How VS Code Went from Monthly to Weekly Releases with AI — Harald Kirschner

Video authored by the channel shown, not by IANIA; all rights belong to the creator. Transcript and summary generated automatically; the original-language content is preserved.

Original language: English

Original video: How VS Code Went from Monthly to Weekly Releases with AI — Harald Kirschner · Channel: AI Engineer · 19:33 · Watch on YouTube

Topics: AI agents, AI evaluation and benchmarks, Software engineering with AI

Summary

Harald Kirschner describes how the VS Code team moved from monthly to weekly releases by changing its entire software-development system, rather than simply using AI to generate more code. The team improved its codebase guidance, reusable skills, build times, UI feedback loops, code review, issue triage, telemetry handling, and staged rollouts to maintain quality as development sped up. It also uses evaluations and rapid prototypes to learn from product scenarios and refine ideas more frequently. The central lesson is to find and improve the feedback loops and bottlenecks that help teams ship faster, maintain quality, and learn faster.

Key points

The team tracks the share of agent-written code that gets committed as a measure of code survival, trust, and confidence.
AI has increased both issue and pull-request volumes, including more community pull requests that are merged.
Agent-ready codebases benefit from lightweight guidance documents and maintained skills that make expert knowledge available across the team.
The team reports that moving to TypeScript Go improved builds by 10 times, helping reduce CI/CD bottlenecks when many agents are running.
Automated component screenshots and browser-based testing give agents and developers faster feedback on UI changes and fixes.
AI assists with code review and issue triage, while human feedback helps correct agent mistakes and improve the workflow.
Telemetry is filtered and grouped to identify error stacks, file issues, and open pull requests that agents can investigate and fix.
Staged rollouts help the team monitor errors and issues while reducing the risk of releases.
Evals and prototypes help the team test product scenarios and discuss ideas in shorter cycles, from weekly releases to daily iteration.
The broader goal is to continuously identify bottlenecks and improve feedback loops, not just increase agent usage.

Chapters

Start	Chapter	Summary
00:12	From monthly to weekly releases	Kirschner introduces the talk’s focus: how AI changed the VS Code team’s development and release system, and the effects on code survival, issues, and contributions.
03:18	Preparing the codebase and team for agents	He argues that shipping faster requires agent-ready documentation, shared skills, accessible expertise, and shorter build and CI/CD cycles.
07:59	Building UI feedback loops	The team uses component screenshots and browser automation so developers and agents can inspect UI changes and verify fixes.
11:08	Review, triage, and automated fixes	Kirschner describes AI-assisted code review and issue triage, error-stack processing, agent-created pull requests, and human oversight.
15:25	Safer releases and faster product learning	The team stages rollouts, builds product evaluations from real scenarios, and uses experiments and prototypes to learn and iterate more quickly.
18:31	Continuously improving feedback loops	He concludes by urging teams to find their next bottleneck and iteratively improve how agents receive feedback.

Quotes

It’s about evolving the whole system, how you’re shipping software to evolve to actually make better use of AI along the whole process. — 03:18

If your agent cannot use your application, your product directly to get this feedback loop of is it all working, then that’s a really big investment that pays off every time you work on UI. — 08:30

So now actually we do stage rollouts and as we do the roll out we monitor error locks and issues and everything else. — 15:25

don’t just tune how you work with agents, but tune where how how do they get feedback? — 18:31

Concepts and entities

VS Code, Harald Kirschner, GPT-4.1, Claude Opus 4.6, TypeScript Go, Playwright, Xcode MCP, GitHub Copilot, VSC bench, component browser

Full transcript (original language)

00:12 Hey uh everyone. This is a hard tone to follow. Why did everybody leave? No. Um this is the rerun of a talk that she gave yesterday upstairs. So this will be better than the one yesterday. So uh kudos to you for catching this one. I’m working on VS Code and we move from a monthly release to a weekly release cycle thanks to AI. And this is about the things we learned, the systems that made this work, not just to ship faster, but actually to ship more effectively.

