This is my first DEV Community note about my own AI-assisted creator workflow.
My name is Nikita Kizevich. I also publish as Mikita Kizevich, AI_Nikitka93 and Nikitka AI. I work across AI-generated photography, AI video, music, and AI-assisted software prototypes.
The core workflow is simple:
- Start with an idea and a real target user.
- Describe the product flow and constraints to an AI coding agent.
- Run the result locally or in a browser.
- Read the logs and browser behavior.
- Send concrete failures back into the loop.
- Package only what is honest to publish: demo, prototype, case study, or production-ready project.
The useful part is not "AI wrote code for me". The useful part is the repeatable loop: idea -> implementation -> runtime check -> correction -> public artifact.
What works best:
- small tasks;
- browser screenshots and real UI checks;
- logs instead of vague "it does not work";
- honest public wording;
- keeping GitHub as a living portfolio, not a fixed list.
What does not work:
- asking for a perfect startup in one prompt;
- publishing generated UI without opening it;
- calling every prototype production-ready;
- hiding where AI was used.
My public GitHub is here:
https://github.com/AI-Nikitka93
Other public links:
YouTube: https://www.youtube.com/@ai_nikitka93Instagram: https://www.instagram.com/ai_nikitka93/
LinkedIn: https://www.linkedin.com/in/kizevichnik/
35PHOTO: https://35photo.pro/nikita650
35AWARDS: https://35awards.com/author/nikita650/
Spotify / Nikitka AI: https://open.spotify.com/artist/3fYjimtlZBBtZKNVHac5pB
I am using DEV as a place to write short practical notes about AI agents, LLM workflows, public demo packaging, Telegram bots, and browser-based checks.