Hands-on course in which you put Claude Code, Anthropic's agentic tool, to productive use in your terminal: from installation and IDE integration to MCP servers, subagents and refactoring.
Free cancellation up to four weeks before the start, so feel free to book now.
In brief. Claude Code for developers is a 2-day classroom course. You can attend it in Amsterdam and Utrecht, in a group of no more than 8 participants. The price is € 1500,- excl. VAT per participant, including course materials, lunch on site and a certificate of attendance. For a team or department we also deliver this course in-company.
Claude Code brings Anthropic's agent to your terminal and changes the way you write, refactor and debug code. In this hands-on course you learn to use the tool productively in your daily development work, with you as the developer firmly in control.
In this hands-on course you work with Claude Code, Anthropic's agentic developer tool that runs in your terminal. You learn how to use this AI CLI in your day-to-day development work: from navigating your codebase and refactoring to writing tests, debugging and proposing commits. You stay in control as the pair programmer.
You work on your own laptop and with your own project or an example codebase we provide. The first day focuses on installation, setup and the basic workflows: prompting effectively in a code context, the difference between agent and chat mode, and setting permissions and hooks. After that you go deeper into slash commands, subagents, MCP servers and working with large codebases. Team workflows, refactoring across multiple files and keeping an eye on token budget and costs are also covered.
The course is entirely practice-based. You do work that you would genuinely do the same way tomorrow, while the trainer looks on and guides you. The small group of no more than eight participants leaves plenty of room for personal attention. The course is given in the classroom or online and is also available in-company.
After this course you will work independently with Claude Code in your terminal and use the tool effectively in your day-to-day development work. You know how to install Claude, connect it to your IDE and MCP servers, and how to configure permissions and hooks safely.
Specifically, by the end you will be able to:
This course is intended for experienced developers who want to become more productive with AI in their terminal workflow. You work with code every day and want to use Claude Code to build features faster, fix bugs and carry out larger refactorings without giving up control.
The course is intended for:
This course is entirely hands-on. You work on your own laptop on real tasks from your own codebase, or on a sample project that we set up for you. You will not come across slides-only hours here.
The trainer looks over your shoulder as you use Claude Code in your terminal: installing, prompting, refactoring, writing tests and debugging. You receive immediate feedback on your approach and learn from what your fellow participants are doing in the group.
With no more than 8 participants per group, there is plenty of room for personal guidance and questions about your specific situation. The course can be taken on location (classroom) or online. In-company is also an option, in which case we come to you.
You will work with a digital workbook containing practice repositories and a reference card with the most commonly used commands and patterns. Claude API credits for the course days are included, so you can get started straight away without having to arrange anything yourself.
You have at least two years of professional development experience and work with code on a daily basis. You are at home on the command line and work routinely with git and your IDE. Experience with Python, JavaScript or TypeScript is useful, but other languages are fine too. Prior knowledge of AI or Claude is not required. You arrange an Anthropic account with an API key during the course.
Nothing special required. You work on your own laptop with Claude Code in the terminal; we provide the API credits for the course days. For the classroom version we take care of coffee, tea and lunch; for the online version you follow the course via a video meeting.
The course is given in Dutch as standard. The trainer speaks English. English-language course materials can be used. If at least 3 participants register, the course can also be given entirely in English.
Would you like to organise this training for a whole group or several groups? This can be cost-effective. For example, we can tailor the content entirely to your organisation, and training a whole group is also cheaper.
Are you looking at large numbers of participants or a complete academy? That involves a great deal. Consider planning and communication, for example, or identifying and agreeing the objectives and content of the training. Or differences in level, feedback mechanisms and safeguarding. Fortunately, Learnit has extensive experience in this field (more than 25 years) and we are happy to help you through this process.
Request a quote More about Claude Code for Developers in-company
2 training days. In order of date.
No suitable start date? Send us a date request, and we'll look at the options together.
Plan your own group on a date that suits you, at your office, at our premises or online. We tailor the content to your day-to-day work, and training a whole group is cheaper than individual bookings.
