Загрузка видео...

Не удалось загрузить видео

На главную

Here's a sneak peak at how we'll enable simple human-in-the-loop authentication for agents like OpenAI Operator and Browserbase Stagehand

clerk's profile picture

Clerk

34,677 subscribers

32,145 просмотров • 1 год назад •via X (Twitter)

ОбразованиеНаука и технологииНовости и политика
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 5

Фото профиля Clerk
Clerk1 год назад

Small correction: it’s @browserbasehq Stagehand*

Фото профиля Diego Alejandro
Diego Alejandro1 год назад

@OpenAI @BrowserBase

Фото профиля Philipp Tsipman
Philipp Tsipman1 год назад

One of the most obvious use cases — this could be great for e2e QA testing Excited to check it out when you ship!

Фото профиля SecurityPal
SecurityPal2 лет назад

Streamline your vendor assessment and mitigate third-party risks with SecurityPal's Vendor Assess. See how CAx enhances security for top companies like @OpenAI @Figma @MongoDB & @Airtable. Check our latest blog🔗: #VendorManagement #RiskManagement

Фото профиля browserbase 🅱️
browserbase 🅱️1 год назад

@OpenAI @BrowserBase 🅱️🤝🔐

Похожие видео

INCREDIBLE!! An MCP server to browse the web like humans! Stagehand by browserbase 🅱️ allows Agents to independently control a browser. Integrating its MCP server with Claude delivers a more reliable alternative to OpenAI Operator. 100% open-source with 10k stars!
0:24

INCREDIBLE!! An MCP server to browse the web like humans! Stagehand by browserbase 🅱️ allows Agents to independently control a browser. Integrating its MCP server with Claude delivers a more reliable alternative to OpenAI Operator. 100% open-source with 10k stars!

Avi Chawla

134,242 просмотров • 1 год назад

Introducing the Stagehand Cache We make your agents and automations faster by caching repeated actions, so identical requests skip redundant LLM calls. Available for free for all Stagehand sessions run on Browserbase.
1:29

Introducing the Stagehand Cache We make your agents and automations faster by caching repeated actions, so identical requests skip redundant LLM calls. Available for free for all Stagehand sessions run on Browserbase.

Stagehand

60,872 просмотров • 5 месяцев назад

Your Operator and Drifter are getting a makeover! Here's a sneak peek at the Operator and Drifter remaster to come at a later date.
1:00

Your Operator and Drifter are getting a makeover! Here's a sneak peek at the Operator and Drifter remaster to come at a later date.

WARFRAME

89,477 просмотров • 10 месяцев назад

Browserbase just launched Director AI. It's an AI tool that can automate any web task using simple English prompts and generate repeatable automation code in one step. Like OpenAI Operator but free, with no coding required. +
0:41

Browserbase just launched Director AI. It's an AI tool that can automate any web task using simple English prompts and generate repeatable automation code in one step. Like OpenAI Operator but free, with no coding required. +

Shubham Saboo

21,166 просмотров • 1 год назад

When the Age is ending but the chaos is just beginning... 🔥 Here's a sneak peak at how crises work in #Civ7:
0:56

When the Age is ending but the chaos is just beginning... 🔥 Here's a sneak peak at how crises work in #Civ7:

Firaxis Games

41,640 просмотров • 1 год назад

Your agents should use a remote browser built specifically for them, We revamped our Browser Skill to use our custom Stagehand CLI, It's faster than MCP tools and each run uses a new browser context, avoiding prompt injection. npx skills add browserbase/skills —skill browser
0:22

Your agents should use a remote browser built specifically for them, We revamped our Browser Skill to use our custom Stagehand CLI, It's faster than MCP tools and each run uses a new browser context, avoiding prompt injection. npx skills add browserbase/skills —skill browser

Browserbase

41,068 просмотров • 5 месяцев назад

Introducing LangSmith Fleet. Agents for every team. → Build agents with natural language → Share and control who can edit, run, or clone each agent → Manage authentication with agent identity → Approve actions with human-in-the-loop → Track and audit actions with tracing in LangSmith Observability Try Fleet:
1:06

Introducing LangSmith Fleet. Agents for every team. → Build agents with natural language → Share and control who can edit, run, or clone each agent → Manage authentication with agent identity → Approve actions with human-in-the-loop → Track and audit actions with tracing in LangSmith Observability Try Fleet:

LangChain

9,398,037 просмотров • 4 месяцев назад

Here's a sneak peak of what the new Gun audio sounds like! Stay tuned for the update! 🫡
0:26

Here's a sneak peak of what the new Gun audio sounds like! Stay tuned for the update! 🫡

Rust Console Edition

107,949 просмотров • 1 год назад

1X's launch video confirms its 'human-in-the-loop' strategy. For tasks NEO can't do autonomously, 'Expert Mode' lets a human operator 'supervise' and 'provide corrective intervention.' This is how they plan to gather training data.
0:39

1X's launch video confirms its 'human-in-the-loop' strategy. For tasks NEO can't do autonomously, 'Expert Mode' lets a human operator 'supervise' and 'provide corrective intervention.' This is how they plan to gather training data.

