrant edge shard (custom-built in Rust and compiled as a native add-on) • Retrieval: Query stored files with optional path-based filtering and configurable relevance thresholds • Runtime: Bun for speed and versatility 💻 Check out the repository and try it yourself: 📚 LiteParse docs:
0:32

Our OSS engineer Clelia Bertelli (🦀/acc) recently built 𝗹𝗶𝘁𝗲𝘀𝗲𝗮𝗿𝗰𝗵, a fully local document ingestion and retrieval CLI/TUI application powered by LiteParse ⚡ litesearch demonstrates how developers can assemble a high-performance, local-first retrieval pipeline using open tools from across the ecosystem: • Parsing: LiteParse, the fast and accurate document parser we recently open sourced • Chunking: @ChonkieAI • Embeddings: A local Nomic model via Hugging Face transformers.js • Vector storage: A local Qdrant edge shard (custom-built in Rust and compiled as a native add-on) • Retrieval: Query stored files with optional path-based filtering and configurable relevance thresholds • Runtime: Bun for speed and versatility 💻 Check out the repository and try it yourself: 📚 LiteParse docs:

LlamaIndex 🦙

14,900 views • 4 months ago

Over 1 billion PDFs are created every day, but your agents still can’t read them reliably. Today we’re releasing Parse 2.0, the most accurate document parsing API in the world. Extend already processes millions of pages daily for leading AI teams like Brex, Mercury, Opendoor, Flatiron Health, and hundreds of others. Now, its even better. Parse 2.0 is SOTA quality on RealDoc-Bench, our open source benchmark that measures agent success rate on real world docs that agents actually encounter in production. We trained Parse 2.0 on 1M+ pages of the hardest documents seen in production. Here’s how it stacks up: - #1 in healthcare, real estate, logistics, and financial services - 95.7% agent Q&A accuracy on 581 docs (next best: 92%) - 0.847 F1 on layout (next best: 0.759) Give it a try today and build production-ready document agents with Extend.
1:32

Over 1 billion PDFs are created every day, but your agents still can’t read them reliably. Today we’re releasing Parse 2.0, the most accurate document parsing API in the world. Extend already processes millions of pages daily for leading AI teams like Brex, Mercury, Opendoor, Flatiron Health, and hundreds of others. Now, its even better. Parse 2.0 is SOTA quality on RealDoc-Bench, our open source benchmark that measures agent success rate on real world docs that agents actually encounter in production. We trained Parse 2.0 on 1M+ pages of the hardest documents seen in production. Here’s how it stacks up: - #1 in healthcare, real estate, logistics, and financial services - 95.7% agent Q&A accuracy on 581 docs (next best: 92%) - 0.847 F1 on layout (next best: 0.759) Give it a try today and build production-ready document agents with Extend.

Kushal Byatnal

587,481 views • 3 months ago

We’re excited to officially launch LlamaParse, the first genAI-native document parsing solution. Not only is it better at parsing out images/tables/charts 📊📈 than virtually every other parser, it is now steerable through natural language instructions - output the document in whatever format you desire! It is also the only parsing solution that seamlessly allows you to build accurate RAG over complex documents, free of hallucinations 🔥 We launched it in private preview a few weeks ago and hit 2k users, 1M total PDF pages parsed. And now it’s better than ever. LlamaParse contains the following killer features: ✅ SOTA table/chart extraction ✅ Seamless integration with LlamaIndex 🦙 advanced RAG/agents ✅✨ Natural language Parsing Instructions ✅✨JSON mode and image extraction ✅✨Support for ~10 document types (.pdf, .pptx, .docx, .xml) and more Our pricing is simple: 1k free per day, and additional pages at 0.3c a page, or $3 for 1k pages. If you want advanced document RAG and/or private deployments, come get in touch with us to chat about LlamaCloud. Check out our full blog post here: LlamaParse client repo: Signup at 🦙☁️: Come talk to us:
5:07

We’re excited to officially launch LlamaParse, the first genAI-native document parsing solution. Not only is it better at parsing out images/tables/charts 📊📈 than virtually every other parser, it is now steerable through natural language instructions - output the document in whatever format you desire! It is also the only parsing solution that seamlessly allows you to build accurate RAG over complex documents, free of hallucinations 🔥 We launched it in private preview a few weeks ago and hit 2k users, 1M total PDF pages parsed. And now it’s better than ever. LlamaParse contains the following killer features: ✅ SOTA table/chart extraction ✅ Seamless integration with LlamaIndex 🦙 advanced RAG/agents ✅✨ Natural language Parsing Instructions ✅✨JSON mode and image extraction ✅✨Support for ~10 document types (.pdf, .pptx, .docx, .xml) and more Our pricing is simple: 1k free per day, and additional pages at 0.3c a page, or $3 for 1k pages. If you want advanced document RAG and/or private deployments, come get in touch with us to chat about LlamaCloud. Check out our full blog post here: LlamaParse client repo: Signup at 🦙☁️: Come talk to us:

