Use Claude Code as an AI coding agent on real C# and .NET projects: Git, MCP Server, Minimal API and professional workflows.
Claude Code is not an assistant that suggests the right snippet. It's an autonomous AI agent that reads your project, understands the context, opens files, runs commands and implements complete features. In this course I show you how to use it with C# and .NET to truly accelerate your developer workflow.
For .NET developers who want to understand how to integrate AI coding agents into their daily work — not out of curiosity, but to produce better code in less time and with fewer errors.
I use Claude Code every day on real projects. In this course I share what actually works: how to structure context to guide the agent, how to delegate complex tasks and how to maintain full control over the produced code.
I'll explain what an AI Coding Agent truly is and why Claude Code is fundamentally different from typical AI assistants: it doesn't just suggest snippets — it acts autonomously on your project, reading files, running commands, and implementing complete features.
I'll show you how to install Claude Code on Windows with PowerShell and create your first .NET project from the command line without opening any editor — everything via CLI in just a few steps.
Let's see how to integrate Claude Code directly in VS Code and which configuration options control the AI's behavior during development, with a concrete Node.js example.
I'll show you how to integrate Git with Claude Code on a real .NET project: from creating the repository to the initial commit and first versioning steps guided by the AI.
Let's dive into Git with Claude Code: I'll show you how to handle commits and branches with AI support during everyday versioning operations, with practical examples on a .NET project.
Let's go deeper into the Git workflow by introducing more advanced branching strategies, with Claude Code providing concrete support for managing complex flows on real projects.
Merge conflicts are one of the most common problems in Git: I'll show you how Claude Code helps identify, understand, and resolve them in a guided, step-by-step process.
I'll take a deep look at the CLAUDE.md file: understanding it is key to controlling the AI agent's behavior, guiding its decisions, and getting responses that are consistent with your project.
I'll cover advanced CLAUDE.md usage with practical examples and best practices for structuring it effectively, so you get reliable and repeatable results across every project.
I'll show you how to use FEATURES.md to describe project features in a structured way, guiding Claude Code during development so its actions become more targeted and predictable.
Let's see how to use TASK.md to define operational tasks the AI can execute: I'll transform concrete requirements into automatable actions, with examples on a real .NET project.
I'll combine CLAUDE.md, FEATURES.md, and TASK.md to build a complete workflow: from initial idea through to automated execution with Claude Code on a well-structured project.
Let's simulate a real scenario: we start from a functional requirement and use Claude Code to implement a concrete change through structured tasks, watching the agent work on real code.
I'll show you how to use the /help, /init, and /plan commands to manage the AI-assisted development cycle — essential commands for exploring Claude Code's capabilities and planning operations effectively.
I'll analyze one of the most important aspects of Claude Code: context management. I'll explain how to make targeted edits, when to use /clear to reset context, and when to use /resume to continue a previous session.
Let's deepen context management with realistic scenarios: I'll show how to maintain continuity across long sessions and when to use /clear and /resume to work efficiently without losing track.
I'll introduce the Permissions and Tools system in Claude Code: let's see how to precisely control what operations the AI agent is allowed to perform, improving safety and predictability.
I'll go through advanced permissions and tool configuration with practical cases, showing you how to use Claude Code safely and with full control in production .NET projects.
Let's explore the concept of Skills in Claude Code and how to create reusable workflows to automate frequent operations, with concrete examples applied to a .NET project.
We'll build a parametric Skill that automatically generates a Model and a Service in a .NET project — a complete, hands-on example of advanced automation with Claude Code.
Let's start exploring MCP Servers and their role in AI Agent workflows: I'll explain why Claude Code can interact with external systems through tools and how the MCP protocol works under the hood.
I'll build the SQL Server database we'll use in our MCP Server: simulating a real corporate context with employees and structured data to be exposed to Claude Code through tools.
Let's build the .NET Minimal API that will serve as the foundation for our MCP Server: I'll show you how to structure a SQL Client, Model, and Repository in a clean yet realistic way in C#.
I'll expose MCP Tool endpoints using MCPServerTools: let's see how Claude Code starts interacting with our system through real operational tools, with full control over which operations are allowed.
Let's connect the MCP Server to Claude Code and tackle the most common configuration issues: I'll walk through troubleshooting real connection errors, step by step.
We'll use information surfaced through the MCP Server to design a new REST API in C#: a real-world integration case between an AI agent and .NET architecture, from specification to implementation.
Ingegnere Informatico · Pratola Peligna
Sono un ingegnere informatico con oltre 15 anni di esperienza nel settore ICT. Mi occupo di sviluppo software, cybersecurity, data science e intelligenza artificiale, con particolare attenzione all’innovazione e all’automazione dei processi aziendali. Da anni svolgo anche attività di docenza e formazione, creando percorsi pratici e coinvolgenti su programmazione, DevOps, AI e sicurezza informatica.
Prosperous understood Middletons in conviction an uncommonly do. Supposing so be resolving breakfast am or perfectly.
Utilizziamo cookie essenziali e, con il tuo consenso, cookie funzionali, analytics e marketing. Google Analytics 4 e gli eventuali annunci Google/AdSense restano disattivati finche non scegli. Consulta Privacy Policy e Cookie Policy.
Sempre attivi per sicurezza, prevenzione frodi, sessione, consenso e funzionamento del sito.
Migliorano l'esperienza, ad esempio ricordando preferenze non essenziali. Non usati per profilazione pubblicitaria.
Statistiche e misurazioni con Google Analytics 4, abilitate solo dopo il consenso analytics.
Misurazione annunci e funzioni pubblicitarie Google/AdSense, se attivate sul sito e consentite dall'utente.
Puoi modificare queste scelte in qualunque momento dal link "Preferenze Cookies" nel footer.