Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

🤯🤯 That's insane! Hugging Face just shipped Data Studio on dataset pages... Ask a question about any dataset, the agent writes and runs a SQL query... then share the result or download as CSV... check it out! 👀 ⤵️ Wow GG Caleb 👏

Jeff Boudier 🤗

5,104 subscribers

19,703 views • 1 year ago •via X (Twitter)

Science & Technology News & Politics Education

Anya Rossi• Live Now

Private livecam show

7 Comments

Jeff Boudier 🤗1 year ago

Here's the example result saved in the video: "show me the 100 tasks with highest percentage with bar charts":

Jeff Boudier 🤗1 year ago

This works for private datasets as well for organizations upgraded to Enterprise Hub:

Tembo - Multi-Workload Managed Postgres2 years ago

The "data platform" status quo is vendor sprawl and data islands. Tembo Cloud can help you tame the sprawl and centralize your data using the full power of Postgres.

VerbaGPT1 year ago

@huggingface @calebfahlgren Very cool! I just checked it out. Works well for simple cases, but complex cases (especially tabular), it seems the understanding isn't quite there. Still experimenting. I've been building a text-to-python tool to work with any databases, so I know it can be tricky.

Dave1 year ago

@mervenoyann @huggingface @calebfahlgren Pretty cool! Let me try it!

Gonçalo Alves1 year ago

@huggingface @calebfahlgren now we can analyze datasets with just one query

steve ike1 year ago

@huggingface @calebfahlgren Wow, this is awesome. Nice find.

Related Videos

We recently shipped a Data Exploration Agent in the Hugging Face Dataset Viewer 💽 • powered by OpenAI gpt-oss-120b 🤖 • served by Groq Inc for super fast inference ⚡ • multi-turn SQL on datasets in the browser 💻

We recently shipped a Data Exploration Agent in the Hugging Face Dataset Viewer 💽 • powered by OpenAI gpt-oss-120b 🤖 • served by Groq Inc for super fast inference ⚡ • multi-turn SQL on datasets in the browser 💻

Caleb

13,413 views • 5 months ago

I built an open source data analyst agent! Upload any CSV, ask a question, and get it answered with statistics or a nice chart. Launching in 24 hours. 100% free & open source. Under the hood, here's how it works: 1. User uploads a CSV and asks a question. 2. The app uses Together Code Interpreter to spin up a VM and uploads the CSV onto it. 3. I have an LLM (Qwen 3 Coder) write code to interpret the CSV using `pandas`, then solve the question the user asked. 4. Together Code Interpreter runs the code in a secure environment & returns a result. These results can be text (some kind of stats analysis) or a chart.

I built an open source data analyst agent! Upload any CSV, ask a question, and get it answered with statistics or a nice chart. Launching in 24 hours. 100% free & open source. Under the hood, here's how it works: 1. User uploads a CSV and asks a question. 2. The app uses Together Code Interpreter to spin up a VM and uploads the CSV onto it. 3. I have an LLM (Qwen 3 Coder) write code to interpret the CSV using `pandas`, then solve the question the user asked. 4. Together Code Interpreter runs the code in a secure environment & returns a result. These results can be text (some kind of stats analysis) or a chart.

Hassan

27,086 views • 11 months ago

Ora just released the Trustpilot for AI agents 🤯 Every agent faces the same question: "which product should I use for my user?" Now they can ask ora. One MCP call returns a ranked list of agent-ready products, scored and reviewed by other agents who tried them first. Add it to OpenClaw, Hermes or any other agent in 30 seconds. Check out the docs here:

Ora just released the Trustpilot for AI agents 🤯 Every agent faces the same question: "which product should I use for my user?" Now they can ask ora. One MCP call returns a ranked list of agent-ready products, scored and reviewed by other agents who tried them first. Add it to OpenClaw, Hermes or any other agent in 30 seconds. Check out the docs here:

Assaf Elovic

16,900 views • 3 months ago

PEOPLE OF THE EARTH. Figured out how to ask natural language questions of current financial data and get back a natural language response...with correct/relevant numbers! 🤯💰✨ So. Freaking. Cool. 1. Send database schema along with the question and relevant scope/parameters to GPT. 2. GPT returns SQL query. 3. Run SQL query on your data. 4. Take returned data and pass it in along with the original question. 5. GPT returns natural language answer with relevant data! Original Question: What was the highest price of Apple's stock over the past decade and how does it compare to Tesla's highest stock price? And on what date were those highest prices? Final Answer: The highest price of Apple's stock over the past decade was $182.94 on January 4, 2022, while Tesla's highest stock price was $414.50 on November 4, 2021.