Humanoids daily

27,906 просмотров • 9 месяцев назад

we just shipped the ability for AI agents to launch their own tokens, own their own wallets, and pay for their own compute via bankrbot the agent earns its keep. no human in the loop live now. here's how it works ↓
0:39

we just shipped the ability for AI agents to launch their own tokens, own their own wallets, and pay for their own compute via bankrbot the agent earns its keep. no human in the loop live now. here's how it works ↓

InstaClaw

53,777 просмотров • 3 месяцев назад

Here's Operator from OpenAI building a Due Diligence portal for an M&A transaction of TikTok on Box. The Agent creates a folder structure, the initial set of docs, and then researches on the web for data. In the future, AI Agents just do work for you in the background.
1:58

Here's Operator from OpenAI building a Due Diligence portal for an M&A transaction of TikTok on Box. The Agent creates a folder structure, the initial set of docs, and then researches on the web for data. In the future, AI Agents just do work for you in the background.

Aaron Levie

196,150 просмотров • 1 год назад

did a simple explanation of the important players linked with openai for those out of the loop:
14:12

did a simple explanation of the important players linked with openai for those out of the loop:

Tyler Cosgrove

110,071 просмотров • 10 месяцев назад

JavaScript Iterator․zip landed in Firefox 148, making it simple to loop over multiple things at the same time. Here's how it works:
1:45

JavaScript Iterator․zip landed in Firefox 148, making it simple to loop over multiple things at the same time. Here's how it works:

Firefox for Web Developers

11,958 просмотров • 5 месяцев назад

Finally, a browser automation framework for Agents that actually works in production (open-source)! Typical browser automation tools like Selenium or Playwright require you to hard-code automation. These are brittle since one change in the website can disrupt the full workflow. On the other hand, high-level Agents like OpenAI Operator can be unpredictable in production. Stagehand is an open-source framework that bridges the gap between: - brittle traditional automation like Playwright, Selenium, etc. and - unpredictable full-agent solutions like OpenAI Operator. Key features: - Use AI when you want to navigate unfamiliar pages. - Use code (Playwright) when you know exactly what to do. - Preview AI actions before running them. - Cache repeatable actions to save tokens. - Compatible with SOTA computer use models with just one line of code. - Available in both Python and TypeScript SDK. Stagehand also has an open-source MCP server. Find a link to the repo in the comments! 👉 Over to you: Would you use this instead of Selenium?
0:24

Finally, a browser automation framework for Agents that actually works in production (open-source)! Typical browser automation tools like Selenium or Playwright require you to hard-code automation. These are brittle since one change in the website can disrupt the full workflow. On the other hand, high-level Agents like OpenAI Operator can be unpredictable in production. Stagehand is an open-source framework that bridges the gap between: - brittle traditional automation like Playwright, Selenium, etc. and - unpredictable full-agent solutions like OpenAI Operator. Key features: - Use AI when you want to navigate unfamiliar pages. - Use code (Playwright) when you know exactly what to do. - Preview AI actions before running them. - Cache repeatable actions to save tokens. - Compatible with SOTA computer use models with just one line of code. - Available in both Python and TypeScript SDK. Stagehand also has an open-source MCP server. Find a link to the repo in the comments! 👉 Over to you: Would you use this instead of Selenium?

Avi Chawla

101,419 просмотров • 1 год назад

Here's an exclusive first look at our new vision for the sim racing community, featuring a prototype sneak peak. 🏎️
1:37

Here's an exclusive first look at our new vision for the sim racing community, featuring a prototype sneak peak. 🏎️

CORSAIR

44,536 просмотров • 2 лет назад

Tower Defense RNG is releasing in October! Here's a sneak peak at some of the levels 🤯😎 #Roblox #RobloxDev
0:54

Tower Defense RNG is releasing in October! Here's a sneak peak at some of the levels 🤯😎 #Roblox #RobloxDev

Leif

19,544 просмотров • 1 год назад

#Twitchmas starts tomorrow! 🎁 Here's a sneak peak at some of the items - and don't forget to connect your accounts! #Rust10
0:26

#Twitchmas starts tomorrow! 🎁 Here's a sneak peak at some of the items - and don't forget to connect your accounts! #Rust10

Rust

248,897 просмотров • 2 лет назад

Agents In Actions! Check out a demo video of one of our $AGENTS. Each agent is designed to be modular, meaning that you can plug and play things like accounts, apis, and more! V1 of Agents (﹢,﹢) is awaiting release, enjoy the sneak peak 🤖
0:33

Agents In Actions! Check out a demo video of one of our $AGENTS. Each agent is designed to be modular, meaning that you can plug and play things like accounts, apis, and more! V1 of Agents (﹢,﹢) is awaiting release, enjoy the sneak peak 🤖

Agents (﹢,﹢)

23,649 просмотров • 1 год назад