Github Copilot Workspace might be the Future of AI-powered software engineering
Github is proving to be a genius acquisition by Microsoft.
Hello Everyone,
On the coding front there has been a significant development. Microsoft is extremely smart with how it’s pushed GitHub Copilot to evolve, the original copilot you might even say.
There next act here strikes me as very smart. What are people on Hacker News saying.
What is Copilot Workspace?
GitHub Copilot Workspace leverages AI developer tools to streamline complex tasks across your entire repo, enhancing developer productivity and making coding faster and smarter. Ideal for navigating unfamiliar programming languages or frameworks, Copilot Workspace acts as a cloud IDE companion, deeply integrated with your project. As your ultimate coding partner, it excels in repo-wide edits and fosters programming collaboration. Whether addressing GitHub Issues or optimizing your task-centric workflow, Copilot Workspace is designed to improve your coding efficiency through its AI-generated code capabilities.
Read the Technical Preview:
Video Promo
Want to explore what was shown in the video?
Check out the repo:
https://github.com/octocademy/utils-library…
Check out the PR:
https://github.com/octocademy/utils-library/pull/7…
I’m not very bullish on productivity boosts for most workers with Copilot, but this is one of them where I am bullish because of how scalable this can be over time as the AI gets better and efficiency is increased for fairly important tasks for Engineering departments all over the world in a wide range of companies and industries.
A Copilot-native dev environment, designed for everyday tasks.
Microsoft Earnings Shows Github is a Winner
During the fiscal third quarter, Microsoft’s Intelligent Cloud segment, including the Azure public cloud, Windows Server, Nuance and GitHub, generated $26.71 billion in revenue. That’s up about 21% and more than the $26.26 billion consensus among analysts surveyed by StreetAccount.
We can assume Github Copilot revenue is doing fairly well and will only get better as the one original Copilot in my mind.
How to Use
Jonathan Carter, head of GitHub Next, GitHub’s software R&D team, pitches Workspace as “somewhat of an evolution of GitHub’s AI-powered coding assistant Copilot into a more general tool, building on recently introduced capabilities like Copilot Chat, which lets developers ask questions about code in natural language.”
Saving Software Engineers Time
Workspace in theory will save engineers time, and who doesn’t like that idea?
Copilot Workspace from what I can tell is a new service that aims to cut down the time engineers and developers spend reading through code and figuring out how to start on a new project. Workspace will only be available in technical preview for a waitlist of developers, but it will be integrated into the larger GitHub Copilot platform after it exits preview.
The Inside Scoop
“Through research, we found that, for many tasks, the biggest point of friction for developers was in getting started, and in particular knowing how to approach a [coding] problem, knowing which files to edit and knowing how to consider multiple solutions and their trade-offs,” Carter said. “So we wanted to build an AI assistant that could meet developers at the inception of an idea or task, reduce the activation energy needed to begin and then collaborate with them on making the necessary edits across the entire corebase.”
What is the Upper Limit of Copilot Workspace?
GitHub wrote in a blog post that Copilot Workspace will be integrated into GitHub repositories or libraries.
Developers can describe to Copilot Workspace, through prompts, what they want to do for the project.
At last count, Copilot had over 1.8 million paying individual and 50,000 enterprise customers. But Carter envisions a far larger base, drawn in by feature expansions with broad appeal, like Workspace.
I’d say the ceiling is pretty high.
Here is why this appears to be the case:
“Since developers spend a lot of their time working on [coding issues], we believe we can help empower developers every day through a ‘thought partnership’ with AI,” Carter said. “You can think of Copilot Workspace as a companion experience and dev environment that complements existing tools and workflows and enables simplifying a class of developer tasks … We believe there’s a lot of value that can be delivered in an AI-native developer environment that isn’t constrained by existing workflows.”
What does it Do?
Copilot Workspace will then offer suggestions on how to start and provide a step-by-step process. Users can edit the suggestions and, once they’re satisfied with the suggestions, run the code (or even use Copilot to help complete the code) and finish the project.
The space is filled with competition.
The cost is high. Copilot loses an average of $20 a month per user, according to a Wall Street Journal report, with some customers costing GitHub as much as $80 a month.
Microsoft is betting the Moon on Copilots, in a hail mary on AI that is likely to end badly as more and better competition arises. I however have a fair degree of faith in Github Copilot and Github Copilot Workspace as being among their best Copilots at scale. With enough adoption I’m fairly sure it can be profitable.
It’s a far better investment than say, wearables, the Metaverse or even grocery delivery. No offense to Meta or Amazon.