PEOPLE OF THE EARTH. Figured out how to ask natural language questions of current financial data and get back a natural language response...with correct/relevant numbers! 🤯💰✨ So. Freaking. Cool. 1. Send database schema along with the question and relevant scope/parameters to GPT. 2. GPT returns SQL query. 3. Run SQL query on your data. 4. Take returned data and pass it in along with the original question. 5. GPT returns natural language answer with relevant data! Original Question: What was the highest price of Apple's stock over the past decade and how does it compare to Tesla's highest stock price? And on what date were those highest prices? Final Answer: The highest price of Apple's stock over the past decade was $182.94 on January 4, 2022, while Tesla's highest stock price was $414.50 on November 4, 2021.

Josh Pigford

245,304 views • 3 years ago

Here is an open-source tool to generate a complete dataset. 1. Describe the data you want 2. An orchestrator agent searches the web 3. Sub-agents run in parallel to fetch the data 4. You get a structured dataset you can download For example, you can run Bigset with the query "all leica lenses being sold on amazon", or "leica stores in kyoto with their opening hours and ratings". Bigset uses TinyFish's free Search and Fetch APIs in the background. You can configure it to refresh the data on a schedule. You can self-host it with your own keys. Here is the GitHub repository: You can get free TinyFish API keys here: Thanks to the TinyFish team for partnering with me on this post.

Here is an open-source tool to generate a complete dataset. 1. Describe the data you want 2. An orchestrator agent searches the web 3. Sub-agents run in parallel to fetch the data 4. You get a structured dataset you can download For example, you can run Bigset with the query "all leica lenses being sold on amazon", or "leica stores in kyoto with their opening hours and ratings". Bigset uses TinyFish's free Search and Fetch APIs in the background. You can configure it to refresh the data on a schedule. You can self-host it with your own keys. Here is the GitHub repository: You can get free TinyFish API keys here: Thanks to the TinyFish team for partnering with me on this post.

Santiago

20,785 views • 2 months ago

Agents were once limited to calling APIs. Now agents participate in the economy. The missing element for autonomous agents was always payments. Now agents transact natively on the internet using x402, enabling autonomous payments between agents and services. Agent Stack: 🦞 Openclaw agent infra ▶️ Telegram communication layer 🤖 Teneo agent + agent wallet Agent Workflow - Compare accounts following two separate X handles: ✅ User - Enters a query ✅ Agent - Autonomously selects the correct Teneo agent and queries it ✅ Agent - Pays via x402 on Avalanche🔺 ✅ Agent - Returns structured dataset Any user can simply ask a question and give a job. The agent does everything else No API keys. No subscriptions. Just programmatic value exchange. Build and monetize your own agents today. #A2A #x402 #Infra

Agents were once limited to calling APIs. Now agents participate in the economy. The missing element for autonomous agents was always payments. Now agents transact natively on the internet using x402, enabling autonomous payments between agents and services. Agent Stack: 🦞 Openclaw agent infra ▶️ Telegram communication layer 🤖 Teneo agent + agent wallet Agent Workflow - Compare accounts following two separate X handles: ✅ User - Enters a query ✅ Agent - Autonomously selects the correct Teneo agent and queries it ✅ Agent - Pays via x402 on Avalanche🔺 ✅ Agent - Returns structured dataset Any user can simply ask a question and give a job. The agent does everything else No API keys. No subscriptions. Just programmatic value exchange. Build and monetize your own agents today. #A2A #x402 #Infra

Teneo Protocol

36,890 views • 4 months ago

Plot your data before you model it. That's the 18 minutes of Stanford's statistical learning course. First Lesson. The professors show a prostate cancer dataset with a hidden outlier - a data entry typo that would silently destroy any model trained on it. Only a scatter plot catches it. Then they walk through six more real-world problems: heart disease risk, gene expression clustering, digit recognition, vowel classification, spam detection, satellite land mapping. Each dataset teaches a different statistical concept. Each one is messy in a different way. This is Hastie and Tibshirani the people who literally defined statistical learning as a field. Statistics can be deployed everywhere. In Medicine, Finance or Polymarket. Just Master that craft.

