How to write code with AI
Approaches to AI development: how to formulate tasks, monitor results, validate code, and turn model responses into a working system.
AGENTS.md: A Single Source of Truth for AI Agents
AGENTS.md is a contract between the project and AI agents. The article explains why it is needed, what problems it solves and why without it, AI begins to break the architecture, even if the code is already written correctly
Project Preparation with AI: From Idea to Documentation
Fully automated workflow: from idea formulation to ready-made Markdown documents
Memory Bank: Storing context for AI in project development
Memory Bank is a simple file system that captures the key context of a project
Git Worktree: Convenient tool for parallel work in one repository
In this article, we will discuss how to use Git Worktree to simultaneously develop multiple tasks in one Git repository without constantly switching branches. Useful for developers working with feature-bunches, hotfix and long-term processes
How to get AI to write tests automatically
In this article, a practical system for generating tests with the help of AI: from the TDD approach and 100% branch coverage to integration tests, external service mosks and a CI-ready pipeline. It shows how to get Claude, Cursor or Windsurf not just to write a few happy-path checks, but to create a full-fledged test infrastructure with autorun, error fixing and coverage report.