How People Are Using AI For Browser Productivity

Today we’re introducing Copilot Mode in Edge, our first step in reinventing the browser for the AI age. My favorite feature is multi-tab RAG. You can use Copilot to analyze your open tabs, like I do here with papers our team has published in @Nature journals over the last year. And there is a lot more to come, including built-in actions so you can delegate tasks as you browse.

ChatGPT can now do work for you using its own computer. Introducing ChatGPT agent—a unified agentic system combining Operator’s action-taking remote browser, deep research’s web synthesis, and ChatGPT’s conversational strengths. https://t.co/7uN2Nc6nBQ

I have connected with hundreds of investors over the last 7 years. All rejected because of hardware. That’s why I took a different path today with Nimo Infinity. Nimo did all these in few minutes. Soon this Canvas will be your AI Office 🎉 1. Find all the investors I’ve connected with from Google Calendar. Analyze them, identify the best fit for Nimo Infinity, and add them to a Google Sheet. 2. Summarize my last conversations with those investors and update the sheet. 3. Send personalized emails to all investors. Saved me days of effort by finding, analyzing, organizing, and emailing 132 right investors.

Movies + Perplexity + Comet = Magic Searching for movies and TV shows on @perplexity_ai just got WAY more fun with posters, trailers, ratings, and more. @PerplexityComet will even order popcorn for you. 🍿 https://t.co/lnoLUuZXGv

wdyt of this @googlechrome ? on comet: you can just close tabs on voice mode :-) looking forward to what you will ship soon https://t.co/uvJcfKw6MR

Browse at the speed of thought. https://t.co/vDqWr3r0kO

A new agentic browser just shipped from Perplexity and it's pretty wild. Watch this video of @PerplexityComet taking over my LinkedIn tab and taking actions on my part. Interesting UX where the tab glows blue as it's taking actions. I like the integration of agentic actions right inside the browser that I'm using versus having to fire off an @OpenAI Operator request.

I loved @arcinternet! I still do. But yesterday, I switched to @diabrowser—and now it's my default browser. @danshipper's conversation with the cofounders of @browsercompany convinced me to make the change—it's the very honest, very real inside story of their pivot into building the browser of the future. After writing a piece about the podcast, I had to try it out! And it genuinely feels like magic! - You can ask the 3-hour YouTube video you're watching at 1.5x the exact questions you care about—and get answers, complete with references to timestamps. - You can ask the 10 open tabs about tennis classes, “Which one has coaching slots in the morning?” - If you're hovering over an email thread with a potential lead, wondering if you should follow up, you can ask Dia that too. It'll read the thread and give you a thoughtful recommendation. Give it a try (or join the waitlist) if you haven't already:)

This makes the future way closer than you think. Director AI automates any tasks you can do in a browser. It interacts with web pages just like a person would. If you could use a browser to complete a task, you can have this AI do it for you. And it's free! Watch the video: https://t.co/IJSOtGItJO

Today's THE day, Folks! 🥁🥁🥁 https://t.co/iKbRNEoXMm is LIVE! I was lucky to beta test it, easily the most capable AI web agent I’ve used!🔥 Built on Stagehand (100% open source), it turns natural language into flawless browser automation. FREE & zero coding needed! 🧵 ↓ https://t.co/TnA6C83vez

Real-time web access for AI agents. This is pretty awesome! Building agents that can do things on our behalf using a web browser will be a multi-billion-dollar business. Here is how you can do it: 1. Go to Browserbase 2. Set up a headless browser 3. Use their API to control it Check it out here: https://t.co/msMjbZk2Kx This works with CrewAI and Langchain, and scales as much as you need. It doesn't get simpler than this!

Today we're excited to introduce Vy, our AI that sees and acts on your computer. At Vercept, our mission is to reinvent how humans use computers–enabling you to accomplish orders of magnitude more than what you can do today. Vy is a first glimpse at AI that sees and uses your computer just like you do. It runs natively on your computer, with access to all your applications and accounts that you’re already signed into. It is available for download starting today! As part of the release, we’ve built VyUI, an AI model bridging the gap between language and your screen. It sets a new state-of-the-art on UI grounding benchmarks like ScreenSpot v1, ScreenSpot v2, and GroundUI Web–beating leading models from OpenAI, Google, and Anthropic. Check out what Vy can do in the thread below: 🧵👇