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.

i’ve been using for the past week web feels like a different place example - i analyze Yelp reviews for a pizza place in Houston it takes 40 sec and $0.10 (no endless scrolling and clicking) this is how agents should interact with the web

Ted | unfair.so

25,738 subscribers

47,230 views • 8 days ago •via X (Twitter)

Science & Technology Finance

Anya Rossi• Live Now

Private livecam show

19 Comments

Ajax8 days ago

thats really great! btw Ted can you merge my account on unfair, i am having problem as i recently changed my username, hope you can merge it:)

Ehsan8 days ago

smart solution to a REAL problem.

Ted | unfair.so8 days ago

facts!!

Inoms8 days ago

Perfect one

Shub8 days ago

Hell yeah

Justinas Rolando8 days ago

speeeeeed

Knowix8 days ago

I should be using it now as well! awesome product

Artem8 days ago

40 seconds and $0.10 is pretty impressive 👀 curious how it handles larger datasets with thousands of reviews

Amelia8 days ago

Saving both time and money is what makes this exciting.

Mohit8 days ago

Good one

Atta 🐬8 days ago

40s for that is impressive 👍️

AI_Explorer8 days ago

impressive work

TaraT8 days ago

this looks intersting i have to try

Aymane8 days ago

How fast is it

Jackson8 days ago

Saving money and time… game changer

Peter Dedene8 days ago

AgentWeb is really impressive, definitely on my list of startups to watch

Uday👨‍💻8 days ago

It’s a game changer now

Emaan8 days ago

thats literally a game changer

André8 days ago

That’s the future of agents browsing

Related Videos

This is what I’ve been saying for weeks on the podcast. It feels like there is no direction for Marvel. It feels like they are just spinning in different directions and no one is driving the bus. They need a clear direction for the universe.

This is what I’ve been saying for weeks on the podcast. It feels like there is no direction for Marvel. It feels like they are just spinning in different directions and no one is driving the bus. They need a clear direction for the universe.

James Portis III | JPenumbra

19,000 views • 5 months ago

This is the room she sleeps in, a place no one should call home. Bathing and using the toilet are daily struggles for her. This is not how anyone should grow old. Let’s come together and give her a safe and dignified place to live. 🙏🏾💔

This is the room she sleeps in, a place no one should call home. Bathing and using the toilet are daily struggles for her. This is not how anyone should grow old. Let’s come together and give her a safe and dignified place to live. 🙏🏾💔

#BoysLivesMatter

37,409 views • 8 months ago

“We should not have a week in November where the SEC takes it off and gets ready for rivalry week” - Brandon is fed up with the SEC November cupcakes. Presented by Twisted Tea

“We should not have a week in November where the SEC takes it off and gets ready for rivalry week” - Brandon is fed up with the SEC November cupcakes. Presented by Twisted Tea

Unnecessary Roughness

68,201 views • 11 months ago

Introducing the Agent Store: one place to discover agents you can text. No downloads, no new apps, just open Messages. Built with our friends Soar, the Agent Store is a marketplace where anyone can discover and interact with conversational agents like Soar, Tomo, and Noscroll in one place.

Introducing the Agent Store: one place to discover agents you can text. No downloads, no new apps, just open Messages. Built with our friends Soar, the Agent Store is a marketplace where anyone can discover and interact with conversational agents like Soar, Tomo, and Noscroll in one place.

Elliott Potter

35,009 views • 3 months ago

New Short Course: Building AI Browser Agents! Learn how to build AI agents that interact and take actions on websites in this course, created in partnership with and taught by and @namangarg0, Co-founders of AGI Inc. AI browser agents can log into websites, fill out forms, click through web pages, or even place orders online for you. They use both visual information, like screenshots, and structural data, like the HTML or Document Object Model (DOM) of a web page, to reason and take action. With the complexity of webpages and multiple possible actions at each step, it can be challenging for an AI browser agent to complete an assigned task. Because these agents run long action sequences, a single error—like clicking the wrong button or misreading a field—can lead to unexpected outcomes or errors that compound over time. In this course, you'll understand how autonomous web agents work, their current limitations, and how AgentQ enables them to improve through self-correction. In detail, you'll: - Learn what web agents are, how they automate tasks online, their architecture, key components, limitations, and an overview of their decision-making strategies. - Build a web agent that can scrape website and return course recommendations in a structured output format. - Build an autonomous web agent that can execute multiple tasks, such as finding and summarizing webpages, filling out a form, and signing up for a newsletter. - Explore AgentQ, a framework that enables agents to self-correct by combining Monte Carlo Tree Search (MCTS), a self-critique mechanism for continuous improvement, and Direct Preference Optimization (DPO). - Deep dive into MCTS, learn how it finds an effective path, illustrated by an example of Gridworld animation, and use AgentQ to complete web tasks. - Understand AI agents' current state and future directions—including key factors shaping their evolution, such as hardware, algorithm innovation, and data availability. By the end of this course, you will have hands-on experience building browser agents and a deeper understanding of how to make them more robust and reliable. Please sign up here:

