Skip to content
Anton GoncharovAI systems developer
RUEN

Vibe Coding: Software Development in the Age of AI

Fan Wenjie, Li Jianchao, Yan Xiaofan, Zhang Bin

  • AI and agents
  • Programming

A book about vibe coding, development in which a human states the goal and AI writes the code. The authors trace the path from machine code and no-code platforms to LLMs and review the ecosystem: chatting with a model, AI in the IDE and agents that carry a task from start to finish.

The practical part covers prompts and Cursor setup, product requirements, review of AI-written code, and an end-to-end example: a backend, a web interface and deployment via GitHub Actions. The last chapter is about the limits of the approach and the skills a developer needs now.

Key ideas

  1. Development is shifting from “how to do it” commands to describing the goal, “what we need to get”.
  2. The quality of the result is determined by the requirements and context the model receives.
  3. AI code can look correct and still contain typical defects — review is mandatory.
  4. A developer’s value is shifting toward architecture, problem framing and verifying the result.

How I apply it

I write code in Cursor with agents, but I keep the task, the architecture and the review of every change to myself. Tests, linters and CI check what the model generated — that’s how this site and the demo bots are built.

Where and how I applied it

  • Demo · Web app · AI security · vanilla JS

    Prompt injection defense trainer

    All attacks run against all protection levels in Vitest and Playwright tests: whatever the model generated, regressions are caught by the tests.

  • Demo · Telegram and Max · knowledge base search

    AI support from a knowledge base

    Search quality metrics are checked in CI on 40 test questions: a change won’t pass if search got worse.

  • Demo · Web app · scenario · aiogram 3 code

    Bot scenario builder

    The aiogram 3 bot code is generated from the diagram, but before export the scenario is checked for dead ends, unreachable steps and loops.

More on the shelf

  • Reading

    Hands-On APIs for AI and Data Science

    Ryan Day

    A practical book on building an API for data and connecting AI to it. The running project is a FastAPI service with a database and documentation, then an SDK for it, using the API in analytics and, finally, LangChain agents that call the API themselves.

    AI and agentsPythonAPIApplied in 3 projects

  • Reading

    Server Applications in Python, Django, Flask and FastAPI

    R. S. Bukharev

    The path of server-side development in Python, from sockets and protocols to architecture and launch on a server. Django, Flask and FastAPI are covered through real projects: a CRM system, a Telegram bot with server-side logic, a REST API for a mobile app and a WebSocket chat. Separate chapters cover caching and scaling, Docker and Kubernetes, PostgreSQL, MySQL, SQLite and MongoDB, and security: password hashing, JWT and OAuth 2.0, protection against SQL injection, XSS and CSRF, TLS.

    ProgrammingPythonBackendApplied in 1 project