00:43 So, it’s not about how we build agents into VS Code, which we can try out anytime. You can come by the booth and see us showing of agents, but this is about how we use agents to build the product itself. And that’s VS Code, that’s the copci and other areas, but also how as you use agents and more AI, things are breaking and you have to rethink actually how you work. And that’s a very small team shipping to over 50 million users. What happened is over the past year is

01:15 we started tracking already early on this code survival metrics in VS code. So that means the percent of agent written code that actually gets committed. how much kind of garbage has the agent produced that you threw out the window again or didn’t trust and that you that you read it u and and scrapped. So GBD 4.1 started at 55%. But then over time and over improving the harness and new models cloud opus 4.6 is now today at 86%.

01:46 And that increase clearly shows developer trust and confidence in shipping AI code faster and more AI code generated. And this success created problems on the VS code side. We’re one of the biggest or the biggest open-source project on GitHub. So we saw a massive increase in issues because AI helps to file issues. So we actually see an increase in quality issues but also the counterpart of more automated lowquality issues. We

02:17 also see more open PRs by the team by our own velocity and by our community. And interesting part we actually see everybody would assume we see a lot of garbage PRs but actually the number of community merged PRs is going up as well which is really amazing that we can unlock more community contributions as well. And as part of this new workflow, we actually moved several months ago, we moved from monthly releases, which happened over 10 years. Since the inception of VS Code 1.0, we have been

02:48 shipping a new version of VS Code on a monthly basis. Including fun facts like the January release actually ships in February. So when you read the release notes in VS Code, you’re wondering why it’s February and you’re reading the January release notes if you’re a month late. No, that’s just how we tracked our iterations. So that cadence was to match to velocity, but it also showed us that the it’s not about using more AI as you work

03:18 dayto-day, which a lot of companies are pushing. Like you’re not token maxing. You’re not spending every day using AI. It’s about evolving the whole system, how you’re shipping software to evolve to actually make better use of AI along the whole process. And that what makes this velocity actually work and doesn’t just generate more code. I’m breaking this down into this first part which a lot of people have been experiencing. I see shipping code faster and that’s the easy part. You have like this 100x engineers that has built this

03:50 beautiful skill MCP plug-in system and they’re just shipping code like crazy and slowly maybe more in the more people in the team uh adopt the same patterns and you see a lot more code shipping faster. But the problem is once you ship faster, you get into code review. You get into how do you actually ship high quality code that doesn’t constantly break. And that’s important for us as VS Code. We’re shipping binaries to user machines. So if something breaks, that recovery is even more costly.

04:22 But once you hit that velocity with shipping high quality code faster with confidence, how do you actually know you’re shipping the right thing or if we should ship this thing? And that’s where AI kicks in to actually learn faster in the end and shipping better products which a lot of people are missing out as as they write more code is applying that product taste and applying that learning. So let’s start shipping faster. Now that everybody can vibe, we can really all

04:53 ship faster. And it’s a big part is getting your codebasation ready. So that’s kind of the no-brainer slide that everybody should already been doing is thinking about how to get your code bases agent ready is creating agents.mmd that give it that are lightweight enough and give the agents a good kind of map of the codebase where to look at mapping out that is every agent now at your uh at your fingertips has a slash in it that gives you a good draft and then you keep itering those are living documents

05:24 that should evolve as the agent makes mistakes and works. And that’s where I see a lot of teams that have invested in developer experience actually gain a lot because once they have good documentation and onboarding for a codebase that is read by the agent as well and that can help the agent as much. Next up you have skills. VS Code has always messed heavily in accessibility. So one skill we added early on was infusing all the accessibility best practices and how we think about

05:54 accessibility into a skill that everybody will use and that previously was one person that had to then got get pulled in or give feedback and now that skill was reviewed and is maintained by the kind of area owner of accessibility. So to bring that that accessibility that short work everywhere into everybody’s hands. So think how you can encode your expert knowledge to unblock this like few users that might be always asked for this input into a skill. And lastly once

06:26 you do it right for us in VS Code the litmus test is can I as a PM effectively VIP code in the VS code repo which I do um and how is that accepted by engineering? How much work does it cost? Is it out of the box working? Is it for me working locally? Or is it eventually breaking when I ship it? So, a lot of these quality improvements will show in the end that you can allow everybody to

06:57 be more effective in the repo. Another improvement, and that’s a massive one, is we switched to TypeScript Go. And if you’ve been in any developer codebase that takes some time to build or run linting or run CI/CD, you’ve noticed it’s already annoying. But developers find other ways. They can review a PR. They can context switch into something else while runs and then do something else. But once you hit that with agents, you have 10 agents, 20

07:28 agents running and hitting the same bottleneck, these any slow part of your CI/CD will compound. And for us, Typescript Go was a 10 times improvements in our builds, which at the scale of automatic PRs running with agents and them fixing getting needing that CI/CD loop for feedback to improve the code is a massive improvement. And that leads to me uh filing big PRs.

