I have a masters in computer engineering. Started coding in the 70s.
I now run a retail bakery and do all the coding for the web site and our back end - i.e. payroll and accounting.
Here's the deal on using AI for coding from someone who has been coding since the start.
In the end, the basics have not really changed with AI. Its just the next level of abstraction that has been going on since I started coding. Coding started as assembler, went to basic, then C/C++, scripting like Awk/Python, web created HTML, PHP, Javascript, etc, DBs have SQL... You get the point. All those made it more efficient for me as the "programmer" to create an "app".
AI is a layer on top of all these. It can generate any of these. But here's the catch, you need to be very, very, very clear on what you are trying to build. You need to know how to state requirements in a way that the AI create the code that aligns with what you want. You need to be able to translate requirements into tests. That debugs both your requirements and the code generated by the AI. When it does not work, you need to be able to figure out where the problem is. AI can help but only if you give it information to help on.
Vibe coding certainly works for creating "toy" applications for your personal fun.
AI is not magical. It's just an abstraction layer on top of all the current coding languages.
Like all the AI chatbots, it comes down to how good you are at the prompts. Those prompts are the requirements. Also how good you are at checking the results - i.e.hallucinations - by both you (you really did not specify the prompt precisely) or by the AI.
Junior coders just implemented requirements. They ideally created test plans for the requirements. AI makes junior coders less relevant. For AI to work, the people who defined the requirements and the senior engineers that understand the whole system are the key.
Those people were once junior coders. The question is how does someone new to doing software get sufficient experience to define requirements and understand the system. Even more importantly, how to test and debug the requirements.
There is no magic in AI. Its just another abstraction compiler. A very costly one in this case. It's not clear that the cost of running and training the AI engine really is less than just having Junior programmers create code from requirements. The business case is not proven. Copilot and Claude are subsidized today by investors. If they were not subsidized, would they really be lower cost than just hiring a human junior programmer.
That remains to be seen.
For me and my business. Copilot has made it so I can do much more in my less time. But I don't even pay for Copilot. I can use a free version. I don't use the copilot embedded in Visual Studio really. Auto code line recommendations can be disruptive.
That's my take on doing this for a year now. Happy vibe coding out there.
the squarespace/wix example is interesting, at least gives the consumer an idea what to expect and then decide if they will build or it still outsource the build
I think supabase has already made deployment super simple for new vibe coder like me. To even lower the bar for development, there will be tradeoff between security and speed. For example, when I deploy supabase, the most tedious part is managing the security key , not writing backend code
Vibe coding is uniquely valuable for creators, people that know how code, design, and do the marketing. The have the knowledge to build something stunning, and the technical background to figure out if code broke or there’s any issue.
On top of that creators are promoting vibe coding content all the time, making every user that is not technical like them feel overwhelmed, that they should be also vibe coding and they are staying behind if they don’t.
Vibe-coding mvps are easy in our time, but vibe-code secure, reliable and scalable ideas into the world are much harder and require often knowledge about coding
Justine, this breakdown of the 'Product Layer' is spot on. The real breakthrough happens when 'vibe coding' transitions from generating syntax to orchestrating outcomes. This aligns perfectly with the shift toward Agentic Flows—where the 'agent' doesn't just write the code but handles the 'backflip' of environment setup and deployment so the user can focus solely on the intent. The 'magic' isn't in the code; it's in the friction-less result.
I resonate with this post a lot! Non-technical marketer here, but managed to solely use AI tools to produce our company's new website, everything from the code to the videos. Produced 10 pages in less than 2 weeks, start to finish. We originally built our website a year ago using a design agency, and it cost $30,000. Sometimes there is a learning curve, but it is worth it. Those not willing to learn will just end up employing those who are or paying more for someone who already has.
Do you think there will be scope to build an AI native technology services agency, only to build, implement and run highly customized software solutions for small and medium businesses?
We're going to see an explosion of interest in accessible vibe coding apps soon, especially once platforms like Wabi take off. Tools like Lovable, Bolt, and v0 can be considered the first generation of these apps. Intuitive interface + handling containerization and security is a must.
I know by the end of the year we'll see a number of vibe app generation products hitting the market. Think Sora, but for apps.
We at https://yggchat.com/ have already solved the distribution issue by providing a full runtime for our users. We already have an app store where anyone can deploy their app made with Yggdrasil with a single click of a button!
Its amazing looking at our users create and upload apps they never would have made before :)
This is an incredibly well put together framing Justine. I am an engineer by education but never did a day of building software per se. Still, I have the technical mindset of knowing what to look for and going 3-4 deep steps past the initial prompt/setup.
Now, I am trying to build something serious for public (not developers) and I struggle. My vision is clear and have a sense of details that need to come together for commercialization but with the current tools I do think I need to get an engineer or two onboard.
Really thoughtful piece — especially the framing around why vibe coding still breaks down for most users.
One angle I’ve been running into a lot in practice is that some of this frustration isn’t just UX or user skill, but the way platforms operate under the hood. Many route or switch models mid-session for cost or load reasons, which can materially change agent behavior halfway through a build.
From the user’s perspective it feels like you suddenly have a different model — same codebase, same prompts, but degraded reliability.
Curious how you think about this from a business-practice / economic perspective, not just tooling.
I have a masters in computer engineering. Started coding in the 70s.
I now run a retail bakery and do all the coding for the web site and our back end - i.e. payroll and accounting.
Here's the deal on using AI for coding from someone who has been coding since the start.