New Short Course: Building AI Browser Agents! Learn how to build AI agents that interact and take actions on websites in this course, created in partnership with and taught by and @namangarg0, Co-founders of AGI Inc. AI browser agents can log into websites, fill out forms, click through web pages, or even place orders online for you. They use both visual information, like screenshots, and structural data, like the HTML or Document Object Model (DOM) of a web page, to reason and take action. With the complexity of webpages and multiple possible actions at each step, it can be challenging for an AI browser agent to complete an assigned task. Because these agents run long action sequences, a single error—like clicking the wrong button or misreading a field—can lead to unexpected outcomes or errors that compound over time. In this course, you'll understand how autonomous web agents work, their current limitations, and how AgentQ enables them to improve through self-correction. In detail, you'll: - Learn what web agents are, how they automate tasks online, their architecture, key components, limitations, and an overview of their decision-making strategies. - Build a web agent that can scrape website and return course recommendations in a structured output format. - Build an autonomous web agent that can execute multiple tasks, such as finding and summarizing webpages, filling out a form, and signing up for a newsletter. - Explore AgentQ, a framework that enables agents to self-correct by combining Monte Carlo Tree Search (MCTS), a self-critique mechanism for continuous improvement, and Direct Preference Optimization (DPO). - Deep dive into MCTS, learn how it finds an effective path, illustrated by an example of Gridworld animation, and use AgentQ to complete web tasks. - Understand AI agents' current state and future directions—including key factors shaping their evolution, such as hardware, algorithm innovation, and data availability. By the end of this course, you will have hands-on experience building browser agents and a deeper understanding of how to make them more robust and reliable. Please sign up here:

Andrew Ng

186,182 views • 1 year ago

🚨BREAKING: The web was never designed to be a programmable platform. It’s a chaotic, human-centric mess with no universal API. We’ve been building on a broken foundation. A fundamental shift in how we interact with the web is finally here.

🚨BREAKING: The web was never designed to be a programmable platform. It’s a chaotic, human-centric mess with no universal API. We’ve been building on a broken foundation. A fundamental shift in how we interact with the web is finally here.

FELIX

170,946 views • 8 months ago

A Web-Based, Agentic ComfyUI-Style Builder for 3D Okay, this is actually pretty interesting. I’ve been testing Flow, a new tool from 3DAIStudio . It’s basically a web-based, ComfyUI-style workflow builder made around 3D, with specialized nodes, logic nodes, and an AI agent that can help build the workflow for you. I tested it across a few different pipelines, models, and node setups — and it works surprisingly well. Full review + results in the video 👇

A Web-Based, Agentic ComfyUI-Style Builder for 3D Okay, this is actually pretty interesting. I’ve been testing Flow, a new tool from 3DAIStudio . It’s basically a web-based, ComfyUI-style workflow builder made around 3D, with specialized nodes, logic nodes, and an AI agent that can help build the workflow for you. I tested it across a few different pipelines, models, and node setups — and it works surprisingly well. Full review + results in the video 👇

Stefan 3D AI

10,579 views • 3 months ago

I’ve been filming in the hallways of 26 Federal Plaza for the past four months and yesterday I asked one of the court clerks who’d been there for years. Was it like this before with the Ice agents standing around, grabbing people and he said absolutely not this is only recently!

I’ve been filming in the hallways of 26 Federal Plaza for the past four months and yesterday I asked one of the court clerks who’d been there for years. Was it like this before with the Ice agents standing around, grabbing people and he said absolutely not this is only recently!

