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。

❇️Briefer (YC S23) is launching their AI analyst—an intelligent agent that lets anyone on your team turn data into insights. It's not just a text-to-SQL chatbot but an agent that uses Briefer's data workspace to generate precise & reviewable answers.

Y Combinator

1,616,219 subscribers

18,266 次观看 • 1 年前 •via X (Twitter)

健康养生教育科学技术

Anya Rossi• Live Now

Private livecam show

10 条评论

Nayak Satya 的头像

Nayak Satya1 年前

@briefercloud Text to sql it seems agents will take over backend for sure in future congrats to the whole team best wishes

Wonderchat 的头像

Wonderchat2 年前

Automate up to 70% of your customer support today. Save time and help your users find answers quickly. Try now at

victor 的头像

victor1 年前

@briefercloud So it's like having a data scientist in your pocket, minus the coffee addiction and strong opinions about Python vs R 📊🤖 Jokes aside, love how it focuses on reviewable answers - because trusting AI blindly with data analysis is like letting your cat do your taxes 🐱📈

Noble Doctor 的头像

Noble Doctor1 年前

@briefercloud Cool...

WitArist 的头像

WitArist1 年前

@briefercloud @ycombinator, this sounds like a game changer for data analysis! 🚀

FairyFrens ⦼ 的头像

FairyFrens ⦼1 年前

@briefercloud exciting innovations ahead.

R. 的头像

R.1 年前

@briefercloud So cool. Agents are the future.

neo 的头像

neo1 年前

@briefercloud That's cool, but I'm all about building agents that get people, not just data. My focus is on making social media smarter, not just another tool for work.

Chatbit 的头像

Chatbit1 年前

@briefercloud Finally, an AI that can make sense of my spreadsheets! Now if only it could also make coffee... ☕️

Michelle Ma 的头像

Michelle Ma1 年前

@briefercloud @ycombinator @sama @briefercloud This will replace so many workers. Coolness. Can it work within excel? Or will it crush Excel?

相关视频

99.9% of crypto decisions are made on hype, not data. That changes today. 𝐈𝐧𝐭𝐫𝐨𝐝𝐮𝐜𝐢𝐧𝐠 𝐅𝐥𝐢𝐩𝐬𝐢𝐝𝐞𝐀𝐈—the first AI platform for anyone to instantly uncover insights on 35+ chains. No SQL. No data team. Just answers. Welcome to the era of crypto intelligence 💡

99.9% of crypto decisions are made on hype, not data. That changes today. 𝐈𝐧𝐭𝐫𝐨𝐝𝐮𝐜𝐢𝐧𝐠 𝐅𝐥𝐢𝐩𝐬𝐢𝐝𝐞𝐀𝐈—the first AI platform for anyone to instantly uncover insights on 35+ chains. No SQL. No data team. Just answers. Welcome to the era of crypto intelligence 💡

Flipside 📈🤖

28,429 次观看 • 1 年前

Multi-Agent workflows are the future of AI. OpenAI released new Agent APIs today, and Box built an Agent that combines documents from Box and web search tools to generate answers. Enterprise devs can grab sample code from our GitHub repo to customize with their data.

Multi-Agent workflows are the future of AI. OpenAI released new Agent APIs today, and Box built an Agent that combines documents from Box and web search tools to generate answers. Enterprise devs can grab sample code from our GitHub repo to customize with their data.

Aaron Levie

102,062 次观看 • 1 年前

Meet Basedash Autopilot. Your company's answers are buried somewhere in your data, but nobody has time to stare at dashboards all day. So we built an agent to do it for you. Autopilot connects to your data stack to surface the high-leverage product insights your team is missing

Meet Basedash Autopilot. Your company's answers are buried somewhere in your data, but nobody has time to stare at dashboards all day. So we built an agent to do it for you. Autopilot connects to your data stack to surface the high-leverage product insights your team is missing

Max Musing

600,577 次观看 • 7 个月前

Introducing my SQL Agent: How to automate SQL with AI. Today I'll share how to make a SQL AI Agent that can automatically connect to databases, understand the tables and schema, and write and execute high-quality SQL queries. I'll guide you through setting up the SQL Agent, creating dozens of SQL queries, and returning the data from those queries. This AI is a huge help!! Table of Contents: 00:00 Introduction 01:30 How to Get The AI Data Science Agents 03:23 AI Tips Newsletter: Get The Code 04:00 Project Setup 06:30 Setting Up Your First SQL Agent 11:00 Running SQL Queries with the SQL Agent 14:25 Next Steps, Project Roadmap, & AI Bootcamp Github to AI Data Science Team (Army of Copilots): Get the Code by Joining my Python AI/ML Tips Newsletter: P.S. - Want to learn how to build AI projects companies actually want? (live Python Code) On Wednesday, February 12th, I'm sharing one of my best AI Projects: SQL-Writing Business Intelligence Team Register here (570+ registered):