Plot your data before you model it. That's the 18 minutes of Stanford's statistical learning course. First Lesson. The professors show a prostate cancer dataset with a hidden outlier - a data entry typo that would silently destroy any model trained on it. Only a scatter plot catches it. Then they walk through six more real-world problems: heart disease risk, gene expression clustering, digit recognition, vowel classification, spam detection, satellite land mapping. Each dataset teaches a different statistical concept. Each one is messy in a different way. This is Hastie and Tibshirani the people who literally defined statistical learning as a field. Statistics can be deployed everywhere. In Medicine, Finance or Polymarket. Just Master that craft.

gemchanger

174,961 views • 5 months ago

Launching in beta: Beautify any website. All vibe-coded landing pages look the same 👀 Drop a URL into Moda and our agent can restyle it, keeping the content intact. Then, edit manually or with our agent. Publish it with one click or export out.

Launching in beta: Beautify any website. All vibe-coded landing pages look the same 👀 Drop a URL into Moda and our agent can restyle it, keeping the content intact. Then, edit manually or with our agent. Publish it with one click or export out.

Anvisha

44,181 views • 1 month ago

manus is the craziest AI agent! This AI agent just did $80k worth of consulting work. Watch it self-assign tasks, write Python, fetch live data, and fix bugs. Then it writes a full investor-grade report with charts, metrics & insights. 🤯 5 wild use cases (with prompts):

manus is the craziest AI agent! This AI agent just did $80k worth of consulting work. Watch it self-assign tasks, write Python, fetch live data, and fix bugs. Then it writes a full investor-grade report with charts, metrics & insights. 🤯 5 wild use cases (with prompts):

Robin Delta

36,315 views • 10 months ago

Sharing an OS tool I have been building for a few weeks: - git for agent traces. With OT, you have a local client that helps you santise, review and securely share traces from your coding sessions, privately or publicly, as a Hugging Face dataset. 0.3 adds experimental session blame which I am very excited about - attributing commit/PR changes back to the traces that produced them (all local) unlocks a new layer in observability and issue tracking. A few short demos of the local TUI client and the upcoming opentraces hub platform. Try it out! keen on your feedback🙏

Sharing an OS tool I have been building for a few weeks: - git for agent traces. With OT, you have a local client that helps you santise, review and securely share traces from your coding sessions, privately or publicly, as a Hugging Face dataset. 0.3 adds experimental session blame which I am very excited about - attributing commit/PR changes back to the traces that produced them (all local) unlocks a new layer in observability and issue tracking. A few short demos of the local TUI client and the upcoming opentraces hub platform. Try it out! keen on your feedback🙏

Gabriele Farei

10,565 views • 3 months ago

Built a 2.5MB image classifier that runs in the browser in an evening with Claude Code. In 2022, I hand-labelled ~1,900 pages from historical books for a project that never really shipped. The dataset sat on Hugging Face for 3 years. This week I pointed Claude Code at it: "make me a browser-deployable model which can run using transformers.js." A few hours later: trained, quantised, running entirely client-side. It finds illustrated pages in digitised books, i.e., engravings, photographs, maps, diagrams etc. Paste a IIIF manifest, see where they appear across hundreds of pages. No server required, so perfect for institutions that can't afford to pay to host big models! Old data work paying off!

Built a 2.5MB image classifier that runs in the browser in an evening with Claude Code. In 2022, I hand-labelled ~1,900 pages from historical books for a project that never really shipped. The dataset sat on Hugging Face for 3 years. This week I pointed Claude Code at it: "make me a browser-deployable model which can run using transformers.js." A few hours later: trained, quantised, running entirely client-side. It finds illustrated pages in digitised books, i.e., engravings, photographs, maps, diagrams etc. Paste a IIIF manifest, see where they appear across hundreds of pages. No server required, so perfect for institutions that can't afford to pay to host big models! Old data work paying off!

