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.

Tip: Use Leo's Multi-Tab Context to draw information from several tabs at once. 📚 It's a great way to complete complex tasks with our AI assistant. Here, we're using it to build a shopping list based on multiple recipes.

Brave

408,819 subscribers

65,096 views • 1 year ago •via X (Twitter)

News & Politics Science & Technology Education

Anya Rossi• Live Now

Private livecam show

11 Comments

Brave1 year ago

Multi-Tab Context is available for testing in @BraveNightly. Here's how to use it: 1. Enter full page mode in Leo. 2. Click the paper clip at the top right. 3. Pick tabs you want to use as sources. 4. Ask your question. Leo will craft an answer based on the selected tabs! 🧠

Brave1 year ago

Please try Multi-Tab Context in Brave Nightly and let us know what you think! Nightly, the testing version of our browser, lets you try out new features and offer feedback. Get it here:

Matt Figdore2 years ago

This is the biggest productivity cheat code right now. Kiss reading documents goodbye. You can get an instant summary of any document with this tool.

Valentin | SuperVictor Universe1 year ago

Brave for the W

Rodrigo ☕︎ 🤷🏻‍♂️ 👇🏻1 year ago

When will it be possible to split two tabs in the same window as well as Edge?

Brave1 year ago

In what way do you think their version of split view is better than ours?

nambavan1 year ago

When's this coming to the stable version?

Brave1 year ago

No definite release date. It's not in Brave Beta yet so will still be a bit. Already very useful in Nightly though.

john redcorn1 year ago

Thank you for being awesome!

Paul1 year ago

While I appreciate the brave browser. I do wonder who thought it a good idea to add AI to it? Did anyone stop to think if they should even do this?

Knight-King1 year ago

Any update on the playlist feature for android stable version?

Related Videos

AI is going to completely change the way we interact with our phones. Here's a first look at how we're using it to build a home screen without apps.

AI is going to completely change the way we interact with our phones. Here's a first look at how we're using it to build a home screen without apps.

Sam Hall

120,794 views • 1 year ago

Just dropped: a tutorial to build your own DEFAI agent on Chromia | Power to the Public using GOAT (Great Onchain Agent Toolkit)! Chat with AI to handle your crypto tasks - it's that simple. Your personal DeFi assistant is just a conversation away 🤖

Just dropped: a tutorial to build your own DEFAI agent on Chromia | Power to the Public using GOAT (Great Onchain Agent Toolkit)! Chat with AI to handle your crypto tasks - it's that simple. Your personal DeFi assistant is just a conversation away 🤖

superoo7

23,555 views • 1 year ago

Playing with Model Context Protocol from Anthropic and it's pure automation magic I've began using it for leading generation and data enrichment processes > Launches multiple browser sessions at once with > Goes to websites, collects information, and formats a response > Adds the leads to my Notion database You can use this too! Link to the repo is below :)

Playing with Model Context Protocol from Anthropic and it's pure automation magic I've began using it for leading generation and data enrichment processes > Launches multiple browser sessions at once with > Goes to websites, collects information, and formats a response > Adds the leads to my Notion database You can use this too! Link to the repo is below :)

AP

50,775 views • 1 year ago

How to chain multiple dexterous skills to tackle complex long-horizon manipulation tasks? Imagine retrieving a LEGO block from a pile, rotating it in-hand, and inserting it at the desired location to build a structure. Introducing our new work - Sequential Dexterity 🧵👇

How to chain multiple dexterous skills to tackle complex long-horizon manipulation tasks? Imagine retrieving a LEGO block from a pile, rotating it in-hand, and inserting it at the desired location to build a structure. Introducing our new work - Sequential Dexterity 🧵👇

Chen Wang

159,777 views • 2 years ago

🚨 Agent Swarms - Multi-Agents Delegate Complex Prompts To Sub-Agents Use Gemini 3.5 Flash, Opus 4.7 and GPT 5.5 xHIgh to create complex multi-agent system A master agent can orchestrate several worker agents to just do things Build full-stack apps, mobile apps and automate complex scheduled tasks Each agent can do different tasks including Q/A, monitoring and software development

🚨 Agent Swarms - Multi-Agents Delegate Complex Prompts To Sub-Agents Use Gemini 3.5 Flash, Opus 4.7 and GPT 5.5 xHIgh to create complex multi-agent system A master agent can orchestrate several worker agents to just do things Build full-stack apps, mobile apps and automate complex scheduled tasks Each agent can do different tasks including Q/A, monitoring and software development

Abacus.AI

82,820,405 views • 1 month ago

.Howard Lutnick: "We're going to create a great economy based on the AI infrastructure build. I think that's going to create advanced manufacturing...reshore it to America."

