Startup CTO insisting on only vibe coding – What to do?
7 comments
I'm building a startup myself and we vibe code everything, except core/complex parts where AI struggles.
My workflow:
1. Give the agent detailed task + relevant file contexts (so it doesn't waste time searching)
2. Guide it with continuous feedback when it veers off
3. Jump in manually if it's going completely wrong direction
I use Claude Code for the agent work, Cursor for manual edits.
Key insight: AI coding works as well as your architecture does. I make all architecture decisions, file structure, organization -- AI just writes the implementation logic.
Clean architecture = better AI output.
I believe This is becoming the norm because it gives startups massive velocity advantage. That's probably why your CTO is pushing it.
Career impact? As a senior who understands what AI writes, you're gaining superpowers, not losing skills. You were previously bottlenecked by implementation speed and needed other engineers. Now you can be a 10x engineer - as long as you can envision the architecture, AI helps you build it faster.
The key is knowing when to guide vs when to take over. That judgment comes from experience.
My workflow:
1. Give the agent detailed task + relevant file contexts (so it doesn't waste time searching)
2. Guide it with continuous feedback when it veers off
3. Jump in manually if it's going completely wrong direction
I use Claude Code for the agent work, Cursor for manual edits.
Key insight: AI coding works as well as your architecture does. I make all architecture decisions, file structure, organization -- AI just writes the implementation logic.
Clean architecture = better AI output.
I believe This is becoming the norm because it gives startups massive velocity advantage. That's probably why your CTO is pushing it.
Career impact? As a senior who understands what AI writes, you're gaining superpowers, not losing skills. You were previously bottlenecked by implementation speed and needed other engineers. Now you can be a 10x engineer - as long as you can envision the architecture, AI helps you build it faster.
The key is knowing when to guide vs when to take over. That judgment comes from experience.
Thank you for your response.
If it's ok, could you please share if you follow a certain structure when defining the detailed task for the agent.
If it's ok, could you please share if you follow a certain structure when defining the detailed task for the agent.
No specific structure - you'll need to experiment based on your project.
I treat it like briefing a senior engineer. Example:
"Currently we have X, Y, Z but it has ABC limitation. We need to support FOOBAR. What are our options?"
Agent suggests 3 approaches.
"Go with Approach 1 but remove the Z part. Implement it."
Try being specific about constraints and current state. The agent fills in the implementation details, but you drive the decisions.
I treat it like briefing a senior engineer. Example:
"Currently we have X, Y, Z but it has ABC limitation. We need to support FOOBAR. What are our options?"
Agent suggests 3 approaches.
"Go with Approach 1 but remove the Z part. Implement it."
Try being specific about constraints and current state. The agent fills in the implementation details, but you drive the decisions.
Hi,
As a former senior solution architect, I have tested several tools or platforms of "vibe-coding" or "agentic software development". None of the available tools or platforms satisfied the quality level, I used to have. Number of failures was more than successes. Which is completely understandable for the "Sophisticated Prediction Algorithms" or LLMs in official terms.
The main problem is these systems do not have proper judgement mechanisms to translate user or customer requirements to executable tasks.
Then, I have ended up with https://github.com/bmad-code-org/BMAD-METHOD. This framework is a well thought approach to create very detailed definitions of the tasks that LLM based coding agents can process and execute with better outcomes.
To address this topic I have recently published an article you can read https://open.substack.com/pub/practicalsecurity/p/the-70-pro... . I hope the information and research for this article gives you some ammunition for your defense.
For further discussions feel free to reach out by leaving a comment to the article if you wish.
I hope things will get better for you in the startup you are contributing.
As a former senior solution architect, I have tested several tools or platforms of "vibe-coding" or "agentic software development". None of the available tools or platforms satisfied the quality level, I used to have. Number of failures was more than successes. Which is completely understandable for the "Sophisticated Prediction Algorithms" or LLMs in official terms.
The main problem is these systems do not have proper judgement mechanisms to translate user or customer requirements to executable tasks.
Then, I have ended up with https://github.com/bmad-code-org/BMAD-METHOD. This framework is a well thought approach to create very detailed definitions of the tasks that LLM based coding agents can process and execute with better outcomes.
To address this topic I have recently published an article you can read https://open.substack.com/pub/practicalsecurity/p/the-70-pro... . I hope the information and research for this article gives you some ammunition for your defense.
For further discussions feel free to reach out by leaving a comment to the article if you wish.
I hope things will get better for you in the startup you are contributing.
Thank you for your reply!
I never heard of BMAD-METHOD, so thank you for sharing this. I will go through it and definitely get back to you via your article.
I never heard of BMAD-METHOD, so thank you for sharing this. I will go through it and definitely get back to you via your article.
Start job hunting. Your CTO is probably a sociopath.
https://pivot-to-ai.com/2025/10/15/ai-is-not-popular-and-ai-...
https://pivot-to-ai.com/2025/10/15/ai-is-not-popular-and-ai-...
That's a new angle!
Job hunting is definitely on the cards anyway, but I want to make sure I also find ways to use these AI tools better. I am guessing there will be a push to use it anywhere I go in as a developer.
Job hunting is definitely on the cards anyway, but I want to make sure I also find ways to use these AI tools better. I am guessing there will be a push to use it anywhere I go in as a developer.
I work for an AI startup where it’s just the two of us (me and the CTO) who handle all the software engineering. I have 10 years of experience building software until 2023, when I took a break. The CTO focuses only on backend AI-related work (since that’s his background), and I take care of everything else—API development, front-end work, AWS infrastructure, etc.
My break coincided with the time when ChatGPT came into the spotlight and vibe coding started gaining traction. Now that I’m back to work as a software engineer, I’m getting used to AI/LLM-assisted development, but there are some drawbacks (e.g., Cursor touching unintended files, not tracking changes across multiple prompts, etc.). Lately, my CTO has been complaining that I’m not vibe coding “well enough” to complete tasks quickly. I’m just not comfortable relying solely on vibe coding without writing code myself.
My question to the community is: Is it okay to vibe code an entire application that will be used in a commercial setting? And would this not impact my own career if most of my work becomes just writing prompts to generate code? I have friends at Microsoft and Google who say they vibe code a reasonable percentage of their work, but not exclusively.
I’m curious whether this is just how things work at my startup or if this is becoming the norm across startups today.