Training course · Claude Code · API Development

Claude Code for API Developers

Agentic coding with Claude Code in the terminal and IDE: CLAUDE.md, subagents, hooks, MCP, CI pipelines and secure permissions.

Duration
2 days (14 hrs)
Format
Online or on-site
Language
German or English
Participants
open dates or exclusive for your team
Certificate
Certificate of attendance

Overview

This course connects Claude Code with the everyday processes of API Development. Participants work on realistic scenarios and leave with prompts, workflows and checklists they can use straight away.

Claude Code is Anthropic’s agentic coding assistant, working directly in your terminal and in popular IDEs. Rather than completing individual lines, it reads your repository, plans changes across multiple files, runs commands, executes tests and prepares commits. Over two days you will learn to use it with deliberate control: clear project instructions in CLAUDE.md, careful context management, and a workflow in which you set the direction as a developer and can trace every change the agent makes back to a clear intention.

The course is built around real engineering work: diagnosing bugs, delivering features, refactoring legacy code and filling gaps in test coverage. You will configure subagents for specialised tasks, enforce quality checks with hooks, connect external systems through the Model Context Protocol (MCP) and capture team knowledge as reusable skills. Finally, you will run Claude Code headless in CI pipelines and define permissions, sandboxing and approval rules so that its use remains defensible even in security-sensitive environments.

APIs form the backbone of modern software landscapes and are increasingly the interface through which AI agents interact with systems. AI coding assistants speed up the entire API lifecycle, from drafting an OpenAPI or AsyncAPI specification to generating server stubs, clients and contract tests, through to documentation and versioning. At the same time, demands for consistency, security and backward compatibility keep rising, because APIs are consumed by many teams, partners and automated agents. In this course you learn to practise API-first development with AI support, enforce design guidelines automatically, catch breaking changes early and expose existing interfaces to AI agents through the Model Context Protocol or tool definitions.

The course is delivered live – either online in a virtual classroom or on-site in our training rooms in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart and Kaiserslautern. We can also run it exclusively for your team.

Who is this course for?

  • Backend developers building REST, GraphQL or gRPC interfaces
  • API architects and owners of API governance
  • Integration developers connecting partners and platforms
  • Platform engineering teams running API gateways and developer portals
  • Developers making company data available to AI agents

Typical challenges we address

  • Inconsistent API design across teams with differing conventions for errors, pagination and versioning
  • Specification, implementation and documentation drift apart
  • Breaking changes are only discovered by consumers
  • Securing authentication, authorisation and rate limiting as users and agent traffic grow

What you will be able to do

  • You use Claude Code for multi-step development tasks while keeping full control over every change.
  • You maintain a CLAUDE.md that effectively conveys project conventions, commands and architectural guidance to the agent.
  • You extend Claude Code with subagents, hooks, MCP servers and skills tailored to your team.
  • You integrate Claude Code into Git workflows and CI pipelines with traceable, test-backed results.
  • Practise API-first development with AI support, from specification to clients, tests and documentation.
  • Automate design governance, contract testing and breaking-change detection in your pipeline.
  • Make existing APIs available to AI agents securely and in a controlled way, for example via the Model Context Protocol.

Course outline

Day 1

Module 1 How Claude Code works
  • Installation, sign-in and use in the terminal, VS Code and JetBrains IDEs
  • Understanding the agentic loop: read, plan, act, verify
  • Using plan mode to agree on an approach before any code changes
  • Writing effective task briefs with goal, context and acceptance criteria
Module 2 Project context with CLAUDE.md and context management
  • Structuring CLAUDE.md at project, directory and user level
  • Documenting build, test and style conventions so the agent follows them reliably
  • Managing the context window with targeted file references, compaction and fresh sessions
  • Resuming sessions and breaking long tasks into manageable stages
Module 3 Extending Claude Code with subagents, hooks, MCP and skills
  • Defining subagents for code review, research or test generation
  • Using hooks to enforce formatting, linting or checks before and after tool calls
  • Connecting MCP servers for issue trackers, databases or internal documentation
  • Creating custom slash commands and skills for recurring team workflows
Module 4 Git workflows, testing and quality assurance
  • Creating branches, meaningful commits and pull requests with Claude Code
  • Test-first work: have tests written before the implementation
  • Reviewing diffs systematically and rejecting or refining changes
  • Organising parallel work with Git worktrees and multiple sessions