In the end, the basics have not really changed with AI. Its just the next level of abstraction that has been going on since I started coding. Coding started as assembler, went to basic, then C/C++, scripting like Awk/Python, web created HTML, PHP, Javascript, etc, DBs have SQL... You get the point. All those made it more efficient for me as the "programmer" to create an "app".
AI is a layer on top of all these. It can generate any of these. But here's the catch, you need to be very, very, very clear on what you are trying to build. You need to know how to state requirements in a way that the AI create the code that aligns with what you want. You need to be able to translate requirements into tests. That debugs both your requirements and the code generated by the AI. When it does not work, you need to be able to figure out where the problem is. AI can help but only if you give it information to help on.
Vibe coding certainly works for creating "toy" applications for your personal fun.
AI is not magical. It's just an abstraction layer on top of all the current coding languages.
Like all the AI chatbots, it comes down to how good you are at the prompts. Those prompts are the requirements. Also how good you are at checking the results - i.e.hallucinations - by both you (you really did not specify the prompt precisely) or by the AI.
Junior coders just implemented requirements. They ideally created test plans for the requirements. AI makes junior coders less relevant. For AI to work, the people who defined the requirements and the senior engineers that understand the whole system are the key.
Those people were once junior coders. The question is how does someone new to doing software get sufficient experience to define requirements and understand the system. Even more importantly, how to test and debug the requirements.
There is no magic in AI. Its just another abstraction compiler. A very costly one in this case. It's not clear that the cost of running and training the AI engine really is less than just having Junior programmers create code from requirements. The business case is not proven. Copilot and Claude are subsidized today by investors. If they were not subsidized, would they really be lower cost than just hiring a human junior programmer.
That remains to be seen.
For me and my business. Copilot has made it so I can do much more in my less time. But I don't even pay for Copilot. I can use a free version. I don't use the copilot embedded in Visual Studio really. Auto code line recommendations can be disruptive.
That's my take on doing this for a year now. Happy vibe coding out there.
So nice to see a16z sharing here. Some free guide on coding in the AI era
from the 🇧🇷 community ✨
https://ocoelhobranco.substack.com/p/o-coelho-branco-026-extra-mastering
the squarespace/wix example is interesting, at least gives the consumer an idea what to expect and then decide if they will build or it still outsource the build
Great post!
I think supabase has already made deployment super simple for new vibe coder like me. To even lower the bar for development, there will be tradeoff between security and speed. For example, when I deploy supabase, the most tedious part is managing the security key , not writing backend code
Vibe coding is uniquely valuable for creators, people that know how code, design, and do the marketing. The have the knowledge to build something stunning, and the technical background to figure out if code broke or there’s any issue.
On top of that creators are promoting vibe coding content all the time, making every user that is not technical like them feel overwhelmed, that they should be also vibe coding and they are staying behind if they don’t.
Vibe-coding mvps are easy in our time, but vibe-code secure, reliable and scalable ideas into the world are much harder and require often knowledge about coding
Justine, this breakdown of the 'Product Layer' is spot on. The real breakthrough happens when 'vibe coding' transitions from generating syntax to orchestrating outcomes. This aligns perfectly with the shift toward Agentic Flows—where the 'agent' doesn't just write the code but handles the 'backflip' of environment setup and deployment so the user can focus solely on the intent. The 'magic' isn't in the code; it's in the friction-less result.
continuous learning and up to date education plans are the answer https://andreioros.com/blog/agentic-and-vibe-coding/
I resonate with this post a lot! Non-technical marketer here, but managed to solely use AI tools to produce our company's new website, everything from the code to the videos. Produced 10 pages in less than 2 weeks, start to finish. We originally built our website a year ago using a design agency, and it cost $30,000. Sometimes there is a learning curve, but it is worth it. Those not willing to learn will just end up employing those who are or paying more for someone who already has.
Do you think there will be scope to build an AI native technology services agency, only to build, implement and run highly customized software solutions for small and medium businesses?
We're going to see an explosion of interest in accessible vibe coding apps soon, especially once platforms like Wabi take off. Tools like Lovable, Bolt, and v0 can be considered the first generation of these apps. Intuitive interface + handling containerization and security is a must.
I know by the end of the year we'll see a number of vibe app generation products hitting the market. Think Sora, but for apps.
We at https://yggchat.com/ have already solved the distribution issue by providing a full runtime for our users. We already have an app store where anyone can deploy their app made with Yggdrasil with a single click of a button!
Its amazing looking at our users create and upload apps they never would have made before :)
This is an incredibly well put together framing Justine. I am an engineer by education but never did a day of building software per se. Still, I have the technical mindset of knowing what to look for and going 3-4 deep steps past the initial prompt/setup.
Now, I am trying to build something serious for public (not developers) and I struggle. My vision is clear and have a sense of details that need to come together for commercialization but with the current tools I do think I need to get an engineer or two onboard.
Really thoughtful piece — especially the framing around why vibe coding still breaks down for most users.
One angle I’ve been running into a lot in practice is that some of this frustration isn’t just UX or user skill, but the way platforms operate under the hood. Many route or switch models mid-session for cost or load reasons, which can materially change agent behavior halfway through a build.
From the user’s perspective it feels like you suddenly have a different model — same codebase, same prompts, but degraded reliability.
Curious how you think about this from a business-practice / economic perspective, not just tooling.
Is it really that hard? I mean, many from the product space, technical, but not coders, have picked it up easily enough.