LlamaIndex 🦙

143,176 views • 2 years ago

Baidu Inc. just dropped PaddleOCR-VL-1.5, and it’s not just another OCR model. This is a fully open-source OCR model with just 0.9B parameters, built specifically for production-grade document understanding. And the results speak loudly 👇 On OmniDocBench V1.5, the most authoritative global document parsing benchmark, PaddleOCR-VL-1.5 ranks #1 overall, hitting 94.5% overall accuracy, outperforming models like DeepSeek-OCR2. As the first OCR model natively supporting irregular document layout positioning, it perfectly solves OCR pain points in production for complex structured business documents such as financial reports and insurance forms. While a lot of the industry is racing toward bigger models, PaddleOCR is betting on something smarter: small parameters + high performance + open source + real usability. That combination is exactly what scalable document intelligence needs right now. Demo / API → Open source → Model → Curious to see how teams start building on top of this.
0:29

Baidu Inc. just dropped PaddleOCR-VL-1.5, and it’s not just another OCR model. This is a fully open-source OCR model with just 0.9B parameters, built specifically for production-grade document understanding. And the results speak loudly 👇 On OmniDocBench V1.5, the most authoritative global document parsing benchmark, PaddleOCR-VL-1.5 ranks #1 overall, hitting 94.5% overall accuracy, outperforming models like DeepSeek-OCR2. As the first OCR model natively supporting irregular document layout positioning, it perfectly solves OCR pain points in production for complex structured business documents such as financial reports and insurance forms. While a lot of the industry is racing toward bigger models, PaddleOCR is betting on something smarter: small parameters + high performance + open source + real usability. That combination is exactly what scalable document intelligence needs right now. Demo / API → Open source → Model → Curious to see how teams start building on top of this.

Bishal Nandi

35,318 views • 6 months ago

An underrated issue with document parsing for RAG / agent use cases is dealing with multi-page tables - sometimes a big table spills over into multiple pages. This breaks chunking algorithms that generally operate at the page-level or smaller, and causes LLMs to lose the full view of the data. With LlamaParse Continuous Mode (in beta), you can now parse a document with multi-page tables and join them into a single table! This means you can now: 💡 Do contiguous chunking for RAG use cases OR 💡 Parse the table for text-to-SQL Check out our blog post highlighting this feature. Huge shoutout to Pierre-Loic Doulcet and Sacha Bron : Signup here: It's in beta, let us know your feedback!
2:22

An underrated issue with document parsing for RAG / agent use cases is dealing with multi-page tables - sometimes a big table spills over into multiple pages. This breaks chunking algorithms that generally operate at the page-level or smaller, and causes LLMs to lose the full view of the data. With LlamaParse Continuous Mode (in beta), you can now parse a document with multi-page tables and join them into a single table! This means you can now: 💡 Do contiguous chunking for RAG use cases OR 💡 Parse the table for text-to-SQL Check out our blog post highlighting this feature. Huge shoutout to Pierre-Loic Doulcet and Sacha Bron : Signup here: It's in beta, let us know your feedback!

Jerry Liu

24,245 views • 1 year ago

Reducto CLI is the best way for agents to interact with document data in any workflow, and I’m really excited to see the range of use cases that are possible with this. It uses our frontier models for anything from parsing to editing, and can help automate full workflows like building spreadsheets or reports with really ugly cases. Raunak’s demo is a great example of what this unlocks
1:46

Reducto CLI is the best way for agents to interact with document data in any workflow, and I’m really excited to see the range of use cases that are possible with this. It uses our frontier models for anything from parsing to editing, and can help automate full workflows like building spreadsheets or reports with really ugly cases. Raunak’s demo is a great example of what this unlocks

