Microsoft has quietly launched an updated Spotlight-like launcher app for Windows that provides quick access to commands, apps, and development tools. The software maker originally launched its PowerToys Run launcher for Windows 10 nearly five years ago, and the updated version — Command Palette — now includes search for apps, folders, and files, calculations, system commands, and much more.

Command Palette is available for any Windows user from the PowerToys app, but it looks like Microsoft is now targeting this particular utility at power users and developers. You use Command Palette to access Windows commands or launch command prompts and shell shortcuts. Command Palette also has the ability to quickly open websites, web searches, and search through folders and files like you’d expect from a Spotlight- or -Alfred-like interface.

Microsoft has also moved its previous Window Walker PowerToy into Command Palette so you can easily switch between open windows. The most interesting part about Command Palette is that Microsoft has made it fully customizable thanks to extensions support so you can add additional commands and features beyond what’s available by default.

The PowerToys Command Palette has been available since early April, and you can activate it using the Win+Alt+Space shortcut once it’s installed. Microsoft says “Command Palette is intended to be the successor of PowerToys Run,” but both are still available for now. Microsoft made some tweaks and changes to Command Palette this week ahead of its Build developer conference on May 19th.

GitHub first introduced its now ubiquitous Copilot back in 2021. At the time, the Microsoft-owned company described it as “a new AI pair programmer that helps you write better code.” That overall mission of augmenting developers and using AI to do away with much of the day-to-day busy work hasn’t changed. But as GitHub CPO Mario Rodriguez told me during an interview on the sidelines of Google’s Cloud Next conference in Las Vegas earlier this month, the company is now squarely in phase two of the Copilot project.

“We named this Copilot for a reason,” he said. “The idea was, hey, the human is at the center, and we’re going to go and augment this human with the power of Copilot to take out the toil, help them code faster, increase productivity, all of those things. And I think wave one of that strategy played out over two plus years — and we’ve been very successful at that.” 

In a separate interview, shortly after Microsoft announced its latest quarterly earnings, GitHub CEO Thomas Dohmke noted that Copilot now has 15 million users, a number that is in part driven by GitHub opening up the free Copilot tier late last year.

2025: The Year of SWE Agents

Almost exactly a year ago, GitHub launched Workspace, its take on letting developers code with natural language — long before “vibe coding” entered the mainstream. Rodriguez admits that GitHub may have been a bit too early with this, but he also clearly believes that this is where things are going, with a large dose of AI agents added to the mix.

In February of this year, GitHub announced Project Padawan, Copilot’s autonomous SWE agent, which in many ways takes the Workspace concept to the next level. 

“We’re now entering, in my opinion, wave two of this — the next is kind of the next evolution of what software development will be,” Rodriguez said. “This next evolution is all about agent tech, in our opinion, and it’s really taking two modalities — synchronous, by which I mean VS Code or any other tool, and be able then to use these agents to augment me. But now, through natural language, I could tell it, ‘Go, do this,’ and the agent will figure out all of the steps on it.”

This, he said, is what Project Padawan is all about. The idea here is for the system to be able to tackle multiple GitHub issues in parallel, for example, by assigning multiple issues to the agent — something an individual developer couldn’t do.

“I think it’s fair to say 2025 is the year of the SWE agent, where for more and more tasks, the developer can either synchronously or asynchronously work with an agent,” Dohmke said.

Peer Programming

Currently, in VS Code, the agent mode handles the synchronous tasks, which Dohmke likened to working with a pair programmer, as it’s essentially a back and forth between the Copilot and the developer.

The original Copilot, Dohmke noted, was mostly a tool for pair programming with the AI model.

“I think the original Copilot, first with autocompletion, then with chat, solved that scenario, and Agent Mode extends it to a degree where you are effectively handing the keyboard to the other person, have them write for a while, but you’re still in charge from [the perspective of] how the roles are within the pair,” Dohmke said.

