Skip to main content

Microsoft Copilot gets an AI agent to browse the web for you

Launching a search with Microsoft Copilot Actions.
Microsoft

Microsoft’s 50th anniversary event was quite loaded, but the company reserved most of its attention for the Copilot AI stack. The buzzy event introduced two crucial upgrades – Actions and Deep Research — which firmly push Copilot into the realm of agentic AI.

Agentic AI is essentially a fancy way of describing an AI tool that can perform multi-step web-based tasks autonomously, or semi-autonomously, on your behalf. In Copilot’s case, the fancier one is Actions. So far, AI chatbots have mostly been able to give answers based on a certain input, but haven’t been able to perform autonomous multi-stage actions.

Recommended Videos

Microsoft says Actions can book “event tickets, grab dinner reservations or send a thoughtful gift to a friend and it will check that task off your list.” The core idea is that instead of having users visit a website and use a combination of clicks and keyboard typing, they can just tell Copilot to do it as a natural language command.

For example, you can ask Copilot to find a list of nearby restaurants that open late into the night, and book a table at the one you like the most, from within the search results. Copilot will do it all by browsing the web, filling in the necessary details, and occasionally asking for input wherever necessary.

Microsoft says it has joined hands with 1-800-Flowers.com, Booking.com, Expedia, Kayak, OpenTable, Priceline, Tripadvisor, Skyscanner, Viator and Vrbo for Copilot actions to get the job done on behalf of users.

Microsoft won’t be the first to launch a browser-based AI agent for handling cores. It’s actually late to the party. OpenAI’s Operator has been available for a while now, and it can accomplish more or less the same chores as Copilot Actions.

Amazon has a similar system in development called Nova Act, built atop its Nova AI model platform, to perform tasks such as ordering food or replenishing supplies. The inherent tech has already been implemented at the heart of its new Alexa+ assistant.

The e-commerce giant has also started public testing of another agent-based AI feature within its mobile app, which can buy items from other retailers’ websites. Even the folks behind Opera browser are working on their AI operator to get basic internet-based tasks done.

Nadeem Sarwar
Nadeem is a tech and science journalist who started reading about cool smartphone tech out of curiosity and soon started…
Exclusive: Copilot’s native Spanish is a ‘game changer,’ says Microsoft expert
Lenovo Yoga laptop with Copilot button visible.

AI brands continue to promise more uniform and human-like experiences for their products, and Microsoft is no different. The brand is working to make the features of its AI assistant more cohesive with the everyday world. This includes a more authentic Spanish language voice for its Copilot product. The company rolled out its Copilot Voice feature last October, which it will soon update with native Spanish speaking-voices to cater to the Latino community in the U.S. and globally. 

Enter Elm and Alder, Copilot’s native Spanish voices. The AI can detect when Spanish is being spoken and respond seamlessly in fluent Spanish with a native accent. Similarly, it expresses a native accent while speaking English in the Spanish setting. I spoke with a Microsoft product expert to explore the process behind developing the new voices and the intent behind providing this unique language and cultural representation within Microsoft's AI suite.

Read more
Kagi’s AI search assistant gives you access to all the big models in one place
Kagi search bar in light mode.

Kagi's "Assistant" feature, previously only available to Ultimate subscribers, is now rolling out to all tiers -- including the free trial tier. The feature gives you access to a range of different LLMs for both chatting and web-searching purposes.

If you don't know much about Kagi, it's a paid search engine that borrows its name from the Japanese word for "key." The concept is simple -- with Google, you pay for the service by allowing ads and data collection. With Kagi, you pay for the service with money to get a private and ad-free experience.

Read more
Microsoft’s Copilot Vision AI is now free to use in Edge
Copilot Vision graphic.

After months of teasers, previews, and select rollouts, Microsoft's Copilot Vision is now available to try for all Edge users in the U.S. The flashy new AI tool is designed to watch your screen as you browse so you can ask it various questions about what you're doing and get useful context-appropriate responses.

The feature works for "most" sites, according to Microsoft but it gives you a list of recommendations to start with. We have Amazon, which makes sense, but also Geoguessr? I'm pretty sure the point of that site is to try and guess where you are on the map without any help. Anyway, the full list of starter sites is as follows:

Read more