Startup CTO Insisting on Only Vibe Coding – What to Do?

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.