But with Project Padawan, that now changes. Dohmke noted how most developers work in teams, and how they have peers within those teams that they communicate with throughout the day, while the manager (or Scrum master) assigns work. Once you bring SWE agents into the loop, the developer becomes a peer of multiple agentic developers, Dohmke believes. Those agentic developers may even work together with a site reliability engineering (SRE) agent, for example, who monitors the health of a company’s infrastructure and then assigns GitHub issues to the SWE agent when things go awry.

“That’s the peer programmer, where you basically become peers with a group of agents, or, as I like to call it, the orchestra of agents,” Dohmke said. “Now, they’re all still working on the behalf of a human developer, right? That’s the conductor of the orchestra, because at the end of the day, these agents still need to get their work assigned to them, and at the end of the process, somebody needs to review that.”

Right now, Rodriguez said, the team is fully focused on executing on this agent vision, which has in part become possible because the models themselves have become so much more sophisticated since GitHub first demoed Workspace. Rodriguez noted, for example, that in the early days of Workspace, GitHub — and the user — were handling the planning stages. But now, with the models having become so much better at planning themselves and also having the ability to call tools, the models themselves can handle most of this. 

“Now these models can go and pick the right tools a lot better than before. There’s still more that needs to happen there, but once you get something that is very good at planning, very good at picking the right tools, and then they continue to get better at code writing and understanding — once you’ve got those three components, you could unlock things that didn’t exist before,” he said.

That’s where Copilot’s recently launched Agent Mode comes in. It can create apps from scratch or help developers debug, refactor or extend their existing applications. (It can create documentation, too.)

With Microsoft’s annual Build conference right around the corner, chances are we’ll hear more about the state of Project Padowan in the coming days.

Copilot Competitors 

Obviously, GitHub isn’t the only company in this game and even though it was among the first to launch AI code completion tools, companies like Cursor, replit, Windsurf and others may almost have as much mindshare today as GitHub has in this space. 

“I think the place where we will shine, it’s on context,” Rodriguez said. “If you pass the model the right context, the model does a pretty good job. If you pass the model the wrong context, it does not.” 

For GitHub, this context isn’t just the code but also what it knows about how people on a team collaborate. “We already inherently have essentially a people graph and a work graph as well. So the combination of this code graph, people graph, and then, as we expand into the application graph as well, I think it’s going to give us a way to have context, and it’ll be really interesting to try to see what Copilot can do with that,” he said.

Rodriguez also notes that he isn’t worried about competitors. “I think that’s a healthy thing for humanity. That’s the normal modus operandi of being in this space. And I think the North Star for Thomas [Dohmke] and I going through this is: can we create the best product? And if we create the best product that is solving the customer needs, then that is success for us and that’s what we continue to be obsessed about.“ 

The fact that Copilot is also available inside all of the popular IDEs, as well as GitHub.com itself, is another area where Rodriguez believes the company has a major advantage.

How To Price a More Advanced Copilot?

In the early days, Copilot set the baseline for how to charge for a service like this by going with a $10/month flat fee. Over time, it added additional tiers, but earlier this year, when it made a number of higher-end models available in Copilot, it switched things up a bit by putting a limit on “premium model requests.” For these, users will receive a limited allotment of requests (300/month for Pro users and 1,500/month for those on the new $39/month Pro+ plan). Additional requests will cost $0.04 per request.

“That’s one way that we’re going,” Rodriguez said about these changes. “That is mainly to support this synchronous Agent Mode and asynchronous Agent Mode as well. So I think that’s kind of a direction we’re going. […] We always take a look at how we should evolve our business model, and where is it that we want to evolve it, and how we want to evolve it, and all those things. Right now, that’s where we’re going. There’s a license and then a consumption model past that.”

What Will Software Development Look Like in a Few Years?

GitHub and its executives often talk about how they want to get to a billion users and make programming available to virtually anyone. Like its competitors, the way the company plans to get there is by using natural language, with the large language model (LLM) as an intermediary between the request and the actual code. 