07:59 That was beginning of the year to get the ask questions tool in which I believe we really needed and then bringing it to the team to show to let them try it out in the product. Within a few weeks we had a perfectly polished and designed experience based on my initially very scrappy PR. But it unblocked that this these discussions the participation of everybody else because we had the ground set laid and the idea and the experience was clear.

08:30 Next up, when agents actually work on UI, and we all had this, that the agent gives you a UI and it says it looks perfect, then you open it and it’s all misaligned. Even with SVG, even with the latest models, you still get it. And it’s like the number one thing I keep telling everybody now these days. If your agent cannot use your application, your product directly to get this feedback loop of is it all working, then that’s a really big investment that pays off every time you work on UI.

09:02 And there’s two areas we invested in. One is the component browser, which is an automated build that runs every time VS Code changes something. Let me open this in this issue as an example. In this case, we added a back button to our customization screen. And because it’s changing wide, we actually have this automated process in the back that takes screenshots of every component in VS Code and points out the differences.

09:33 It allows us to detect unexpected changes like we’re changing one component as the ripple effect of something else moving or some other icon disappearing. and allows you to quickly review a PR as well because you also get directly a view and what the PR is actually doing and that’s what we ask every developer before we ask them to at least attach a video or screenshot on what they have been implementing so we don’t have to run everything from scratch and we can quickly assess and and give feedback and this is now automated with the component explorer

10:07 next up we have the self-correcting loop because in VS Code we run uh a web browser and open a website. Basically, that’s what VS Code is. It’s all HTML. We can actually use Playright to automate a lot in the browser. So, we have a /launch skill that would just open up VS Code and give it a specific scenario to click through in VS Code. So, it’s a really powerful way to diagnose issues because you can also get the locks along the way, but also validate any fixes you did before and

10:37 after without you having to click through it. So you can just hit launch move on to the next task and then come back once the agent verified it’s worked because it can access your application and to call out this is nice because we have playright and we are a web app uh running in electron but there’s many other solutions out there one of my favorites is Xcode MCP because on my site I work on iOS apps and once you see Xcode MCP just creating in VS code without Xcode involvement just making an

11:08 iOS app opening it up clicking through it, taking screenshots. These moments are magical and give you a really tight feedback loop as well. So there’s other tools available for Android as well to make this work. Let’s talk about code review, which I think is the next big investment. We know in the past when we enabled code we on GitHub the automated GitHub copiloted one we’re not convinced yet but over the next months and weeks they have massively improved and now it’s a mandatory uh review every time somebody

11:38 opens a PR and there’s more improvements coming actually dial in the uh the effort that a code review does depending on how much risk you have in this repo so you have a low medium high effort for code review so you can dial in kind of the cost benefit as well but for us is if a review after review is done, humans will not even look at PR until all the comments are resolved and and addressed. Okay, now we’re holding we’re shipping faster. We got to hold quality. And a big signal for us because we’re on

12:10 GitHub is of course issues. Uh who has filed a GitHub issue? Who has had problems in VS Code before? Yeah, cool. Kind of similar. Awesome. This the last crowd had less hands up. So it’s good. Um, yeah. So it’s a massive, it’s a really good signal. And as I said, we get sometimes even better issues now because of AI and more people with different language backgrounds being able to file very good issues. But we also get a lot of issues. And previously engineers actually triage them manually. And now we have AI doing

12:42 the filtering to get out spam enriching and translating in the end assigning area owners for all the issues to raise the signal to noise quality of this. We also add a human layer to that once you are in issue because the agent will make mistakes and we need that feedback loop when it makes mistakes. We create a Chrome extension that allows you to fix duplicated issues as well. So we have the agent doing the work and we have a feedback loop where humans can still fix it that we can bring back into the into

13:14 the agent work up front. That’s a really important thing to think about as you have agents doing the work that you get the human feedback as well. The other input we have is a lot of error stacks. Every time there’s an exception and most apps will have this you get an error stack reported and we actually don’t use any external tool for that. It’s all in our own data and we built all the tooling around it and it’s mostly we already had it. We already had an ML doing sorting on top and this is now actually done by a mix of criteria.