Adit

16,957 views • 8 months ago

PDF parsing is still painful because LLMs reorder text in complex layouts, break tables across pages, and fail on graphs or images. 💡Testing the new open-source OCRFlux model, and here the results are really good for a change. So OCRFlux is a multimodal, LLM based toolkit for converting PDFs and images into clean, readable, plain Markdown text. Because the underlying VLM is only 3B param, it runs even on a 3090 GPU. The model is available on Hugging Face . The engine that powers the OCRFlux, teaches the model to rebuild every page and then stitch fragments across pages into one clean Markdown file. It bundles one vision language model with 3B parameters that was fine-tuned from Qwen 2.5-VL-3B-Instruct for both page parsing and cross-page merging. OCRFlux reads raw page images and, guided by task prompts, outputs Markdown for each page and merges split elements across pages. The evaluation shows Edit Distance Similarity (EDS) 0.967 and cross‑page table Tree Edit Distance 0.950, so the parser is both accurate and layout aware. How it works while parsing each page - Convert into text with a natural reading order, even in the presence of multi-column layouts, figures, and insets - Support for complicated tables and equations - Automatically removes headers and footers Cross-page table/paragraph merging - Cross-page table merging - Cross-page paragraph merging A compact vision‑language models can beat bigger models once cross‑page context is added. 🧵 1/n Read on 👇
0:44

PDF parsing is still painful because LLMs reorder text in complex layouts, break tables across pages, and fail on graphs or images. 💡Testing the new open-source OCRFlux model, and here the results are really good for a change. So OCRFlux is a multimodal, LLM based toolkit for converting PDFs and images into clean, readable, plain Markdown text. Because the underlying VLM is only 3B param, it runs even on a 3090 GPU. The model is available on Hugging Face . The engine that powers the OCRFlux, teaches the model to rebuild every page and then stitch fragments across pages into one clean Markdown file. It bundles one vision language model with 3B parameters that was fine-tuned from Qwen 2.5-VL-3B-Instruct for both page parsing and cross-page merging. OCRFlux reads raw page images and, guided by task prompts, outputs Markdown for each page and merges split elements across pages. The evaluation shows Edit Distance Similarity (EDS) 0.967 and cross‑page table Tree Edit Distance 0.950, so the parser is both accurate and layout aware. How it works while parsing each page - Convert into text with a natural reading order, even in the presence of multi-column layouts, figures, and insets - Support for complicated tables and equations - Automatically removes headers and footers Cross-page table/paragraph merging - Cross-page table merging - Cross-page paragraph merging A compact vision‑language models can beat bigger models once cross‑page context is added. 🧵 1/n Read on 👇

Rohan Paul

149,292 views • 1 year ago

Parsing documents with AI agents just got a lot more seamless🚀 We've rebuilt the LlamaParse MCP server to handle your document processing workflows, and you can connect it today to any MCP-compatible client at 🌐 Once connected, you'll be able to: 📁 Parse documents into clean markdown 🔍 Classify files against your own categories ✂️ Split long documents into labelled sections ⬆️ Upload files via URL or a browser-based upload flow Building a production MCP server surfaced some non-obvious challenges: getting auth to align with an existing platform identity system using WorkOS, working around MCP's lack of built-in file upload support, and making deployments, rate limiting and observability feel native with Vercel and . We wrote up all of it, from the OAuth flow, to the token-based upload design, to the tradeoffs we hit along the way📝 📚 Read the full blog: 👩‍💻 GitHub repository:
1:01

Parsing documents with AI agents just got a lot more seamless🚀 We've rebuilt the LlamaParse MCP server to handle your document processing workflows, and you can connect it today to any MCP-compatible client at 🌐 Once connected, you'll be able to: 📁 Parse documents into clean markdown 🔍 Classify files against your own categories ✂️ Split long documents into labelled sections ⬆️ Upload files via URL or a browser-based upload flow Building a production MCP server surfaced some non-obvious challenges: getting auth to align with an existing platform identity system using WorkOS, working around MCP's lack of built-in file upload support, and making deployments, rate limiting and observability feel native with Vercel and . We wrote up all of it, from the OAuth flow, to the token-based upload design, to the tradeoffs we hit along the way📝 📚 Read the full blog: 👩‍💻 GitHub repository:

LlamaIndex 🦙

19,906 views • 3 months ago

2026 might be the year where hedge fund level research becomes accessible to literally anyone. Some random guy with Claude, a few regulatory PDFs and $12 of API credits can now do the kind of reverse engineering that used to require an actual team of analysts. Meanwhile most people still think AI is for anime pictures. This Jane Street / SEBI breakdown is one of the first articles in a while that actually feels like a glimpse of where things are going More like, AI turning highly asymmetric institutional workflows into open source infrastructure. Great article to read. -> A multi-agent LLM framework that simulates a hedge fund team analyzing stocks and generating trading signals, with support for Anthropic, OpenAI, and local models. -> A Python library for parsing and analyzing all major SEC EDGAR filing types (13F, ADV, 10-K, 8-K, 13D) with a built-in Claude MCP server for natural language queries.
0:20