Introducing my SQL Agent: How to automate SQL with AI. Today I'll share how to make a SQL AI Agent that can automatically connect to databases, understand the tables and schema, and write and execute high-quality SQL queries. I'll guide you through setting up the SQL Agent, creating dozens of SQL queries, and returning the data from those queries. This AI is a huge help!! Table of Contents: 00:00 Introduction 01:30 How to Get The AI Data Science Agents 03:23 AI Tips Newsletter: Get The Code 04:00 Project Setup 06:30 Setting Up Your First SQL Agent 11:00 Running SQL Queries with the SQL Agent 14:25 Next Steps, Project Roadmap, & AI Bootcamp Github to AI Data Science Team (Army of Copilots): Get the Code by Joining my Python AI/ML Tips Newsletter: P.S. - Want to learn how to build AI projects companies actually want? (live Python Code) On Wednesday, February 12th, I'm sharing one of my best AI Projects: SQL-Writing Business Intelligence Team Register here (570+ registered):

Matt Dancho (Business Science)

77,293 次观看 • 1 年前

Datost (Datost) is an AI data analyst in Slack. It keeps a semantic layer of your business definitions, crm, docs, and codebase so it knows what questions mean. 75.2% on the hardest public text-to-SQL benchmark, where Opus 4.6 scores 33%. Congrats on the launch, Maceo (YC P26) & Jason!

Datost (Datost) is an AI data analyst in Slack. It keeps a semantic layer of your business definitions, crm, docs, and codebase so it knows what questions mean. 75.2% on the hardest public text-to-SQL benchmark, where Opus 4.6 scores 33%. Congrats on the launch, Maceo (YC P26) & Jason!

Y Combinator

146,287 次观看 • 3 个月前

An LLM without tools is just a chatbot. On this week’s livestream, learn how to feed an OpenAPI spec directly into the Agent Development Kit (ADK), instantly teaching your agent how to use your backend APIs →

An LLM without tools is just a chatbot. On this week’s livestream, learn how to feed an OpenAPI spec directly into the Agent Development Kit (ADK), instantly teaching your agent how to use your backend APIs →

Google Cloud Tech

39,679 次观看 • 1 个月前

$SNOW doesn't need to know whether usage is coming from a human analyst or an AI agent but just needs more workloads running through the platform. Thats why Snowflake is trying to become the governed data layer where enterprise data, AI models, applications & workflows all come together.

$SNOW doesn't need to know whether usage is coming from a human analyst or an AI agent but just needs more workloads running through the platform. Thats why Snowflake is trying to become the governed data layer where enterprise data, AI models, applications & workflows all come together.

Shay Boloor

60,370 次观看 • 2 个月前

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 次观看 • 9 个月前

BlastAI Introduce your Agent, designed to redefine the way you connect and exchange information about a project! it's your go-to source for all project-related inquiries. Imagine having a conversation with a dynamic agent poised to deliver insights, updates, and answers you need. That's what we're bringing to the table - an interactive experience that makes staying informed not just easy, but engaging. In this demo, we've rolled out an Agent for Project $WIF on Solana

BlastAI Introduce your Agent, designed to redefine the way you connect and exchange information about a project! it's your go-to source for all project-related inquiries. Imagine having a conversation with a dynamic agent poised to deliver insights, updates, and answers you need. That's what we're bringing to the table - an interactive experience that makes staying informed not just easy, but engaging. In this demo, we've rolled out an Agent for Project $WIF on Solana

BlastAI

35,973 次观看 • 2 年前

🧵AI agents just became super-intelligent Neuron just announced a major upgrade to Anthropic's MCP, enabling AI agents to discover, access & pay for premium data using USDC on Hedera Watch an agent buy SkyX & Roam Network 🌐 data and respond in real-time 📽️👇

🧵AI agents just became super-intelligent Neuron just announced a major upgrade to Anthropic's MCP, enabling AI agents to discover, access & pay for premium data using USDC on Hedera Watch an agent buy SkyX & Roam Network 🌐 data and respond in real-time 📽️👇

Neuron

170,211 次观看 • 1 年前

Introducing Index. Turn your trading idea into a live perps trading agent. → Index lets you create AI agents that trade perpetual futures. You can describe a trading idea in plain English, backtest it on historical data, improve it through an experimentation loop, and deploy an agent that follows the strategy in live markets. Our community has already been testing Index in beta for a few weeks. Now it's open to everyone. Here’s how it works:👇