"Fine, short yet complete basic course."
"I am very satisfied with the course. I got more out of it than I had expected, and that is always good."
"Useful and interesting course!"
"I like this kind of trainings, so I consider it should be done more often"
"In a short space of time – unfortunately I was unable to attend the second day – I learned some very practical applications."
Yes. Up to four weeks before the first day of the course you can cancel free of charge, without giving a reason. You then receive a credit note or, if you have already paid, a refund. If you cancel later, you pay part of the course fee: 25% between four and two weeks before the start, 75% in the two weeks before it and 100% in the final week. Moving to another start date is free of charge up to two weeks before the start, after that 50%. Sending a colleague in your place is always possible. Read the cancellation terms.
You can find the current price at the top right of this course page, along with the schedule, location and delivery format. For in-company or bespoke courses we are happy to provide a quotation on request.
You have at least two years of professional development experience and work with code on a daily basis. You are at home on the command line and use git and an IDE as a matter of routine. Experience with Python, JavaScript or TypeScript is useful, but other languages are fine too. Prior knowledge of AI, Claude or other LLMs is not required; you will learn that during the course.
The course suits software engineers, full-stack developers, DevOps and platform engineers and tech leads who want to become more productive with AI in their terminal workflow. You build features, fix bugs and carry out refactorings, and you want to use Claude Code as a pair programmer without giving up control. Senior developers who want their team to work with Claude Code are also in the right place here.
You learn to install Claude Code and connect it to your IDE, to prompt effectively with file and line references, and to switch between agent mode and chat mode. You also practise with permissions and hooks, slash commands and custom commands, subagents for specialised subtasks and MCP servers for external tools such as a database, git, Jira and monitoring. Refactoring across multiple files, navigating large codebases and keeping an eye on your token budget are covered as well.
Yes. You can choose classroom training at our training location, online via Microsoft Teams, or in-company at your own office. For in-company courses we tailor the content to your stack, codebase and team workflow. Get in touch for a bespoke proposal.
Yes. On completion you receive a certificate of attendance from Learnit. You can add this to your LinkedIn profile or your personal development record.
The course is entirely hands-on. You work on your own laptop on real tasks from your own codebase, or on a sample project that we set up for you. The trainer actively follows along in your terminal and gives immediate feedback on your approach. You receive a digital workbook with practice repositories and a reference card covering the most important commands, workflows and shortcuts.
Copilot is an autocomplete tool that offers suggestions in your editor. Claude Code works differently: it is an agent in your terminal that reads your codebase, edits several files at once, runs commands and completes tasks independently. That calls for a different way of working and directing. In this course you learn to master that agentic workflow, so you can handle larger refactorings and more complex features than with an autocomplete assistant alone.
Yes, that is the whole point. During the course you preferably practise with your own codebase, so you go home with a working setup, experience with your own stack and concrete workflows you can put to use straight away. The reference card helps you quickly find the right commands and patterns during the first few weeks.
A general AI course gives you an overview of tools, prompting techniques and use cases at a high level. This course goes into depth specifically on Claude Code: the agent architecture, MCP servers, subagents, hooks and the terminal workflow. If you want to know what is available on the market, choose a broader AI course. If you want to use Claude Code productively in your daily work, you are in the right place here.
Certainly. Team workflows are an explicit part of the course. You learn how to share conventions, custom commands and subagents with colleagues, how to set permissions and hooks so that the rest of the team can work safely, and how to make Claude Code part of your review and release process. As a tech lead you go home with an approach for rolling the tool out across the whole team.
Staying in control is a central theme of the course. You learn to work with permissions (which commands and file operations the agent may carry out without approval), hooks (where you want to build in a manual check) and the difference between agent mode and chat mode. You practise with safety settings that suit different kinds of work: experimental on a feature branch, cautious on production code. That way you stay at the wheel, not the agent.
Free cancellation up to four weeks before the start, so you can secure a place now.