2026 might be the year where hedge fund level research becomes accessible to literally anyone. Some random guy with Claude, a few regulatory PDFs and $12 of API credits can now do the kind of reverse engineering that used to require an actual team of analysts. Meanwhile most people still think AI is for anime pictures. This Jane Street / SEBI breakdown is one of the first articles in a while that actually feels like a glimpse of where things are going More like, AI turning highly asymmetric institutional workflows into open source infrastructure. Great article to read. -> A multi-agent LLM framework that simulates a hedge fund team analyzing stocks and generating trading signals, with support for Anthropic, OpenAI, and local models. -> A Python library for parsing and analyzing all major SEC EDGAR filing types (13F, ADV, 10-K, 8-K, 13D) with a built-in Claude MCP server for natural language queries.

Couch

34,875 views • 3 months ago

We Parse PDFs We spent 7 figures to put this on billboards throughout SF. I thought long and hard about putting something more creative and whimsical. But then you wouldn’t know what we do. AI agents (and humans) are consuming exponentially more documents as they do real work. They need the best quality document parser to not output garbage on downstream tasks. This is what we do today as a company. If you have any PDFs (or other documents), we parse them :) If you’re around SF in June for one of the following events, come stop by our booths: ✅ Snowflake Summit (this week, Booth 1123) ✅ Databricks Data+AI Summit (June 15-18, Booth 137) ✅ AI Engineer World Fair(June 29-July 2, Booth L-G47) You can find us by the same sign we put on our billboards! We Parse PDFs LlamaIndex 🦙
2:26

We Parse PDFs We spent 7 figures to put this on billboards throughout SF. I thought long and hard about putting something more creative and whimsical. But then you wouldn’t know what we do. AI agents (and humans) are consuming exponentially more documents as they do real work. They need the best quality document parser to not output garbage on downstream tasks. This is what we do today as a company. If you have any PDFs (or other documents), we parse them :) If you’re around SF in June for one of the following events, come stop by our booths: ✅ Snowflake Summit (this week, Booth 1123) ✅ Databricks Data+AI Summit (June 15-18, Booth 137) ✅ AI Engineer World Fair(June 29-July 2, Booth L-G47) You can find us by the same sign we put on our billboards! We Parse PDFs LlamaIndex 🦙

Jerry Liu

15,150 views • 2 months ago

Web scraping will never be the same. (100% open-source visual search at scale) PixelRAG is a retrieval system that skips HTML parsing completely. Instead of scraping a page into text and embedding chunks, it screenshots the page and retrieves the image. A vision-language model reads the answer straight off the pixels. Why that matters: parsing is where web RAG quietly loses information. - A single HTML-to-text parser can drop 40%+ of a page. - Tables, charts, and layout get flattened or thrown out. - Swapping parsers alone can move accuracy ~10 points on the same docs. PixelRAG indexes the page a person actually sees. The team built a visual index of all of Wikipedia, 30M+ screenshots, and it still beats the strongest text RAG baseline by 18.1% on text-only QA. The repo also ships a Claude Code plugin that gives Claude eyes. It lets Claude screenshot any URL and read the rendered page instead of scraping the DOM. So you can hand it a live page, an arXiv paper, or your local site and ask what it actually looks like. One setup script. No MCP server, no backend. How the pipeline works: - Renders each document (web, PDF, image) to image tiles. - Embeds them with Qwen3-VL-Embedding, LoRA fine-tuned on screenshots. - Builds a FAISS index and serves a search API. A stronger reader model lifts accuracy with no re-indexing, since the index is just pixels. Everything is open-source under Apache-2.0. GitHub repo: Talking about RAG, I recently wrote an article on a new approach that makes retrieval much more efficient by cutting corpus size by 40x, reducing tokens per query by 3x, and improving vector search relevance by 2.3x. The article is quoted below.
0:55