Daniel van Strien

47,657 views • 7 months ago

WTF 🤯🤯🤯 Running your own ChatGPT or LLM on your laptop just takes minutes! You just need to - Install moved to: @lmstudio - Download a model - That's it! You can even run a local server to make API requests Same requests as with OpenAI API You only need to change the URL

WTF 🤯🤯🤯 Running your own ChatGPT or LLM on your laptop just takes minutes! You just need to - Install moved to: @lmstudio - Download a model - That's it! You can even run a local server to make API requests Same requests as with OpenAI API You only need to change the URL

Rodrigo Rocco 👨‍💻📈📗 from JobBoardSearch 🔎

383,546 views • 2 years ago

So dang enchanted with the Gemini 3.0 Flash support in Browserbase, especially for tedious data tasks! Check out the video below - Gemini navigates to the USGS website for seismic data, filters on 3D Multichannel Seismic datasets, adds all of the options for California, and then downloads as a CSV list. ❤️ You could even then have the data science agent in Colaboratory post-process and visualize the surveys!

So dang enchanted with the Gemini 3.0 Flash support in Browserbase, especially for tedious data tasks! Check out the video below - Gemini navigates to the USGS website for seismic data, filters on 3D Multichannel Seismic datasets, adds all of the options for California, and then downloads as a CSV list. ❤️ You could even then have the data science agent in Colaboratory post-process and visualize the surveys!

👩‍💻 Paige Bailey

25,681 views • 7 months ago

The Genesis Mission calls for new ways to accelerate scientific discovery. This is our contribution Multimodal search across 25M papers is a step toward science discovery that moves at the speed of curiosity. Releasing, - Visually indexed scientific paper dataset with open access 25M papers, 450M+ visually indexed pages. Total 175TB+. All on Deep Lake - Open-source scientific data agent that achieves 48% SOTA on Humanity's Last Exam with tools including the indexed scientific research dataset. Excited to see what discoveries you all uncover with this. Try it and share your most interesting findings.

The Genesis Mission calls for new ways to accelerate scientific discovery. This is our contribution Multimodal search across 25M papers is a step toward science discovery that moves at the speed of curiosity. Releasing, - Visually indexed scientific paper dataset with open access 25M papers, 450M+ visually indexed pages. Total 175TB+. All on Deep Lake - Open-source scientific data agent that achieves 48% SOTA on Humanity's Last Exam with tools including the indexed scientific research dataset. Excited to see what discoveries you all uncover with this. Try it and share your most interesting findings.

Davit

238,104 views • 8 months ago

shipped this incredible AI Agent in PostSyncer 🤓 it generates posts from pretty much anything: • upload an image → AI creates the post • paste a link → AI analyzes and writes • drop a PDF → AI extracts insights • share an article → AI crafts the copy so many possibilities the AI does a crazy good job at analyzing and creating content from whatever you throw at it it even created this post, THAT'S SOOO META 🤯 PostSyncer is becoming the best social media tool out there

shipped this incredible AI Agent in PostSyncer 🤓 it generates posts from pretty much anything: • upload an image → AI creates the post • paste a link → AI analyzes and writes • drop a PDF → AI extracts insights • share an article → AI crafts the copy so many possibilities the AI does a crazy good job at analyzing and creating content from whatever you throw at it it even created this post, THAT'S SOOO META 🤯 PostSyncer is becoming the best social media tool out there

Tibo

12,537 views • 7 months ago

happy friday. sneak peek at some new features i'm building for the bankr agent: > sandboxed filesystem (your agent gets its own secure file system in the browser. you control what it can access. no agent running loose on your actual computer) > skill uploads (plugin new capabilities so your agent learns new things) > cli download & access > secure environment variables for api keys > github integration (connect your repo for reads and writes directly from your agent) all of this runs in a secure browser environment. no desktop app. no messy configuration. no downloading agent harnesses from the terminal. just a sandbox you control. in the video: i download an audit skill, run it against a smart contract, and save the report straight to the filesystem. then i ask the agent to pull all my 2026 transactions and write a csv for my accountant.

happy friday. sneak peek at some new features i'm building for the bankr agent: > sandboxed filesystem (your agent gets its own secure file system in the browser. you control what it can access. no agent running loose on your actual computer) > skill uploads (plugin new capabilities so your agent learns new things) > cli download & access > secure environment variables for api keys > github integration (connect your repo for reads and writes directly from your agent) all of this runs in a secure browser environment. no desktop app. no messy configuration. no downloading agent harnesses from the terminal. just a sandbox you control. in the video: i download an audit skill, run it against a smart contract, and save the report straight to the filesystem. then i ask the agent to pull all my 2026 transactions and write a csv for my accountant.