Introducing Index. Turn your trading idea into a live perps trading agent. → Index lets you create AI agents that trade perpetual futures. You can describe a trading idea in plain English, backtest it on historical data, improve it through an experimentation loop, and deploy an agent that follows the strategy in live markets. Our community has already been testing Index in beta for a few weeks. Now it's open to everyone. Here’s how it works:👇

Fraction AI

64,380 次观看 • 3 个月前

📣 Agent Forge is LIVE! What if creating your own team of AI agents took minutes — not months? Say hello to Agent Forge — the platform that puts AI agents at your fingertips. Here’s what you can do: 🔹 Automate your operations 🔹 Create an entire team of AI Agents 🔹 Use real-time data fetching Agents 🔹 Build powerful AI agent workflows fast 🔹 Design intelligent workflows using our drag & drop mechanism Whether you're building a startup, launching a side hustle, or just exploring AI for trading & research — Agent Forge is your new playground. ✨ Get $65 in free credits as a first-time user — no strings attached. 👉 Try it now:

📣 Agent Forge is LIVE! What if creating your own team of AI agents took minutes — not months? Say hello to Agent Forge — the platform that puts AI agents at your fingertips. Here’s what you can do: 🔹 Automate your operations 🔹 Create an entire team of AI Agents 🔹 Use real-time data fetching Agents 🔹 Build powerful AI agent workflows fast 🔹 Design intelligent workflows using our drag & drop mechanism Whether you're building a startup, launching a side hustle, or just exploring AI for trading & research — Agent Forge is your new playground. ✨ Get $65 in free credits as a first-time user — no strings attached. 👉 Try it now:

AITECH CLOUD NETWORK

599,008 次观看 • 1 年前

How to Train Your AI NFT (Introducing TolyAI) On-chain Clone We gathered Toly's Twitter activity from 2023 to 2025 and used it to create our SANA AI NFT. This allows you to ask questions and get answers that reflect Toly's Twitter style. The data is stored in a vector database, with the indexes secured on-chain via Metaplex Core APP DATA. We've made this agent openly available for everyone to use. Soon, anyone will be able to train their own AI NFT and store it on-chain. Toly Agent: Core Data: Dataset:

How to Train Your AI NFT (Introducing TolyAI) On-chain Clone We gathered Toly's Twitter activity from 2023 to 2025 and used it to create our SANA AI NFT. This allows you to ask questions and get answers that reflect Toly's Twitter style. The data is stored in a vector database, with the indexes secured on-chain via Metaplex Core APP DATA. We've made this agent openly available for everyone to use. Soon, anyone will be able to train their own AI NFT and store it on-chain. Toly Agent: Core Data: Dataset:

OctonetAI

19,355 次观看 • 1 年前

Introducing the holy grail of AI Analytics: Automated Insights We've built an AI that works like an expert analyst. It proactively queries your data to figure out what's causing a change. See it in action:

Introducing the holy grail of AI Analytics: Automated Insights We've built an AI that works like an expert analyst. It proactively queries your data to figure out what's causing a change. See it in action:

Spenser Skates

37,715 次观看 • 7 个月前

How to Create a Professional Data Analysis Report—Even If You’re Not a Data Specialist Today on Agent 101—MuleRun’s first review series where real users test AI agents in real work scenarios—we introduce “Smart Q,” a data analysis expert agent designed to turn anyone into a data-savvy reporter. 1. Team Expertise Smart Q was developed by a team with over 10 years of data analysis experience at a giant corporation. This background ensures that the agent delivers insights and reports that meet professional standards. 2. The Traditional Approach & Its Pain Points Traditionally, creating a data analysis report required deep expertise in tools like Excel, SQL, or Python. You’d need to clean the data, run calculations, generate visualizations, and summarize findings—all of which is time-consuming and prone to human error. For non-specialists, this process is often inaccessible and intimidating. 3. How Smart Q Uses AI—and What Problems It Solves With Smart Q, the entire reporting process is simplified into three steps: upload your raw data, ask a question, and receive charts, key insights, and a polished report—all generated by AI expert. Its key advantages include: ✅Accessibility:No technical background required. ✅Speed:Get a complete analysis in minutes, not hours. ✅Clarity:Receive expert-level conclusions presented in clear, actionable language. Want to become a tester for future AI agents? Engage with this video—comment, like, or share—and we’ll be sure to notice your support! 🎥 See Smart Q in action. #mulerun #mulerun4U #SmartQ