Web scraping will never be the same. (100% open-source visual search at scale) PixelRAG is a retrieval system that skips HTML parsing completely. Instead of scraping a page into text and embedding chunks, it screenshots the page and retrieves the image. A vision-language model reads the answer straight off the pixels. Why that matters: parsing is where web RAG quietly loses information. - A single HTML-to-text parser can drop 40%+ of a page. - Tables, charts, and layout get flattened or thrown out. - Swapping parsers alone can move accuracy ~10 points on the same docs. PixelRAG indexes the page a person actually sees. The team built a visual index of all of Wikipedia, 30M+ screenshots, and it still beats the strongest text RAG baseline by 18.1% on text-only QA. The repo also ships a Claude Code plugin that gives Claude eyes. It lets Claude screenshot any URL and read the rendered page instead of scraping the DOM. So you can hand it a live page, an arXiv paper, or your local site and ask what it actually looks like. One setup script. No MCP server, no backend. How the pipeline works: - Renders each document (web, PDF, image) to image tiles. - Embeds them with Qwen3-VL-Embedding, LoRA fine-tuned on screenshots. - Builds a FAISS index and serves a search API. A stronger reader model lifts accuracy with no re-indexing, since the index is just pixels. Everything is open-source under Apache-2.0. GitHub repo: Talking about RAG, I recently wrote an article on a new approach that makes retrieval much more efficient by cutting corpus size by 40x, reducing tokens per query by 3x, and improving vector search relevance by 2.3x. The article is quoted below.

Akshay 🚀

945,628 views • 2 months ago

Kicking off the Document Agent Olympics. Build a document agent - Win $200 🥇 Document agents turn messy PDFs, invoices, and filings into structured data you can actually use. Think: extracting financials from SEC filings, reconciling invoices against contracts, or processing a stack of resumes to surface top candidates. We're giving away three $200 prizes for the best agents built over the next 3 weeks. To enter: 💛 Deploy the agent to LlamaCloud 🤝 Make sure the agent repository is public 🚀 Explain what your document agent is solving 🔥 Bonus points for a good readme and demo video And most importantly, let us know what you think about our new LlamaAgents Builder! Ready to participate? Join the contest and start building your winning agent! Signup to LlamaCloud to get started
0:35

Kicking off the Document Agent Olympics. Build a document agent - Win $200 🥇 Document agents turn messy PDFs, invoices, and filings into structured data you can actually use. Think: extracting financials from SEC filings, reconciling invoices against contracts, or processing a stack of resumes to surface top candidates. We're giving away three $200 prizes for the best agents built over the next 3 weeks. To enter: 💛 Deploy the agent to LlamaCloud 🤝 Make sure the agent repository is public 🚀 Explain what your document agent is solving 🔥 Bonus points for a good readme and demo video And most importantly, let us know what you think about our new LlamaAgents Builder! Ready to participate? Join the contest and start building your winning agent! Signup to LlamaCloud to get started

LlamaIndex 🦙

12,111 views • 6 months ago

We’re open sourcing the first document OCR benchmark for the agentic era, ParseBench. Document parsing is the foundation of every AI agent that works with real-world files. ParseBench is a benchmark that measures parsing quality specifically for agent knowledge work: ✅ It optimizes for semantic correctness (instead of exact similarity) ✅ It has the most comprehensive distribution of real-world enterprise documents It contains ~2,000 human-verified enterprise document pages with 167,000+ test rules across five dimensions that matter most: tables, charts, content faithfulness, semantic formatting, and visual grounding. We benchmarked 14 known document parsers on ParseBench, from frontier/OSS VLMs to specialized parsers to LlamaParse. Here are some of our findings: 💡 Increasing compute budget yields diminishing returns - Gemini/gpt-5-mini/haiku gain 3-5 points from minimal to high thinking, at 4x the cost. 💡 Charts are the most polarizing dimension for evaluation. Most specialized parsers score below 6%, while some VLM-based parsers do a bit better. 💡 VLMs are great at visual understanding but terrible at layout extraction. GPT-5-mini/haiku score below 10% on our visual grounding task, all specialized parsers do much better. 💡 No method crushes all 5 dimensions at once, but LlamaParse achieves the highest overall score at 84.9%, and is the leader in 4 out of the 5 dimensions. This is by far the deepest technical work that we’ve published as a company. I would encourage you to start with our blog and explore our links to Hugging Face to GitHub. All the details are in our full 35-page (!!) ArXiv whitepaper. 🌐: Blog: 📄 Paper: 💻 Code: 📊 Dataset: 🎥 YouTube:
1:08

