00:00:00How important are tech stack choices by developers like you and me now in April 2026 with all the things that happened in the AI space and with all the advancements in the AI models and even more importantly the AI agent harnesses, the AI agent tools like Cloud Code and Codex and so on.
00:00:23And I created videos about these tools, I have some courses on these tools in case you're interested, Cloud Code and Codex courses which are very popular.
00:00:31But the question today which I want to take a closer look at and share my opinion on is how important are tech stack choices by developers?
00:00:42Do they still matter or should we let the AI decide or maybe more relevant should we make decisions based on the fact that we're about to use AI and I'll let you know what I mean.
00:00:57Now obviously the most basic form of not caring about the tech stack and by the way I'll primarily focus on tech stack choices from the lens of web developers because that is my main thing, web development, but I guess it will apply to all kinds of developers.
00:01:16The easy path you could take is of course that you may be using a tool like let's say Cloud Code, doesn't matter, and you don't really care about the tech stack that's being chosen.
00:01:29Who cares if you're using TypeScript and Next.js with React or if you're using vanilla JavaScript and let's say 10 stack start or maybe you're using Angular instead of React. Who cares, right? Let the AI decide.
00:01:47Now you could do that of course but here we enter the realm of wipe coding obviously because we as a developer don't make any choices and as soon as you stop making choices and decisions, as soon as you stop steering the AI and caring about the code you could say that is my definition of wipe coding.
00:02:09But of course there would be one way of saying that these choices don't really matter anymore and I'll get back to that question.
00:02:16The other maybe more relevant aspect though is that you could argue that yes, you as a developer kind of still make a choice but ultimately it's influenced by the fact that you're about to use AI to help with the development process and you will review the code, you care about it, you're not wipe coding, but still because you're about to use AI a lot,
00:02:45you use a text that you know AI is good at. You use TypeScript, you use Next.js with React for example because you know there's been a lot of training data on that and AI will do good at that.
00:02:59These are the two main points here. We have the first way of not caring which is let AI choose the wipe coding approach and we have the second aspect which is that we let AI influence the choice.
00:03:16I would argue both approaches are kind of wrong and a bit short-sighted. I would argue as a developer it's more important than ever maybe to have an opinion on the tech stack you're going to work on, to make smart decisions and choices because of course the way we developers work is shifting, is changing.
00:03:44We are writing less code. I definitely write less code. Maybe different for you, maybe it will forever be different for you, but as an industry as a whole it's clear to see that there is a big shift going on to developers writing less code and instead orchestrating and using these AI agents and tools.
00:04:06That of course implies that it becomes even more important which choices and decisions we make. If you go down the wipe coding tunnel, if you let AI make the choices, the decisions, that may not be a great future as a developer for obvious reasons.
00:04:28Because who needs you if all you do is ask the AI without any opinions, without any influence on the code it will produce. Nobody needs a developer for that. That will not lead anywhere.
00:04:43Maybe a decent, a good approach for quickly building some prototype, for building some internal application that just needs to do one thing well and you don't care about edge cases, niche cases, problems, security. There are definitely use cases where this may be a valid approach where you may just wipe code something.
00:05:06This also of course may be very useful. Wipe coding may be very useful for people that don't know how to code but that can build some of the software they need for themselves with ease. With all the disadvantages wipe coding has but it has its purpose I would say.
00:05:24There are use cases where it may be a decent decision but of course obviously the tech stack doesn't matter in that case and the people that do wipe code may not even know which options exist out there.
00:05:36Now when it comes to letting AI influence the choice I would argue this may have been a valid argument maybe like a year ago, maybe not even back then but definitely not anymore today and I'll tell you why.
00:05:53Obviously AI has a favorite stack. I've said that before in other videos. If you let AI run, if you go down the wipe coding path chances are pretty high if we're talking about web development that you will get a TypeScript, React, Next.js, Tailwind project.
00:06:13That's the favorite stack of AI and there are reasons for that. Obviously there have been a lot of React, Next.js, Tailwind projects in the training data but depending on how we look at the training data.
00:06:28We include code from the 2010s, the early 2010 years. Obviously there will not be any Tailwind in there. There will be far fewer TypeScript projects or no TypeScript projects in there. No Next.js projects.
00:06:43So obviously there would have been a lot of vanilla JavaScript jQuery projects in that training data too and there definitely were.
00:06:51But the reason for that not being the favorite tech stack of AI of course is not just the amount of training data it saw which matters but it's not the only thing.
00:07:01But it's also that these AI models as we use them no matter by which provider they go through different stages.
00:07:09There is the pre-training stage, there is the fine-tuning, the reinforcement learning stages. There are all these stages where the model provider kind of shapes these models and their behavior.
00:07:20And then there are system prompts. If you're using a tool like Cloud Code there is an invisible system prompt, more or less invisible, that instructs the AI model to act in certain ways.
00:07:34And we already know we saw that these models have definitely been influenced to prefer certain technologies like TypeScript and React.
00:07:45And why is that? That is because, especially TypeScript for example, is a language that works pretty well for AI because it is able to validate the code it produced by checking for type errors.
00:08:00Obviously that's not the only way of validating. A type error-free code base is not necessarily a good code base and not necessarily a code base that works the way you want it to work.
00:08:10But it's an indicator. It tends to be better than vanilla JavaScript as far as I know.
00:08:17So these are reasons why AI has that favorite tech stack and why you may come to the conclusion that it's a good idea to go with that favorite tech stack or something closely related.
00:08:31For example, you may decide that using vanilla JavaScript is not something you want to do because you heard, by me for example, that AI benefits from using type-safe languages like TypeScript.