“We took a big bet on natural language in 2021,” Rodriguez said, “The beauty of Copilot at the very beginning, by the way, was not that it could go ahead and write some code. IntelliSense already could do that at that moment and autocomplete things. The thing that blew me away in 2021 was the fact that you could have a comment, type something in the comment, and the machine understood it and then was able to write something big after that. I had never seen that in my life, with that level of accuracy — and it wasn’t highly accurate, maybe 15 or 20 percent — but no MLOps pipeline ever had done that. So I think natural language is the unlock.

“The thing that needs to keep up is human interfaces to be able to then unlock what you want to get done,” he added. “The cool thing also about natural language is you could speak in your native language and accomplish things in your native language, which in programming, that hasn’t been the case.”

Rodriguez does not seem all that worried about what this means for the overall coding skills, especially for junior developers. 

“I think for us, what needs to happen is more of a redefinition of what a software developer is, and this is why it’s 1 billion for us,” he said. ”If you think about it, the IDE today is this thing called professional developers, which I think limits the acceleration of human progress. In my opinion, you should go and look at what happens if 10% of the world population can become software developers?”

But what happens when these developers can’t read and understand the code that the models wrote for them? Rodriguez believes that may be a short-term problem, but “what is reading the code in the future, like, 100 years?” he asked. “And why does it need to be so static? […] I think you do have to bet on humanity and there will be an evolution.”

When I asked Dohmke a similar question, he offered a similar answer, but also added that in his view, the difference between junior and senior developers is not the amount of code they’re writing, but the quality of that code. And while models will likely only get better at coding over time — and may hence become more akin to senior developers themselves in some ways — they will likely continue to lack in some aspects.

“I think, fundamentally, they’re lacking what I would call craft,” he said. “And as such, they cannot actually replace the real senior developer. They’re always going to be an assistant, a helper to the senior developer that is still in charge, flying the plane or driving the software life cycle.”

The post GitHub Copilot Wants To Become Your Peer Programmer appeared first on The New Stack.

The post Microsoft proposes commitments to resolve European competition concerns about Teams appeared first on Microsoft On the Issues.

Explore the fundamentals of Node.js streams for efficient I/O operations. Learn how readable, writable, and transform streams work with practical examples of data handling, piping, and backpressure management in this comprehensive guide.

Continue reading The Basics of Node.js Streams on SitePoint.

Streamline your day with new, user-focused updates to Microsoft 365 Copilot. Jump into work faster with a redesigned layout that puts Chat, Search, and your agents front and center. New Copilot Search lets you yse natural language to find files, emails, and conversations — even if you don’t remember exact keywords — and get instant summaries and previews without switching apps.

Create high-impact visuals, documents, and videos in seconds with the new Copilot Create experience, complete with support for brand templates. Tap into powerful agents like Researcher and Analyst to handle deep tasks or build your own with ease. And if you manage Copilot across your organization, you now have better tools to deploy, monitor, and secure AI use — all from a single view.

Describe what you want.

Don’t know the keywords to find your content in Microsoft 365? You don’t need to. See how the new Copilot Search works.

On-demand expertise.

Use agents like Researcher or Analyst to do the thinking for you. Start here.

View AI agent activities in Microsoft Purview.

Find data security policy matches and see if agents are being used with sensitive information or by risky users. Watch here.

Watch our video here.

QUICK LINKS:

00:00 — Microsoft 365 Copilot new capabilities

00:36 — Microsoft 365 Copilot app

01:49 — Copilot Search

03:09 — Specialized agents

04:06 — Create experience

06:07 — Copilot Notebooks

07:40 — Updates for IT admins

08:16 — Data security with AI apps & agents in Purview

08:51 — Reports

09:20 — Wrap up

Link References

Check out https://aka.ms/CopilotWave2Spring

Unfamiliar with Microsoft Mechanics?

As Microsoft’s official video series for IT, you can watch and share valuable content and demos of current and upcoming tech from the people who build it at Microsoft.