We’re open sourcing the first document OCR benchmark for the agentic era, ParseBench. Document parsing is the foundation of every AI agent that works with real-world files. ParseBench is a benchmark that measures parsing quality specifically for agent knowledge work: ✅ It optimizes for semantic correctness (instead of exact similarity) ✅ It has the most comprehensive distribution of real-world enterprise documents It contains ~2,000 human-verified enterprise document pages with 167,000+ test rules across five dimensions that matter most: tables, charts, content faithfulness, semantic formatting, and visual grounding. We benchmarked 14 known document parsers on ParseBench, from frontier/OSS VLMs to specialized parsers to LlamaParse. Here are some of our findings: 💡 Increasing compute budget yields diminishing returns - Gemini/gpt-5-mini/haiku gain 3-5 points from minimal to high thinking, at 4x the cost. 💡 Charts are the most polarizing dimension for evaluation. Most specialized parsers score below 6%, while some VLM-based parsers do a bit better. 💡 VLMs are great at visual understanding but terrible at layout extraction. GPT-5-mini/haiku score below 10% on our visual grounding task, all specialized parsers do much better. 💡 No method crushes all 5 dimensions at once, but LlamaParse achieves the highest overall score at 84.9%, and is the leader in 4 out of the 5 dimensions. This is by far the deepest technical work that we’ve published as a company. I would encourage you to start with our blog and explore our links to Hugging Face to GitHub. All the details are in our full 35-page (!!) ArXiv whitepaper. 🌐: Blog: 📄 Paper: 💻 Code: 📊 Dataset: 🎥 YouTube:

Jerry Liu

108,093 views • 4 months ago

Today we’re introducing Superhuman Docs, the evolution of Coda (Superhuman Docs) into the best place for teams and AI to work together. I co-founded Coda to reimagine the modern document and enable anyone to make a doc as powerful as an app. Superhuman Docs builds on that mission, and is reimagined for how teams work with AI now. With Superhuman Docs, AI is no longer a solo experience. Docs AI works with you the way a teammate would, with full context of everything your team has built: your data, your briefs, your roadmaps, your connected tools. You can ask it to summarize a sprint, draft a decision record from your meeting notes, or pull a competitor analysis into a new page, and that work stays right where your teammates can pick it up. I’m incredibly proud of the team for bringing Docs to life! There’s so much more we’re launching, including a way to create custom interfaces on top of your data just by describing it. We’re also introducing Superhuman Databases for teams to manage up to 1 million rows, launching Docs MCP to open it up to the AI tools you already use, and debuting a brand new Mac app. We’ve been building toward this moment for a long time, and Docs starts rolling out today. If you’re an existing Coda user, everything you rely on in your docs will remain the same, and if you’re new, now is a great time to jump in.
4:07

Today we’re introducing Superhuman Docs, the evolution of Coda (Superhuman Docs) into the best place for teams and AI to work together. I co-founded Coda to reimagine the modern document and enable anyone to make a doc as powerful as an app. Superhuman Docs builds on that mission, and is reimagined for how teams work with AI now. With Superhuman Docs, AI is no longer a solo experience. Docs AI works with you the way a teammate would, with full context of everything your team has built: your data, your briefs, your roadmaps, your connected tools. You can ask it to summarize a sprint, draft a decision record from your meeting notes, or pull a competitor analysis into a new page, and that work stays right where your teammates can pick it up. I’m incredibly proud of the team for bringing Docs to life! There’s so much more we’re launching, including a way to create custom interfaces on top of your data just by describing it. We’re also introducing Superhuman Databases for teams to manage up to 1 million rows, launching Docs MCP to open it up to the AI tools you already use, and debuting a brand new Mac app. We’ve been building toward this moment for a long time, and Docs starts rolling out today. If you’re an existing Coda user, everything you rely on in your docs will remain the same, and if you’re new, now is a great time to jump in.

Shishir

23,966 views • 1 month ago

i built pasal(.)id during the Claude hackathon! 280 million indonesians access their laws through government pdfs scattered across 1,200+ websites. no search. no structure. just pdfs. there's no single ideal place to look up indonesian law. pasal(.)id changes that. we parse government pdfs into clean structured text and expose it through an MCP server. connect claude, ask a legal question about indonesia, get an answer with exact article citations. real law, not hallucination. but here's what gets me excited: at scale, parsing 40k+ pdfs will have edge cases... so we built a correction agent on opus 4.6 that picks up user-submitted corrections, verifies them against the original pdf, and applies fixes autonomously. and when it spots a systemic bug, it opens a github issue with a diagnosis and suggested code fix. the parser gets better on its own! entire codebase built with opus 4.6. video: live site, working MCP server, correction agent all running in production right now. open source and free forever! thank you for organizing the hackathon! cc: Cerebral Valley Ivan Porollo Boris Cherny cat Thariq Lydia Hallie ✨ Ado
1:03

