Training

Effective development with Claude Code

Claude Code is an advanced agentic development environment in which an agent can read, edit, and run code as a full-fledged member of the team. Unlike ordinary chat assistants, Claude Code lets you work directly with your projects, execute commands in the terminal, edit files, run tests, and make Git commits, all within a single isolated work session. This training will give you a systematic understanding of Claude Code’s capabilities, its architecture, and best practices for using it to speed up and automate development. You’ll learn how to safely and effectively bring Claude Code into your everyday engineering tasks and team workflows.

Goals and objectives

  • Understand the architecture and capabilities of Claude Code as an agentic development platform
  • Learn to use the Claude Code CLI to analyze, edit, and maintain code on real projects
  • Master configuring and extending Claude Code with custom slash commands, skills, hooks, and tools
  • Learn how to integrate Claude Code safely into team workflows and CI/CD
  • Build a practical understanding of the best approaches and patterns for working with context
Target audience
Java or Python developers, architects, tech leads
Price
$450per participant
Date and time
8 modules of 3 hours each
Trainer
Mikalai AlimenkouIndependent consultant

Book for your company

Detailed program

Part 1

  • Generative AI and the Transformer architecture
  • How LLMs work and the main stages of their training
  • Capabilities and limitations of LLMs
  • LLMs on the market and how they are classified

Part 2

  • Overview of Anthropic models and the options for accessing them
  • Overview of the Claude family of tools
  • The philosophy behind an agentic development platform
  • The agentic loop for solving tasks and managing context
  • Overview of the Claude Code ecosystem (CLI, desktop, web)
  • Installing Claude Code and basic setup

Part 3

  • Managing sessions
  • Plan mode
  • Saving and reusing plans
  • The permission system
  • Working with checkpoints
  • Custom slash commands

Part 4

  • Principles of context engineering
  • Managing memory in Claude Code
  • Project-level CLAUDE.md and AGENTS.md files
  • Configuration scopes
  • Basic context management techniques

Part 5

  • The MCP protocol
  • Configuring additional tools via MCP
  • Key MCP servers for development
  • Browser automation

Part 6

  • The concept of guardrails
  • Configuring custom guardrails with hooks
  • Extracting shared skills
  • Using skills flexibly to free up context

Part 7

  • Subagents for delegating tasks
  • Built-in subagents and adding custom subagents
  • Ways to manage context with subagents
  • Multi-agent development patterns
  • Isolating the agent’s environment with sandboxing
  • Working with git worktree for parallel tasks

Part 8

  • Configuring Claude Code for a development team
  • Practices for optimizing API usage costs
  • The spec-driven development approach
  • Using Spec Kit to extend Claude Code
  • Using OpenSpec to extend Claude Code
  • Implementing code review with Claude Code

Past runs

  • June 8-24, 2026Online8 sessions on Zoom on Mondays, Wednesdays, and Fridays (4:00 to 7:00 p.m., Kyiv time).
  • May 18 - June 3, 2026Online8 sessions on Zoom on Mondays, Wednesdays, and Fridays (4:00 to 7:00 p.m., Kyiv time).
  • April 8-22, 2026Online7 sessions on Zoom on Mondays, Wednesdays, and Fridays (4:00 to 7:00 p.m., Kyiv time).
  • March 18 - April 1, 2026Online7 sessions on Zoom on Mondays, Wednesdays, and Fridays (4:00 to 7:00 p.m., Kyiv time).
  • February 27 - March 13, 2026Online7 sessions on Zoom on Mondays, Wednesdays, and Fridays (4:00 to 7:00 p.m., Kyiv time).