1. Home
  2. Workshops
  3. Claude Code Fundamentals

Claude Code Fundamentals

In this workshop your developers learn how to work with Claude Code as a terminal-based coding agent. We start with the basic loop of exploring, planning, implementing and verifying, then apply it to real tasks in your own repository or a sandbox project. The focus is on speed with control: every change stays reviewable, and humans keep responsibility.

Request without obligation

Deutsche Version

Duration
1 day
Level
Beginner
Format
Remote or on-site, English or German
Group size
Up to 12 participants per trainer

Who it is for

  • Developers new to coding agents
  • Engineers who have tried Claude Code but lack a routine
  • Tech leads evaluating agentic workflows for their team

What your team will be able to do

  • Set up Claude Code and explain what it can read, change and run
  • Work through the explore, plan, implement and verify loop on a real task
  • Write prompts that give the agent enough context and clear acceptance criteria
  • Use permission modes and diffs to keep every change under control
  • Review agent-made changes and commit them as clean Pull Requests

Agenda

  1. Setup and mental modelHow a coding agent differs from autocomplete and chat. Installation, project access and first interactions.
  2. The agentic loopExplore the code, plan the change, implement in small steps and verify with tests. Practised on a first guided task.
  3. Prompts and contextHow to describe goals, constraints and acceptance criteria. Referencing files and giving the agent project conventions.
  4. Permissions and safetyWhat the agent may read, edit and execute, and how to approve or restrict actions deliberately.
  5. Review and Git workflowReading agent diffs critically, asking for corrections and preparing a Pull Request your colleagues can review.
  6. Own-task labParticipants tackle a real ticket from their backlog, supported by the trainer, and share lessons learned.

Prerequisites

  • Basic experience with a programming language and Git
  • A laptop with terminal access and a repository you may use
  • An account for the tool, which we can help you prepare in advance

Why apprat.io workshops

  • Taught by practising AI Code Engineers
  • Your repositories or a sandbox project
  • AI speed, human responsibility: review, security and governance included
  • ISO 9001 & ISO/IEC 27001 certified processes
  • Follow-up office hours after 30 days

Request without obligation

Tell us about your team and goals. We reply within one business day with a tailored agenda and a quote – free and without obligation.

24/7 call support in English & German:
+49 761 519 751 50

Frequently asked questions

Do we need to bring our own repository?

Ideally yes, because real code makes the exercises more relevant. If that is not possible, we prepare a sandbox project that matches your stack.

Is the workshop suitable for non-experts in AI?

Yes. No prior experience with coding agents is required, only solid development fundamentals.

Can the workshop be held remotely?

Yes, it works remotely or on-site in English or German, with a maximum of 12 participants per trainer.

Fields marked * are required.

Related workshops

All workshops