i built pasal(.)id during the Claude hackathon! 280 million indonesians access their laws through government pdfs scattered across 1,200+ websites. no search. no structure. just pdfs. there's no single ideal place to look up indonesian law. pasal(.)id changes that. we parse government pdfs into clean structured text and expose it through an MCP server. connect claude, ask a legal question about indonesia, get an answer with exact article citations. real law, not hallucination. but here's what gets me excited: at scale, parsing 40k+ pdfs will have edge cases... so we built a correction agent on opus 4.6 that picks up user-submitted corrections, verifies them against the original pdf, and applies fixes autonomously. and when it spots a systemic bug, it opens a github issue with a diagnosis and suggested code fix. the parser gets better on its own! entire codebase built with opus 4.6. video: live site, working MCP server, correction agent all running in production right now. open source and free forever! thank you for organizing the hackathon! cc: Cerebral Valley Ivan Porollo Boris Cherny cat Thariq Lydia Hallie ✨ Ado

ilham

38,431 views • 6 months ago

I vibe coded a new product on the side while running Every 🧱—and today we're launching it for free. It's called Proof, and it’s a live collaborative document editor where humans and AI agents work together in the same doc. It’s built from the ground up for the kinds of documents agents are increasingly writing: bug reports, PRDs, implementation plans, research briefs, copy audits, strategy docs, memos, and proposals. It's fast, free, and open source—available now at Why Proof? When everyone on your team is working with agents, there's suddenly a ton of AI-generated text flying around—planning docs, strategy memos, session recaps. But the current process for collaborating and iterating on agent-generated writing is…weirdly primitive. It mostly takes place in Markdown files on your laptop, which makes it reminiscent of document editing in 1999. That’s why we built Proof. What makes Proof different? - Proof is agent-native. Anything you can do in Proof, your agent can do just as easily. - Proof tracks provenance: A colored rail on the left side of every document tracks who wrote what. Green means human, Purple means AI. - Proof is login-free and open source: This is because we want Proof to be your agent's favorite document editor. How we use Proof Every 🧱: - Brandon Gell had OpenAI's Codex write a feature plan in Proof, then tagged my personal Claw (R2-C2) in Slack to review it. R2-C2 left feedback, I added comments, Brandon's agent revised the plan, and then Codex executed on it. Brandon submitted a PR to production without writing a line of code. - Austin Tedesco texts his Claw ideas while he's out on a run, then has it maintain a running Proof doc for his weekly food newsletter. He dictates drafts using Naveen Naidu's Monologue, writes into the outline himself, and uses the provenance gutter to track what's his voice vs. the agent's. - Kieran Klaassen uses it as a lightweight scratchpad for his compound engineering workflow. He brainstorms with an agent in the terminal, shares to Proof with one click, then opens the doc to leave comments and tells the agent to go work on them. His take: Proof's job is to communicate about writing and ideas. Proof is free, open source, and requires no login. I built the whole thing by vibe coding between meetings. I sat down with Brandon, Kieran, and Austin on Every 🧱's AI & I to demo it live and talk about how it's changing the way we work. If you're building with agents and need a better way to collaborate on text, this one's for you. Watch below! Timestamps Introduction and the origin story of Proof: 00:02:00 From Mac app to collaborative web editor: 00:07:24 What makes Proof "agent native": 00:09:00 Live demo—watching an agent join and write inside a shared document: 00:14:30 How Austin uses Proof for creative writing and food journalism: 00:20:51 The challenge of multiple agents editing one document simultaneously: 00:24:30 When AI-written docs are better read by agents than by humans: 00:26:48 Brandon's agent-to-agent collaboration loop: 00:29:30 Proof as a lightweight scratchpad versus existing tools like Notion and GitHub: 00:37:09 Why Proof is open source and what that means for builders: 00:42:18
44:37

