This training is designed to help software development teams move beyond using Claude Code as a terminal-based AI assistant and adopt it as an extensible agentic development platform supported by subagent architectures and Model Context Protocol (MCP) integrations.

During this advanced two-day program, participants will explore planning-first development methodologies, the design of task-specific subagents, agent orchestration techniques, and structured output mechanisms. By working with agents assigned to different responsibilities within Claude Code, participants will learn how to organize software development activities into modular, controlled, and manageable workflows.

The second day focuses on connecting AI agents to external resources such as Git repositories, file systems, APIs, and databases through MCP. The program also examines access permissions, security boundaries, token and cost optimization, audit logging, and architectural approaches for enterprise AI systems.

Upon completing the training, participants will have developed the knowledge and practical skills needed to coordinate multiple agents in Claude Code, implement MCP-enabled integrations, and design secure, scalable, and auditable AI agent architectures for enterprise software development.

For corporate groups, we can organize this training as an on-site private group.

What You Will Learn

By the end of this training, participants will be able to:

Apply plan-first software development practices using Claude Code.
Understand Main Agent, Orchestrator, and Subagent architectures.
Develop specialized subagents for planning, coding, testing, and code review.
Manage task distribution and workflows across multiple AI agents.
Integrate Git, file systems, APIs, and databases through MCP.
Manage agent security, access permissions, and Prompt Injection risks.
Apply token usage and cost optimization strategies.
Design secure, scalable, and auditable enterprise AI agent architectures.

Training Outline

Day 1 – Claude Code Fundamentals and Subagent Architecture

1. Planning-First Approach to Software Development

Organizing development workflows using the plan-first methodology
Applying step-by-step reasoning techniques
Exploring the benefits of long-context capabilities
Techniques for achieving deterministic code and output generation
Performing analysis and planning before generating code

2. Understanding Subagents and Their Architecture

The role and operating principles of the Main Agent (Orchestrator)
Designing task-oriented subagent structures
Executing tasks within isolated context environments
Delegating responsibilities through role-based task assignment

3. Subagent Types and Responsibilities

Planner Agent: Planning and task organization
Coder Agent: Code development and implementation
Test Agent: Test creation and execution
Reviewer Agent: Code review and evaluation
Refactor Agent: Code improvement and restructuring

4. Best Practices for Subagent Orchestration

Breaking complex tasks into manageable components through task decomposition
Establishing clearly defined input and output formats
Enforcing structured outputs across agent workflows
Implementing the Plan → Execute → Validate cycle
Identifying and managing risks associated with repetitive reasoning loops

Day 2 – MCP Integration and Enterprise Agent Architecture

5. Introduction to Model Context Protocol (MCP)

Core principles and architectural structure of MCP
Understanding the concept of tool exposure
How context injection works
Architecture for integrating MCP with Claude Code

6. Connecting External Systems Through MCP

Accessing Git repositories
Integrating file systems
Executing API requests
Performing database queries
Analyzing application and system logs

7. Security Model for Agents and MCP

Establishing access permissions and permission boundaries
Restricting tool capabilities through tool scoping
Evaluating prompt injection threats
Implementing validation for tool outputs
Monitoring agent activities through audit and logging practices

8. Designing Enterprise AI Agent Architectures

Comparing monolithic and modular agent architectures
Designing a centralized orchestrator
Managing the lifecycle of subagents
Controlling token consumption and operational costs
Evaluating on-premises and cloud deployment strategies

9. Final Project: End-to-End Agentic Software Development

Analyzing software requirements
Designing a Planner Subagent architecture
Generating code and test scenarios
Implementing data integrations through MCP
Performing security checks and validation
Producing reports and technical documentation

Why Choose Us

Leading UK-based global training provider since 1995.

Experience Agentic Software Development with Claude Code in Changi through Bilginç IT Academy's live and interactive virtual classroom environment. Join a Public course as an individual delegate or arrange a dedicated Private / In-house online training program exclusively for your organization.

Delivery Method: Online Instructor-Led
Participation Model: Public / Private (In-house)
Live and Interactive Training: Connect with your instructor in real time and actively participate through discussions, Q&A sessions, practical exercises, and group activities.
Flexible Participation: Join the training from your home, office, or any location with a suitable internet connection.
Expert Trainer Network: Learn from experienced trainers with strong industry backgrounds and practical field expertise.
Over 30 Years of Training Expertise: Benefit from Bilginç IT Academy's professional training experience since 1995.
Worldwide Access: Join our live virtual classrooms from Changi or anywhere else in the world, or arrange a dedicated online training program for your organization.

Experience Agentic Software Development with Claude Code through face-to-face Classroom Based training in Changi. Training can be delivered as a Public course open to individual delegates or as a dedicated Private / In-house class for your organization.

Delivery Method: Classroom Based
Participation Model: Public / Private (In-house)
Face-to-Face Learning: Interact directly with your instructor and fellow delegates in an engaging classroom environment.
Experienced Trainers: Learn from specialists with extensive industry experience and practical real-world knowledge.
Professional Training Environment: Attend training in comfortable, well-equipped classrooms designed to support effective learning.
Practical Learning: Depending on the course, reinforce your knowledge through hands-on exercises, scenarios, case studies, and instructor-led activities.

Arrange Agentic Software Development with Claude Code in Changi as a dedicated Onsite training program for your organization. Bilginç IT Academy trainers can deliver the training at your office or another location of your choice, with the program planned around your team's requirements and business objectives.

Delivery Method: Onsite
Participation Model: Private (In-house)
Training at Your Preferred Location: Organize the training at your company's office or another location selected by your organization.
Tailored Course Content: Adapt the training program to your projects, team structure, existing skill levels, and specific business requirements.
Team-Focused Learning: Develop your team around a shared knowledge base while strengthening internal collaboration and knowledge transfer.
Flexible Scheduling: Plan the training dates, location, and program according to your organization's operational requirements.
Worldwide Onsite Delivery: Arrange the training in Changi or at another preferred location worldwide. Bilginç IT Academy trainers can travel to your selected location to deliver the dedicated training program.

Agentic Software Development with Claude Code Training in Changi