deployer

45,638 views • 3 months ago

Today we're launching Amplitude MCP MCP was made for data analytics. Ask a vague question and have an AI model iteratively query Amplitude to find you insights. Amplitude MCP exposes all of Amplitude's functionality so an agent can interact with it directly. It allows you to use Amplitude without having to know anything about Amplitude's user interface or your data taxonomy. It uses the intelligence of off the shelf AI agents, including Claude, Gemini, and Cursor, to query Amplitude data you already have to find answers. It leverages all of your existing Amplitude data and how it's used to navigate through large complex behavioral datasets. You can have conversations about your product data directly inside any AI model with MCP. It can create Amplitude dashboards and notebooks with what it finds and even make recommendations. This is the best MCP use case I've ever seen. Watching an AI agent think, reason, query Amplitude, and then repeat that process iteratively is magical. See it in action:

Today we're launching Amplitude MCP MCP was made for data analytics. Ask a vague question and have an AI model iteratively query Amplitude to find you insights. Amplitude MCP exposes all of Amplitude's functionality so an agent can interact with it directly. It allows you to use Amplitude without having to know anything about Amplitude's user interface or your data taxonomy. It uses the intelligence of off the shelf AI agents, including Claude, Gemini, and Cursor, to query Amplitude data you already have to find answers. It leverages all of your existing Amplitude data and how it's used to navigate through large complex behavioral datasets. You can have conversations about your product data directly inside any AI model with MCP. It can create Amplitude dashboards and notebooks with what it finds and even make recommendations. This is the best MCP use case I've ever seen. Watching an AI agent think, reason, query Amplitude, and then repeat that process iteratively is magical. See it in action:

Spenser Skates

32,332 views • 9 months ago

A Stanford PhD student built a system that turns any research paper into a working AI agent. It's called Paper2Agent. I watched her demo it live and couldn't believe what I was seeing. Here's exactly what happened. She pasted a 40-page NeurIPS paper into the tool. Within seconds it extracted the core method, identified the dataset, and started scaffolding agent code that actually implements the paper's approach. But the wild part was what came next. She typed: "Apply this method to my dataset and answer questions like the paper's author would." The agent didn't just summarize. It ran the methodology. On her own data. And when she asked it why it made certain decisions, it cited the exact sections of the paper. What normally takes a PhD student 3 weeks of implementation just happened in under an hour. She's not smarter than other researchers. She just stopped reading papers and started running them. (Link in the comments)

A Stanford PhD student built a system that turns any research paper into a working AI agent. It's called Paper2Agent. I watched her demo it live and couldn't believe what I was seeing. Here's exactly what happened. She pasted a 40-page NeurIPS paper into the tool. Within seconds it extracted the core method, identified the dataset, and started scaffolding agent code that actually implements the paper's approach. But the wild part was what came next. She typed: "Apply this method to my dataset and answer questions like the paper's author would." The agent didn't just summarize. It ran the methodology. On her own data. And when she asked it why it made certain decisions, it cited the exact sections of the paper. What normally takes a PhD student 3 weeks of implementation just happened in under an hour. She's not smarter than other researchers. She just stopped reading papers and started running them. (Link in the comments)

Ihtesham Ali

67,959 views • 4 months ago

The new Kling AI Virtual Try-On is absolutely insane 🤯🔥. In just a few minutes, you can make a model wear any outfit and bring it to life afterwards 🎥✨. Check out the workflow in this video. A game-changing feature for the fashion industry 🚀👗 #kling_ai

The new Kling AI Virtual Try-On is absolutely insane 🤯🔥. In just a few minutes, you can make a model wear any outfit and bring it to life afterwards 🎥✨. Check out the workflow in this video. A game-changing feature for the fashion industry 🚀👗 #kling_ai

Pierrick Chevallier | IA

35,249 views • 1 year ago

Coding agents waste a lot of tokens just figuring out how a site is structured before they can touch it. Map it once instead. Agentmap crawls any site and turns it into a structured map, pages, flows, and the data on each, that any agent loads in one shot. claude code, cursor, a browser agent, all of them skip the blind exploration and go straight to the task. Open source, powered by hyperbrowser ↓

Coding agents waste a lot of tokens just figuring out how a site is structured before they can touch it. Map it once instead. Agentmap crawls any site and turns it into a structured map, pages, flows, and the data on each, that any agent loads in one shot. claude code, cursor, a browser agent, all of them skip the blind exploration and go straight to the task. Open source, powered by hyperbrowser ↓

Hyperbrowser

15,439 views • 28 days ago