I vibe coded a new product on the side while running Every 🧱—and today we're launching it for free. It's called Proof, and it’s a live collaborative document editor where humans and AI agents work together in the same doc. It’s built from the ground up for the kinds of documents agents are increasingly writing: bug reports, PRDs, implementation plans, research briefs, copy audits, strategy docs, memos, and proposals. It's fast, free, and open source—available now at Why Proof? When everyone on your team is working with agents, there's suddenly a ton of AI-generated text flying around—planning docs, strategy memos, session recaps. But the current process for collaborating and iterating on agent-generated writing is…weirdly primitive. It mostly takes place in Markdown files on your laptop, which makes it reminiscent of document editing in 1999. That’s why we built Proof. What makes Proof different? - Proof is agent-native. Anything you can do in Proof, your agent can do just as easily. - Proof tracks provenance: A colored rail on the left side of every document tracks who wrote what. Green means human, Purple means AI. - Proof is login-free and open source: This is because we want Proof to be your agent's favorite document editor. How we use Proof Every 🧱: - Brandon Gell had OpenAI's Codex write a feature plan in Proof, then tagged my personal Claw (R2-C2) in Slack to review it. R2-C2 left feedback, I added comments, Brandon's agent revised the plan, and then Codex executed on it. Brandon submitted a PR to production without writing a line of code. - Austin Tedesco texts his Claw ideas while he's out on a run, then has it maintain a running Proof doc for his weekly food newsletter. He dictates drafts using Naveen Naidu's Monologue, writes into the outline himself, and uses the provenance gutter to track what's his voice vs. the agent's. - Kieran Klaassen uses it as a lightweight scratchpad for his compound engineering workflow. He brainstorms with an agent in the terminal, shares to Proof with one click, then opens the doc to leave comments and tells the agent to go work on them. His take: Proof's job is to communicate about writing and ideas. Proof is free, open source, and requires no login. I built the whole thing by vibe coding between meetings. I sat down with Brandon, Kieran, and Austin on Every 🧱's AI & I to demo it live and talk about how it's changing the way we work. If you're building with agents and need a better way to collaborate on text, this one's for you. Watch below! Timestamps Introduction and the origin story of Proof: 00:02:00 From Mac app to collaborative web editor: 00:07:24 What makes Proof "agent native": 00:09:00 Live demo—watching an agent join and write inside a shared document: 00:14:30 How Austin uses Proof for creative writing and food journalism: 00:20:51 The challenge of multiple agents editing one document simultaneously: 00:24:30 When AI-written docs are better read by agents than by humans: 00:26:48 Brandon's agent-to-agent collaboration loop: 00:29:30 Proof as a lightweight scratchpad versus existing tools like Notion and GitHub: 00:37:09 Why Proof is open source and what that means for builders: 00:42:18

Dan Shipper 📧

33,065 views • 5 months ago

In the last 18 months or so my terminal use has exploded. From being a place where I mostly navigated the file system, ran a server and did some very light nvim use, to my entire workspace, connected to multiple machines, where I spend most of my day. This is the starting point we're using for designing the Superlogical multiplexer, and we're borrowing ideas from another app that blurs the local and remote, long lived sessions and throwaway tabs: the web browser. And the first thing I wanted to borrow: favicons, for your terminal apps. We call it the Deck icon (like a deck of cards), since it needs to represent your own layout of (potentially) multiple running processes.
0:27

In the last 18 months or so my terminal use has exploded. From being a place where I mostly navigated the file system, ran a server and did some very light nvim use, to my entire workspace, connected to multiple machines, where I spend most of my day. This is the starting point we're using for designing the Superlogical multiplexer, and we're borrowing ideas from another app that blurs the local and remote, long lived sessions and throwaway tabs: the web browser. And the first thing I wanted to borrow: favicons, for your terminal apps. We call it the Deck icon (like a deck of cards), since it needs to represent your own layout of (potentially) multiple running processes.

almonk

301,890 views • 22 days ago

2am, July 2 — and we’re still shipping! We're excited to share our newest innovation: Genspark AI Docs — the world’s first full-agentic AI document creator: Instantly create any document with a single prompt — and freely edit it! Hundreds of designer templates, all free! Supports both Rich Text and Markdown formats! With AI Slides, AI Sheets, and now AI Docs, our classic productivity trio for the AI era is finally complete. We believe that in the AI era, eventually all work can be done with a simple prompt. We call this vibe working! Start vibe working today with Genspark — your all-in-one AI workspace. This is just about 10% of what we have planned. There’s another exciting product on the way — can’t wait to keep building and sharing more with everyone!
1:59

2am, July 2 — and we’re still shipping! We're excited to share our newest innovation: Genspark AI Docs — the world’s first full-agentic AI document creator: Instantly create any document with a single prompt — and freely edit it! Hundreds of designer templates, all free! Supports both Rich Text and Markdown formats! With AI Slides, AI Sheets, and now AI Docs, our classic productivity trio for the AI era is finally complete. We believe that in the AI era, eventually all work can be done with a simple prompt. We call this vibe working! Start vibe working today with Genspark — your all-in-one AI workspace. This is just about 10% of what we have planned. There’s another exciting product on the way — can’t wait to keep building and sharing more with everyone!

Eric Jing

2,497,860 views • 1 year ago

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:
3:31

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

200,832 views • 7 months ago