00:08:44And there may be some truth to that, but at this point in time, in April 2026, it has been proven over and over again, and it has been my experience too, that AI and these AI agents like Claude Code are really good at picking up whichever tech stack you throw at them.
00:09:04It used to be the case that it is kind of annoying to, for example, work with libraries or frameworks that are pretty new and where there hasn't been a lot of data in the training data or maybe no data at all, but that's not really the case anymore.
00:09:20As a developer using AI, you can obviously go to the docs of any library you want to use. Let's say you want to use the latest version of Nuxt.js or you want to use Svelte 5 or whatever it is.
00:09:34A 10 stack start, for example, which is relatively new. You can go to the docs of these projects and you can pick the relevant articles and just throw them into the context of your current chat session so that the AI is aware of this documentation.
00:09:51And it will be able to pick up on the code examples and the explanation it sees there and apply that to your code base so you can absolutely use very new libraries that may not have been in the training data in your project.
00:10:07And nowadays, you typically don't even have to go to the docs and choose them manually. Instead, if you just have a specific enough prompt where you tell it that you want to use a library, let's say 10 stack start, and you tell the AI that it should go look at the docs
00:10:24and you maybe gave it an MCP like the Context 7 MCP or the AI agents like Claude Codenson. They also have web search. You trust that it does a web search and finds the relevant documentation and you can, of course, influence that by using skills, for example.
00:10:43I have a code research skill where I tell the AI that for certain prompts I may be using, it should take a look at that skill and in that skill, I then describe how it should look up docs.
00:10:57So you may have stuff like that. And if you do have that, you typically don't have to include documentation yourself.
00:11:03Instead, the AI can look for it on its own and include it and pull in the relevant documentation as it needs to. And shocking, of course, as a developer, you can also still write code.
00:11:14And it turns out that if you have a project, AI tends to kind of replicate what's already in there regarding code style, for example.
00:11:28So if you have a project, if you created a project and maybe you already created some functions in there, some routes already, anything like that where you may be using Nuxt.js or 10-stack start or whatever it is,
00:11:42the AI will pick up on that and it will not suddenly start using Nuxt.js syntax and features in that 10-stack start project typically.
00:11:51So all these things combined, existing code, pulling in the right context, nudging the AI towards looking up documentation and including that,
00:12:03all these things together make it really easy these days to work with libraries or a tech stack in general that is not the default and that may include certain technologies that are not well known by AI.
00:12:17That has been my experience. I read a lot on X by other people where the experience has been kind of similar.
00:12:23So that definitely works today. Maybe that was different a year ago, but it's absolutely viable today.
00:12:30And that kind of brings me back to my original question.
00:12:34Does the tech stack choice still matter? Because, of course, it's great that you can make a choice that you are not forced to take one of these two routes.
00:12:44That is great. But does it matter? And I would argue, yes, it matters a lot.
00:12:49As I said initially, that is one of the things that sets a developer apart from non-developers.
00:12:55Not the only thing, but a thing. Different projects benefit from different tech stack choices.
00:13:02And yes, theoretically, you can build anything with any tech stack or with most tech stacks and often it may not matter, but it can matter.
00:13:12If you are working on some project where performance is key, and I don't mean the performance for your 10 users,
00:13:19I mean for bigger projects where performance really will matter, you may prefer to go for a backend language like Go, for example.
00:13:28Because you want better performance, a better memory footprint than you maybe get it with, let's say, TypeScript.
00:13:35That being said, just to also have that in there, there is no reason to over-optimize if you're just building something and you don't even know how many users you'll have.
00:13:45If you ever reach the point where your application chokes under the load, you can always rewrite it.
00:13:52That also is easier than ever now with AI. But yeah, those choices obviously still matter.
00:13:59It also matters what you as a developer know. If you are really good in Angular, let's say, there's no reason to build a React application.
00:14:09Because as a developer, you still want to understand and review the code and get in there and write some code here and there to, again, get AI to move into the right direction.
00:14:20We don't want to become vibe coders. Instead, we want to leverage our knowledge and basically enhance it or leverage it, yeah, with AI.
00:14:30So obviously, if you know something really well, that is a good reason to go with that technological choice, with that framework, library, programming language, whatever it is.
00:14:41And therefore, yes, tech stack choices do matter. And different languages, different frameworks, libraries, they have purposes. They have a reason to exist.
00:14:53Now, you could definitely make the argument that there are some changes going on there because maybe like five or six years ago, a new JavaScript library may have appeared.
00:15:08You know, back then we had new JavaScript libraries almost every week, it felt like. A new library may have come up because it provided better developer ergonomics.
00:15:20That may not be as relevant today anymore. Today, you could argue a new library could come up because it's easier to use by agents,
00:15:30because it does something that makes it particularly easy to be used by agents while still being readable and understandable by humans, too, of course.
00:15:40But yeah, I definitely could see a shift like this happening.
00:15:44And some reasons for why you might have chosen a certain library or framework or programming language in the past may not matter anymore because you are writing less code.
00:15:56Still, for me personally, at least, and I have the luxury of being able to make a lot of tech stack choices for my own projects, obviously.
00:16:04So for me, aesthetics still matter. For example, I still want to work with a tech stack, with a language where I enjoy looking at the code because I'm looking at a lot of code.
00:16:16I'm reviewing a lot of code. So I want to look at something I like seeing.
00:16:23So yeah, tech stack choices, in my opinion, still matter. The reasons may have changed a bit and the impact of choosing certain technologies.
00:16:35But it's an important choice, in my opinion. And of course, as always, I am also interested in hearing your opinion on that.