Skip to main content

GitHub Copilot Agent mode (Preview)

Agents are the next big thing in GenAI and with the introduction of Agent mode last week, agentic AI are now coming to GitHub Copilot as well.

In agent mode, Copilot can reason and iterate on its own code. It can automatically infer and execute subtasks needed to complete the main task you requested.

At the moment of writing this post, the new agent mode is still in preview. So you need to download the VS Code Insiders version available here: Download Visual Studio Code Insiders

Once the installation has completed, you can active the agent mode through the Copilot settings:

  • Go to File –> Preferences –> Settings:

 

  • Search for ‘chat agent’ and make sure that the Agent mode checkbox is checked:

OK, we are good to go.

  • Open the Copilot Chat window and switch to the Edits view:

 

  • At the bottom of the Edits view, switch from the Edit mode to the Agent mode:
  • Similar to Copilot edits mode, we select the files that should be included in the working set. Now we can ask the agent to do his work:

 

  • It can take some time before the agent is ready so be patient. After a while the agent is done with his changes. Now we can verify and accept the changes (if they are ok) or discard them:

 

  • In this case the agent made some mistakes, so I ask the agent to try again:

 

  • Unfortunately, still some mistakes. I switched to Claude Sonnet and gave an extra hint on what’s missing:

 

  • It seems that Claude Sonnet did a better job and finally got the result I wanted.

 

That’s enough for a first try of the new agent mode. I’ll try in on some other scenario’s in the future…

Also have a look at the following video (the agent functionality is demonstrated starting from 1:30):

More information

GitHub Copilot: The agent awakens - The GitHub Blog

Use GitHub Copilot Agent Mode to create a Copilot Chat application in 5 minutes

Download Visual Studio Code Insiders

Labels:

Popular posts from this blog

Podman– Command execution failed with exit code 125

After updating WSL on one of the developer machines, Podman failed to work. When we took a look through Podman Desktop, we noticed that Podman had stopped running and returned the following error message: Error: Command execution failed with exit code 125 Here are the steps we tried to fix the issue: We started by running podman info to get some extra details on what could be wrong: >podman info OS: windows/amd64 provider: wsl version: 5.3.1 Cannot connect to Podman. Please verify your connection to the Linux system using `podman system connection list`, or try `podman machine init` and `podman machine start` to manage a new Linux VM Error: unable to connect to Podman socket: failed to connect: dial tcp 127.0.0.1:2655: connectex: No connection could be made because the target machine actively refused it. That makes sense as the podman VM was not running. Let’s check the VM: >podman machine list NAME         ...
Read more

Cache stampede: when our cache turned against us

While investigating some performance issues, we ran into an ASP.NET Core API that cached a fairly expensive aggregation query for 60 seconds. Under normal load, that was fine: one request rebuilds the cache, everyone else reads from it. Under peak load, dozens of requests would arrive in that same expiry window, all see a cache miss, and all fire the same expensive query in parallel. The database didn't like that. That was the moment when our caching layer stopped helping and started hurting. A burst of requests comes in at the same time, all miss the cache, and all go hammer the database or the downstream API at once. That's a cache stampede . The cache was supposed to protect our backend, and for a few hundred milliseconds it did the opposite. Why this happens IMemoryCache.GetOrCreate (and its async sibling) looks like it protects you, but it doesn't add any locking on its own. Look at the naive version: public async Task<Report> GetReportAsync(string key) ...
Read more

A complex system designed from scratch never works

A few years ago, I worked as an architect on a big mainframe rewrite. I still count it as one of my failures. Not because the technology was wrong, but because I couldn't convince the management team to simplify the approach. Years later, the organization is still struggling to get the new system up and running. I left the project at the time, because I couldn't put my name behind an approach that would take very long and cost a lot of money without a working system to show for it along the way. Gall’s Law That memory keeps coming back to me, because it's a textbook case of Gall's Law playing out in real life. Gall's Law , from John Gall's Systemantics , states it plainly: A complex system that works is invariably found to have evolved from a simple system that worked. A complex system designed from scratch never works, and it cannot be patched to make it work. You have to start over with a simple system that works. What does that mean in practice,...
Read more