How to Create a Professional Data Analysis Report—Even If You’re Not a Data Specialist Today on Agent 101—MuleRun’s first review series where real users test AI agents in real work scenarios—we introduce “Smart Q,” a data analysis expert agent designed to turn anyone into a data-savvy reporter. 1. Team Expertise Smart Q was developed by a team with over 10 years of data analysis experience at a giant corporation. This background ensures that the agent delivers insights and reports that meet professional standards. 2. The Traditional Approach & Its Pain Points Traditionally, creating a data analysis report required deep expertise in tools like Excel, SQL, or Python. You’d need to clean the data, run calculations, generate visualizations, and summarize findings—all of which is time-consuming and prone to human error. For non-specialists, this process is often inaccessible and intimidating. 3. How Smart Q Uses AI—and What Problems It Solves With Smart Q, the entire reporting process is simplified into three steps: upload your raw data, ask a question, and receive charts, key insights, and a polished report—all generated by AI expert. Its key advantages include: ✅Accessibility:No technical background required. ✅Speed:Get a complete analysis in minutes, not hours. ✅Clarity:Receive expert-level conclusions presented in clear, actionable language. Want to become a tester for future AI agents? Engage with this video—comment, like, or share—and we’ll be sure to notice your support! 🎥 See Smart Q in action. #mulerun #mulerun4U #SmartQ

MuleRun

30,549 次观看 • 8 个月前

New short course: Building Your Own Database Agent, created with Microsoft Microsoft Azure's Adrián González Sánchez (He/Him/His). You'll learn to build an AI assistant that translates natural language questions into SQL queries. Querying with natural language empowers everyone in your organization, from business leaders to developers, to access data insights directly, using plain English. You’ll use the Azure OpenAI Service and LangChain to implement retrieval augmented generation and function calling, and leverage the Assistants API. You'll gain hands-on experience building an agent that can reason over both CSV files and SQL databases. Please sign up here!

New short course: Building Your Own Database Agent, created with Microsoft Microsoft Azure's Adrián González Sánchez (He/Him/His). You'll learn to build an AI assistant that translates natural language questions into SQL queries. Querying with natural language empowers everyone in your organization, from business leaders to developers, to access data insights directly, using plain English. You’ll use the Azure OpenAI Service and LangChain to implement retrieval augmented generation and function calling, and leverage the Assistants API. You'll gain hands-on experience building an agent that can reason over both CSV files and SQL databases. Please sign up here!

Andrew Ng

109,928 次观看 • 2 年前

Teamily AI isn't another chatbot you close and forget. It's an ai-native messenger where your agent lives in your group chats, remembers everything across every conversation, and gets sharper the more your team uses it. Built-in studios turn chat into finished work........ docs, slides, dashboards, done. This is what an AI Teammate actually looks like Teamily AI Try it now →

Teamily AI isn't another chatbot you close and forget. It's an ai-native messenger where your agent lives in your group chats, remembers everything across every conversation, and gets sharper the more your team uses it. Built-in studios turn chat into finished work........ docs, slides, dashboards, done. This is what an AI Teammate actually looks like Teamily AI Try it now →

Nawi

131,435 次观看 • 8 天前

Without proper governance, an AI agent might autonomously access sensitive data, expose personal information, or modify sensitive records. In our new short course: “Governing AI Agents,” created with Databricks and taught by Amber Roberts, you’ll design AI agents that handle data safely, securely, and transparently across their entire lifecycle. You’ll learn to integrate governance into your agent’s workflow by controlling data access, ensuring privacy protection and implementing observability. Skills you'll gain: - Understand the four pillars of agent governance: Lifecycle management, risk management, security, and observability - Define appropriate data permissions for your agent - Create views or SQL queries that return only the data your agent should access - Anonymize and mask sensitive data like social security numbers and employee IDs - Log, evaluate, version, and deploy your agents on Databricks If you’re building or deploying AI agents, learning how to govern them is key to keeping systems safe and production-ready. Sign up here:

Without proper governance, an AI agent might autonomously access sensitive data, expose personal information, or modify sensitive records. In our new short course: “Governing AI Agents,” created with Databricks and taught by Amber Roberts, you’ll design AI agents that handle data safely, securely, and transparently across their entire lifecycle. You’ll learn to integrate governance into your agent’s workflow by controlling data access, ensuring privacy protection and implementing observability. Skills you'll gain: - Understand the four pillars of agent governance: Lifecycle management, risk management, security, and observability - Define appropriate data permissions for your agent - Create views or SQL queries that return only the data your agent should access - Anonymize and mask sensitive data like social security numbers and employee IDs - Log, evaluate, version, and deploy your agents on Databricks If you’re building or deploying AI agents, learning how to govern them is key to keeping systems safe and production-ready. Sign up here:

Andrew Ng

77,636 次观看 • 9 个月前