• Subscribe to our YouTube: https://www.youtube.com/c/MicrosoftMechanicsSeries
• Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog
• Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast

Keep getting this insider knowledge, join us on social:

• Follow us on Twitter: https://twitter.com/MSFTMechanics
• Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/
• Enjoy us on Instagram: https://www.instagram.com/msftmechanics/
• Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics

Video Transcript:

-So, Microsoft 365 Copilot keeps getting better, and today I’ll show you how the Copilot experience is evolving to make everything easier with new AI-powered capabilities to help you get even more done, and if you’re an IT, I’ll show you new options for agent management, including updates in the Microsoft 365 Admin Center, new data security views and controls, and Microsoft Purview’s Data Security Posture Management for AI, as well as improved reporting and visibility into Copilot analytics from Viva Insights. So let’s start with updates to the Microsoft 365 Copilot app experience, which has evolved to make every interaction easier and more intuitive. Chat is the core of the experience and where you’ll find the app by default and there’s a new navigation moving what’s important to the left side of your screen where you’ll find links to Search, Chat, your Agents, new Notebooks, and Create experiences that I’ll show you in a moment.

-Now moving to the center of the app, you’ll notice that there’s a more streamlined view with the prompt box taking center stage. Under that, you’ll find personalized suggestions for what to do next, including upcoming meetings. And as the author prompts, you can quickly pull up an agent right from here to bring in content sources you want like your files, interactions with people, your meetings, emails and more to generate what you want. And even without referencing your work directly, Copilot is connected to it and can find the matching information that you have access to. That’s because behind the scenes, Microsoft 365 Copilot uses advanced AI native vector-based search to find the most relevant content. And now outside of Copilot Chat, you can use this directly from the new Copilot Search experience. It brings together AI search and your work information across Microsoft Graph.

-From here, you can easily get to your recommendations and quick access to what you’ve been working on. Then moving to the search bar, you’ll see that search now goes way beyond keyword search that you’re used to compared to Copilot Chat. This is optimized to find specific content items. Now, where you can ask in simple terms, for example, based on what you remember, to quickly find your files, your emails, chats, and meetings for Microsoft 365, and even information and other graph connected line of business systems like you’re seeing here with Jira. Now it knows like-concepts, synonyms, and contextual information around a topic, so you don’t need to know keywords or be precise with search terms. In fact, many of these results don’t contain words from the search, but they’re highly relevant. And based on the top items and the results, Copilot can summarize what search finds in line to save you time. And without having to open its sighted items in separate apps, Copilot will also help summarize and preview those files right from the Copilot app.

-Next, we’ve made it easier to access specialized agents, which give you on-demand help to complete tasks that would normally require an expert. Now these include both Analyst to find insights in your data as well as Researcher for written reports, both first-of-their-kind reasoning agents for work. In fact, we dedicated an entire show on reasoning agents that you can check out at aka.ms/reasoningmechanics. And here in the navigation you’ll also find your pinned and recently used agents on top. And clicking into all agents takes you to the new agent store where you can find more agents that are built by Microsoft, also the broader ecosystem, and your company’s own custom agents. And of course, you can also create your own agents right from here by describing what you want your agent to do or configuring it directly with your instructions and knowledge sources.

-Then beyond agents and AI-generated content from Copilot Chat, the new create experience lets everyone tap into powerful and personalized design skills where you can create images like the samples you’re seeing on the screen here, powered by the GPT 4o Model for image generation. And you can design a poster or flyer like these ones and they’re also great for cover pages to your reports. And speaking of that, from Create, you can write a stylized draft document using templates and right from here, you can also upload and edit your own images to make them stand out and select parts of images to remove distractions like this tree. Importantly, what sets the Create experience really apart is that you can use brand templates and even bring in your company’s brand kit, and these include your approved company logos, fonts, and colors. In fact, let me show you how this works by creating a new image.

-So I’ll start by describing what I’m looking for. I’ll choose a picture of this new shoe from my local device to work from, and now I’ll choose my style that matches what I want to create. Here’s where my company brand comes in. I can choose the brand kit I want with the right color palette and icon. Now this will take a moment to generate and now I have an image that fits my brand and I can add to this same image. I’d like to see a little ground cover in the image. I’d like to ask for some moss and some rocks. Then I’ll give it a second to render a new image and it gets even better with new direct editing options like background removal, object transform, and enhancements. I’m going to choose the erase option, then select this rock and this plant on the right and hit erase. That’s better. Now, I just need to add a text element and I’ll paste in the shoe name and now it’s ready to go and I can download the image right from here.

