Skip to main content

Visual Studio 2026–From plan mode to plan agent

Having your AI agent come up with a plan before start coding, has helped me a lot in my agentic development workflow. It allows me to verify the steps the agent will take and allowed me to avoid that the agent goes down the wrong path.

To help you with this, Visual Studio got a ‘plan mode’ that once enabled allowed the agent to create a plan. I really liked the feature, the only problem is that is what not always obvious when the agent decides to create a plan and when it just starts executing.

To tackle this issue, the plan mode in Visual Studio has evolved to a separate plan agent, similar to what we have in VSCode.

Plan first, code second

If you have never heard about plan mode or the plan agent, it is a dedicated mode in Copilot Chat that focuses entirely on understanding what you want to build before touching a single file. Instead of jumping straight to implementation, it asks clarifying questions, reads your codebase using read-only tools, and drafts a detailed implementation plan for you to review.

Think of it like pair programming with a very thorough senior dev who insists on talking through the approach before opening their editor.

How it works

Here's the basic flow:

  • Pick "Plan" from the agent picker in Copilot Chat and describe what you want to build. You can be vague ("refactor the payment module") or specific — the more context you give, the sharper the plan.

 


  • Copilot explores and asks questions. It scans your codebase read-only and flags anything ambiguous. If the task is straightforward, it'll skip straight to drafting.

 


  • You get a plan to review. Not code — a plan. You can ask Copilot to rethink an approach, add edge cases, split a step into smaller pieces, or reconsider which files to touch. Iterate until it matches your vision.


  • Edit the plan directly. Every plan is saved as a markdown file at .copilot/plans/plan-{title}.md in your repo. Open it in the editor, tweak it yourself, share it with your team for a review — it's just a file.

 


  • Hit "Implement plan" when you're ready. Only then does Copilot switch into Agent mode and start making actual changes, working through the plan step by step while you watch in real time.

 


    No surprises. No undoing a dozen edits. You stay in control.

    Why I think it is a must in every developer workflow

    The old problem with agentic AI tools isn't that they're bad at coding — it's that they're too eager. They optimise for doing rather than understanding. The Plan agent puts a deliberate checkpoint between your prompt and the first file change, which is where a lot of the real thinking should happen anyway.

    It's also worth noting the .copilot/plans/ markdown files aren't just a nice-to-have. They make AI-assisted work reviewable and shareable in a way that a chat history isn't. You can commit a plan, get feedback from teammates, and have a clear record of the intended approach before any implementation exists.

    Give it a try

    The Plan agent is available now in Visual Studio. Next time you're about to kick off something non-trivial — a new feature, a refactor, a big integration — try reaching for Plan instead of Ask or Agent mode. The extra few minutes spent aligning on the approach will almost certainly save you more time on the back end.

    More information

    Plan Before You Build: Introducing the Plan agent in Visual Studio - Visual Studio Blog

    I love it when a plan comes together

    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