.Howard Lutnick: "We're going to create a great economy based on the AI infrastructure build. I think that's going to create advanced manufacturing...reshore it to America."

Rapid Response 47

54,954 views • 7 months ago

Brave Leo is rolling out on Android! Now you can use Brave's AI assistant anytime, anywhere to get the help you need. Go to Settings -> Leo now to give it a shot.

Brave Leo is rolling out on Android! Now you can use Brave's AI assistant anytime, anywhere to get the help you need. Go to Settings -> Leo now to give it a shot.

Brave

49,831 views • 2 years ago

Tip: Use Brave's AI assistant Leo for interview prep! 👨‍💼 Leo can analyze a job listing and come up with possible interview questions you can use for practice.

Tip: Use Brave's AI assistant Leo for interview prep! 👨‍💼 Leo can analyze a job listing and come up with possible interview questions you can use for practice.

Brave

12,616 views • 10 months ago

🤯 with OpenAI Whisper + TTS + GPT4V, you can just permanently share your screen with an AI and talk to it to get help on anything on screen. a generally intelligent assistant for your digital life. with a bit more engineering you could probably feed it extra docs and context based on the currently active tab/app.

🤯 with OpenAI Whisper + TTS + GPT4V, you can just permanently share your screen with an AI and talk to it to get help on anything on screen. a generally intelligent assistant for your digital life. with a bit more engineering you could probably feed it extra docs and context based on the currently active tab/app.

swyx

1,051,687 views • 2 years ago

We’re bringing together Amazon's AI shopping assistant, Rufus, and Alexa+ to create Alexa for Shopping. Super powerful assistant with context from Alexa. Rolling out starting this week and free for all Amazon customers. Details here:

We’re bringing together Amazon's AI shopping assistant, Rufus, and Alexa+ to create Alexa for Shopping. Super powerful assistant with context from Alexa. Rolling out starting this week and free for all Amazon customers. Details here:

Panos Panay

33,149 views • 1 month ago

Wave 5 is here! Headlining this update: ⏩ Windsurf Tab We've made huge improvements to our passive predictive Tab experience, which is now much faster and handles more context. It's also free to use for everyone, with no limits! Also included in this wave are several context, performance, and credit system improvements.

Wave 5 is here! Headlining this update: ⏩ Windsurf Tab We've made huge improvements to our passive predictive Tab experience, which is now much faster and handles more context. It's also free to use for everyone, with no limits! Also included in this wave are several context, performance, and credit system improvements.

Windsurf

172,321 views • 1 year ago

We're winning the AI browser wars, and we're not even trying. Our mission isn't to build a browser. We're an agent company, not a browser company. We've seen firsthand how teams struggle to get started with AI. The tools they tried are too complex and lack the context you need. We decided to build a browser since it's already the tool you work in. We all know how to use a browser. You can pick up Strawberry and start using AI agents from day one. By building a browser we are also positioning ourselves to build towards the internet of the future. An internet where trillions of agents will be communicating with each other. This is the biggest opportunity of our lifetime. But someone has to make sure it is safe, effective and accessible to teams across the world. That is our mission.

We're winning the AI browser wars, and we're not even trying. Our mission isn't to build a browser. We're an agent company, not a browser company. We've seen firsthand how teams struggle to get started with AI. The tools they tried are too complex and lack the context you need. We decided to build a browser since it's already the tool you work in. We all know how to use a browser. You can pick up Strawberry and start using AI agents from day one. By building a browser we are also positioning ourselves to build towards the internet of the future. An internet where trillions of agents will be communicating with each other. This is the biggest opportunity of our lifetime. But someone has to make sure it is safe, effective and accessible to teams across the world. That is our mission.

Charles Maddock

38,118 views • 24 days ago

We upgraded Tabracadabra 🎉 to bring an entire context-aware assistant (not just tab to autocomplete!) to any textbox. It's pretty great if you hate switching between the chat interface and what you're working on. We're also open-sourcing, so you can try it out!🧵

We upgraded Tabracadabra 🎉 to bring an entire context-aware assistant (not just tab to autocomplete!) to any textbox. It's pretty great if you hate switching between the chat interface and what you're working on. We're also open-sourcing, so you can try it out!🧵

Omar Shaikh

40,973 views • 1 month ago

We built an AI that can draw on your screen. It's a true personal tutor. Using Claude Opus we're able to draw polygons, point with pixel perfect accuracy, and walk users through complex steps directly on their screen. Here's me learning Pythagorean Theorem + FL Studio. Demo:

We built an AI that can draw on your screen. It's a true personal tutor. Using Claude Opus we're able to draw polygons, point with pixel perfect accuracy, and walk users through complex steps directly on their screen. Here's me learning Pythagorean Theorem + FL Studio. Demo:

Farza 🇵🇰🇺🇸

570,189 views • 25 days ago

Simplest way to create an AI agent today: You don't need to write any code. You don't need to build a workflow. You can literally build agents that complete useful tasks for you using a single prompt. Check the quick video I recorded!