-And for your bigger projects and tasks, Copilot Notebooks is then another new capability. These help you bring together all of your relevant content for your task at hand, including Copilot Chats. And I’ll open this one for Copilot Craft and you’ll see that I can chat with Copilot about everything in here, and it’s filled with reference content and related chat history to keep interactions in scope to what’s here and even create an audio overview of this notebook. Now the last major update that I’ll show from the Microsoft 365 Copilot app experience is with personalization and memory. Where from Copilot settings, you can specify custom instructions and enable Copilot memory.

-First, custom instructions let you add details about your interests, your preferences, the tone of what you expect from Copilot responses. Think of this information as something that will get appended to your initial prompts in future Copilot sessions to improve its output. Then, moving back to personalization settings, Copilot memory works in the same way to recall a handful of notable memorable items from previous conversations in real time. Again, this information sits outside of the large language model and is retrieved for future chat sessions. And you have full visibility and control over what is maintained in Copilot memory and can delete what you don’t want to personalize its responses.

-Next, I’ll move on to updates for IT admins. We’re adding more controls to the Copilot Control System so that you have the tools that you need to manage, govern, and measure Copilot and now also agents across your organization. You can now manage the agents and agent deployment right from Microsoft 365’s admin center. Here you’ll see a list of agents in use and the ones you’ve blocked. Also, apps where the agents are supported and usage details. You can also deploy agents from here as well, scoping the right users and groups.

-Next, we’re also adding more insights and controls for data security with AI apps and agents and Microsoft Purview. The new AI apps and agents page in Data Security Posture Management for AI gives you a single dashboard to view and create policies for your AI apps and agents, where you’ll find coverage for data protection and compliance policies that you already have in place, and clicking into any of these items, lets you discover more insights, including potentially risky interactions, inappropriate use, as well as sensitive information being shared.

-And finally, for reports that you can share beyond your administrator and data security teams, using Copilot Analytics and Viva Insights, you can measure the usage and business impact of your agents. And direct from Viva Insights, the new Copilot Studio agents report can be shared with your team, and it provides a comprehensive view of agent use, session outcomes, and you can see how assisted actions are contributing to overall ROI.

-So Microsoft 365 Copilot continues to evolve to help you get more done, along with enterprise grade IT controls to help keep your data protected. Now, to find out more, check out aka.ms/CopilotWave2Spring and keep checking back to Microsoft Mechanics for the latest updates. Thanks so much for watching.

 

Spotlight

• Learn how you can build advanced agents for Microsoft 365 Copilot by leveraging the Microsoft 365 Agents SDK. Join the session
   
• Get an in-depth look at building agents in Copilot Studio, with a special focus on the latest innovations and what's ahead. Add to schedule
• Discover how you can add more knowledge to Microsoft 365 Copilot with Copilot connectors and actions. See more details
• From Copilot Studio to Visual Studio and Azure AI Foundry, join this session to discover the various ways you can build agents for Microsoft 365. Register now

Learn

• Explore how to build Microsoft Teams collaborative agents as virtual colleagues with Visual Studio Code. Sign up
• Join us for a session on building advanced copilot Studio agents by integrating Azure AI Search, the Azure model catalog, and Model-Context Protocol (MCP) into your agents. Learn more
• Build task -specific declarative agents for Microsoft 365 Copilot using advanced recipes in Copilot Studio. View session
• See how you can build agent in Copilot Studio with deep integration into Azure AI Foundry services. Explore more
• Tune into this breakout session to learn how to build declarative agents for Microsoft 365 Copilot. Save to favorites

Keep up to date

• Microsoft build labs- Learn how to use all of the latest dev tools in our hands-on labs. Sign up
• Updated Teams AI library- Create even more powerful agents for Microsoft Teams. Read how
• LinkedIn- Get the lates news, product announcements, demos and more Follow us
• Community calls- Learn from our experts on a variety of Microsoft 365 platform topics. Join a call