Sandi Bachom 📹

397,644 views • 1 year ago

If I design a menu for a pizza place, this is how it would look like. Can you share another better/improved idea?

If I design a menu for a pizza place, this is how it would look like. Can you share another better/improved idea?

Zulfiqar Ahmed 🤔

99,698 views • 3 years ago

I’ve been building Liquid Glass for the Web this last week. Works in all the major browsers including Chrome, Firefox and Safari. It’s open source and free for anyone to use

I’ve been building Liquid Glass for the Web this last week. Works in all the major browsers including Chrome, Firefox and Safari. It’s open source and free for anyone to use

Sam Asante

100,105 views • 4 months ago

Your agents suck when using the web because 85% of it doesn't have an API. Browserbase gives them everything they need to do work online. Leading AI companies like Ramp, Lovable, and Clay trust us to power agents that do real work on behalf of real people. With a single API key, your agent gets everything it needs to navigate the wild web: browsers, search, fetch, identity, a sandbox runtime, and model gateway. Stop waiting on integrations, build agents that can browse and interact with the web just like humans.

Your agents suck when using the web because 85% of it doesn't have an API. Browserbase gives them everything they need to do work online. Leading AI companies like Ramp, Lovable, and Clay trust us to power agents that do real work on behalf of real people. With a single API key, your agent gets everything it needs to navigate the wild web: browsers, search, fetch, identity, a sandbox runtime, and model gateway. Stop waiting on integrations, build agents that can browse and interact with the web just like humans.

Paul Klein IV

1,732,241 views • 7 months ago

Introducing web-agent, an open framework for building web agents 🔥 Build AI agents that search, scrape, and interact with the web - powered by the same architecture behind our /agent endpoint. 100% open source. Bring any model. Anthropic, OpenAI, or your own.

Introducing web-agent, an open framework for building web agents 🔥 Build AI agents that search, scrape, and interact with the web - powered by the same architecture behind our /agent endpoint. 100% open source. Bring any model. Anthropic, OpenAI, or your own.

Firecrawl

123,983 views • 6 months ago

I found an AI browser that is actually awesome FlowithOS is a web browser COMPLETELY powered by AI You give it tasks, the agents work for you in the background It's like an army of AI agents working for you 24/7 Here's a guide on how it works and how you can get started today

I found an AI browser that is actually awesome FlowithOS is a web browser COMPLETELY powered by AI You give it tasks, the agents work for you in the background It's like an army of AI agents working for you 24/7 Here's a guide on how it works and how you can get started today

Alex Finn

25,490 views • 10 months ago

No one can imagine how difficult it is to live in a place like this. This is tent life.😭 There is no bathroom and no potable water , It is diseases and a swamp for epidemics. This is the place where my family live now ⚠️⚠️ Please DONATE AND SHARE 🙏🆘

No one can imagine how difficult it is to live in a place like this. This is tent life.😭 There is no bathroom and no potable water , It is diseases and a swamp for epidemics. This is the place where my family live now ⚠️⚠️ Please DONATE AND SHARE 🙏🆘

ahmad shamia 🍉

14,707 views • 2 years ago

Ty Bryant, a Lexington native and 4-year Wildcat, on being a part of a Kentucky team that’s sitting at 1st place in the SEC: “It’s amazing. I told Coach Bateman when the clock was winding down ‘I love you man… I’ve been here for 4 years and I’ve never seen anything like this.’”

Ty Bryant, a Lexington native and 4-year Wildcat, on being a part of a Kentucky team that’s sitting at 1st place in the SEC: “It’s amazing. I told Coach Bateman when the clock was winding down ‘I love you man… I’ve been here for 4 years and I’ve never seen anything like this.’”

Cats Coverage

46,723 views • 12 days ago

MiniMax 2.1 by is here🎄, and I've already been using it as a drop-in replacement for Claude Sonnet 4.5! Quite impressed. It works really well with the Claude Agents SDK, at only 10% of the cost. Use case: populate deadlines for my "AI deadlines" web app

MiniMax 2.1 by is here🎄, and I've already been using it as a drop-in replacement for Claude Sonnet 4.5! Quite impressed. It works really well with the Claude Agents SDK, at only 10% of the cost. Use case: populate deadlines for my "AI deadlines" web app

Niels Rogge

13,143 views • 10 months ago