Simplest way to create an AI agent today: You don't need to write any code. You don't need to build a workflow. You can literally build agents that complete useful tasks for you using a single prompt. Check the quick video I recorded!

Santiago

62,639 views • 8 months ago

I’m excited to kick off the first of our short courses focused on agents, starting with Building Agentic RAG with LlamaIndex, taught by Jerry Liu, CEO of LlamaIndex 🦙. This covers an important shift in RAG (retrieval augmented generation), in which rather than having the developer write explicit routines to retrieve information to feed into the LLM context, we instead build a RAG agent that that has access to tools for retrieving information. This lets the agent decide what information to fetch, and enables it to answer more complex questions using multi-step reasoning. In detail, you'll learn about: - Routing: Where your agent will use decision-making to route requests to multiple tools. - Tool Use: Where you'll create an interface for agents to select what tool (function call) to use as well as generate the right arguments. - Multi-step reasoning with tool use: Where you'll use an LLM to carry out multiple steps of reasoning, while retaining memory throughout the process. You’ll also learn how to step through what your agent is doing to debug and improve it iteratively. It’s an exciting time to build agents. Sign up and get started here!

I’m excited to kick off the first of our short courses focused on agents, starting with Building Agentic RAG with LlamaIndex, taught by Jerry Liu, CEO of LlamaIndex 🦙. This covers an important shift in RAG (retrieval augmented generation), in which rather than having the developer write explicit routines to retrieve information to feed into the LLM context, we instead build a RAG agent that that has access to tools for retrieving information. This lets the agent decide what information to fetch, and enables it to answer more complex questions using multi-step reasoning. In detail, you'll learn about: - Routing: Where your agent will use decision-making to route requests to multiple tools. - Tool Use: Where you'll create an interface for agents to select what tool (function call) to use as well as generate the right arguments. - Multi-step reasoning with tool use: Where you'll use an LLM to carry out multiple steps of reasoning, while retaining memory throughout the process. You’ll also learn how to step through what your agent is doing to debug and improve it iteratively. It’s an exciting time to build agents. Sign up and get started here!

Andrew Ng

297,131 views • 2 years ago

The best way to learn AI is to build with agents. To help with that, we've launched hands-on labs and a new series on Agentic Engineering. First topic: Agent Skills. Next in the pipeline: planning, context engineering, multi-agent systems, long-running agents,.. Go build!

The best way to learn AI is to build with agents. To help with that, we've launched hands-on labs and a new series on Agentic Engineering. First topic: Agent Skills. Next in the pipeline: planning, context engineering, multi-agent systems, long-running agents,.. Go build!

elvis

31,802 views • 1 month ago

"We're at the precipice of a transition in user behavior" - of . "It's also a transition in trust, from not trusting AI to trusting AI, so eventually the traditional knowledge of what an application is will change." "That's why I like to call it application abstraction." 🦣 "AI is really great at aggregating information both from consuming information and executing it, so users don't have to manually curate information."

"We're at the precipice of a transition in user behavior" - of . "It's also a transition in trust, from not trusting AI to trusting AI, so eventually the traditional knowledge of what an application is will change." "That's why I like to call it application abstraction." 🦣 "AI is really great at aggregating information both from consuming information and executing it, so users don't have to manually curate information."

The Rollup

14,250 views • 1 year ago

One of our favorite ways to use the Audio Overviews feature is to pair it with Deep Research. Now, with just a click, you can turn your Deep Research reports into a lively conversation for learning on-the-go. Your AI hosts will summarize the material, draw connections between topics, and engage in a dynamic back-and-forth to help you make sense of complex information in a new way.

One of our favorite ways to use the Audio Overviews feature is to pair it with Deep Research. Now, with just a click, you can turn your Deep Research reports into a lively conversation for learning on-the-go. Your AI hosts will summarize the material, draw connections between topics, and engage in a dynamic back-and-forth to help you make sense of complex information in a new way.

Google Gemini

14,793 views • 1 year ago