13:48 So one is we collect the raw telemetry. We filter it down and that’s like 51 billion per day. We filter it down to just error stacks that actually have the full stack. Then we group it and bucket it. That’s more of the fingerprinting exercise. And then in the end after we all of that we have 10 issues filed assigned to specific area owners that a PR is autocreated to actually already try to fix the problem. This is our error page where we see all the stacks including how many hits and

14:18 how many users affected so we can quickly react to anything that’s coming. And once we have this working we get a issue filed and a PR automatically opened. This is the issue. is the error with some initial diagnosis and then the PR got opened with and the agent actually goes in and finds out why does this happen who was responsible in this case um added a change that was connected to this to find f find symbols and then it

14:50 figured that the on cancellation request wasn’t in the RPC protocol so the agent already opened the PR we could just merge it and that’s a really great automated way you don’t care about errors you just want to get a more stable code base. So all of this automated the triage initially mix of agents and deterministic systems then the issue is filed handed off to an agent in the PR multi- aent system and in the end we have fixing fixes landing mostly automatically with some human oversight to still approve the PR.

15:25 There you go. So previously VS Code did yolo releases in a way that it was release day everything was stable. We did our testing and we shipped the release to 100%. We just opened the floodgates but because of agents we want to derisk that process. We should have probably done it earlier. So now actually we do stage rollouts and as we do the roll out we monitor error locks and issues and everything else. So just like good citizens in a in an web application, we now apply the same because rollbacks on an install app are

15:56 so expensive. Okay, now we have this shipping faster, shipping at quality. How do we actually do this in a in a speed that we actually learn faster, which is the which is a bigger challenge with AI? You actually want to build a better product faster. So one of the examples is our VSC bench. We’re shipping an agentic product. So it’s important that we have our own evals of our product always at hand and being really easy to extend. It’s all in the GitHub issue. It’s all in GitHub.

16:26 When we file an issue to add a new scenario, it’s actually an agent picking up from a template and bootstrapping the scenario for you. So we make it as easy as possible to bring in all the developer scenarios that are coming up in issues through customer conversations through all these channels to bring them back into our emails. So we then start hill climbing actually against them and then com also confirm that it’s all improving offline and then an online experimentation. So classic product life cycle for um for us and we

16:58 see these interesting things in our stack. Understanding your evals is critical. One experiment we did that you can read about on our blog is that we gave a very simple eval scenario of just write a file with hello world just testing out our eval harness end to end and how different models react. The same five character file took the most expensive model 70x more tokens and that was not the high reasoning model. You can read more about unblock. We actually don’t talk about the models,

17:29 but just that insight in how your models react with your harness is extremely is a very important exercise. Next up, we have prototyping, which I do a lot of because I noticed that I don’t actually want to land most of my work into VS Code PRs itself. It’s a great way to start a conversation, but most often I want to have a quick conversation because now we’re meeting on a daily basis where we just want to have very quick feedback loops on here’s the idea, here’s how it could look like,

18:00 what if we do this. Next day you come back with updated uh prototypes and you just keep having this conversation. So much quicker feedback from a month release cycle to weekly to daily sprints where you just keep working on problems and prototypes unlock those deeper discussions and how the experience should look like. It also means that we have the durable ownership in internal work as I mentioned daily sprints um smaller squads, smaller work streams that really

18:31 prioritize and drive smaller sets um of areas to move faster. So try these things, find out where your bottlenecks are to actually ship higher quality, ship faster and learn faster and find fix that next bottleneck. And don’t just tune how you work with agents, but tune where how how do they get feedback? How do you build these loops? And then figure out after you have these these success moments, how can you improve that feedback loop for the next moment of what’s blocking you to move even

19:02 faster and it’s a constant iterative cycle across all these cycle ones. That’s it. Come by code booth. Happy to chat now. Otherwise, happy coding. >> [applause]

19:33 [music]