Although Microsoft’s 2023 Build conference covered a variety of topics, the company left no doubt about its priorities. Microsoft focused the bulk of the conference on its new Copilot technology.
Copilot can be described as a large language model (LLM) chatbot coupled with an automation engine. In other words, it enables users to input ChatGPT-like queries to prompt the underlying application to perform tasks. For example, Microsoft 365 Copilot lets users request summaries of meetings, plan parties, or create PowerPoint presentations based on the contents of Word documents.
A notable feature of Microsoft 365 Copilot is its ability to generate content in different styles. Users can instruct Copilot to make a paragraph more formal or change the style of a PowerPoint presentation to be fun and festive.
It’s important to note that while I used Microsoft 365 to illustrate what Copilot can do, Copilot is not limited to Microsoft 365. Microsoft is developing Copilots for Windows, the Edge browser, and other applications. The company is even working on a Copilot focused on security, aimed at helping organizations improve their security posture.
Among the many Copilot-related announcements made at Build 2023, two stood out as particularly profound.
Edge Copilot Will Transform Web Browsing
One of the significant announcements was the development of a Copilot for Microsoft Edge. There are two compelling reasons why a browser Copilot holds importance.
Firstly, the Edge Copilot will bring ChatGPT-like functionality to current information. A major drawback of using ChatGPT today is its limited information about events occurring after 2021. As such, ChatGPT usually isn’t the best tool for gathering information on the latest technologies or events. However, the Edge Copilot will have access to the same up-to-date data as the Edge browser, enabling it to use information from webpages regardless of when the page was created, be it five years ago or 20 minutes ago.
This leads to the second reason why Edge Copilot matters. While ChatGPT is often used as an alternative to traditional search engines, the Edge Copilot is not designed to replace a search engine (although Microsoft has created a Bing-ChatGPT mashup for web search). Instead, the Edge Copilot aims to help users digest and use the information they find on the webpage they are currently viewing. For instance, users can ask the Edge Copilot to summarize the key points of a page.
Microsoft executive Yusuf Mehdi demonstrates Edge Copilot at Build 2023
In a demo at the Build conference, Microsoft executive Yusuf Mehdi opened the Edge browser to a page containing a recipe and asked Copilot to list the recipe’s ingredients and add them to Instacart. The demo illustrated Edge Copilot’s ability to analyze webpage contents (in this case, identifying recipe ingredients) and work with extensions (adding the ingredients to Instacart). My guess is that Edge Copilot will continue to enhance the usefulness of the browser in the future.
Copilot SDK Will Transform Software Development
The other Copilot-related announcement that caught my attention was Microsoft’s plan to release the Copilot SDK to the public, allowing third-party developers to build their own Copilots. As more developers embrace this technology, I anticipate that working with Copilot will become increasingly accessible.
To illustrate the potential impact, let me share an example from my personal experience. Last year, I used a popular CAD program to create a 3D model of my home. I wanted to undertake a home improvement project and ensure its feasibility before purchasing materials. The 3D model let me explore various options before committing to the project.
As useful as my CAD model was, creating it was no small task. I encountered numerous instances where I made mistakes and had to painstakingly backtrack to make corrections. There were also times when I struggled to find solutions and had to watch many YouTube tutorials.
Now, imagine if the CAD software had contained a Copilot. I could have used the Copilot to assist me with the more technically complex aspects of my project. For example, instead of manually adjusting the height of my living room ceiling, I could have simply asked Copilot to raise the ceiling by four feet.
Copilot has enormous potential to simplify how we interact with complex applications. However, there is another potential use case that I have yet to hear anyone discuss. As previously mentioned, Copilot combines an LLM chatbot with an automation engine. Consider the possibilities if multiple developers collaborated to create cross-product Copilots. Suppose a video editing software company partnered with the aforementioned CAD software company. With a complete CAD drawing, Copilot could be used to instruct the software to generate a 3D walkthrough, export the walkthrough to the video editing software, add background music and color grading, and export the final video as a 4K MPG file.
Ultimately, the specific uses and the companies that will develop Copilots remain to be seen. Nevertheless, I believe that Copilot has the potential to revolutionize the way we use software.