Day 2

Module 5 Headless operation, CI and security
  • Running Claude Code non-interactively in scripts and CI pipelines
  • Automated reviews and issue handling in GitHub or GitLab workflows
  • Configuring permission modes, allow and deny rules, and sandboxing
  • Handling secrets, prompt injection risks and organisation-wide policies
Module 6 Practice lab: API Development
  • Generating OpenAPI specs
  • Generating servers and clients
  • Building contract tests
  • Detecting breaking changes
  • Reviewing API security
  • Opening APIs to AI agents
Module 7 Data protection, quality & transfer to daily work
  • APIs frequently carry personal and confidential data: you learn to create specifications and sample data without real customer records, keep API keys and tokens out of the AI context and apply data protection by design under the GDPR as well as NIS2 requirements.
  • Ground rules for safe AI use in your team
  • Checking results: facts, sources, tests and the four-eyes principle
  • Personal action plan for the next 30 days
  • Open questions, outlook and resources for further learning

Practical scenarios from your field

Generating OpenAPI specs

Draft complete OpenAPI specifications with schemas, examples, error objects and security schemes from requirements, domain models or existing code, and check them against your style guide rules.

Generating servers and clients

Derive controller scaffolding, validation logic and type-safe client SDKs for several languages from a specification, keeping generated parts cleanly separated from hand-written business logic. Regenerating after spec changes is simple.

Building contract tests

Define consumer-driven contracts, generate test cases for edge values, error paths and authentication, and run them automatically in CI against both the specification and the live implementation.

Detecting breaking changes

Compare two versions of a specification, identify incompatible changes, write migration notes for consumers and plan deprecation strategies using versioning and sunset headers. The check runs on every pull request.

Reviewing API security

Analyse endpoints for typical weaknesses from the OWASP API Security Top 10, such as broken object-level authorisation, mass assignment or missing rate limits, and propose fixes.

Opening APIs to AI agents

Expose existing interfaces as MCP servers or tool definitions, phrase descriptions and parameters so agents use them correctly and scope permissions so agents can only perform approved actions.

Possible hands-on projects

API linter with house rules

A command-line tool that checks OpenAPI files against your design guidelines and posts clear improvement suggestions directly on the pull request.

Mock server from spec

A small service that generates realistic sample responses from a specification so frontend teams can work in parallel with backend development.

MCP server for an internal API

An MCP server that exposes selected endpoints of an internal REST API as tools for AI assistants, with authentication and logging.

Prerequisites

You have hands-on programming experience in at least one language and are comfortable with Git and the command line. You build backend applications in a mainstream language such as Java, C#, TypeScript, Python or Go and understand HTTP, JSON and REST fundamentals.

Technical requirements

Your own laptop with admin rights, Git, a Node.js runtime and an up-to-date editor; a Claude subscription or Anthropic API access is required for the exercises.

Data protection & compliance

APIs frequently carry personal and confidential data: you learn to create specifications and sample data without real customer records, keep API keys and tokens out of the AI context and apply data protection by design under the GDPR as well as NIS2 requirements.

Suggested dates

All dates are suggestions – your preferred date is always possible.

  • Thu, 26 November 2026 – Fri, 27 November 2026 Online Request
  • Thu, 10 December 2026 – Fri, 11 December 2026 Stuttgart Request
  • Wed, 13 January 2027 – Thu, 14 January 2027 Online Request
  • Wed, 20 January 2027 – Thu, 21 January 2027 Berlin Request
  • Wed, 3 February 2027 – Thu, 4 February 2027 Online Request
  • Thu, 18 February 2027 – Fri, 19 February 2027 Munich Request

Frequently asked questions

How is Claude Code different from traditional code completion?

Code completion suggests the next few lines, whereas Claude Code acts as an agent that handles whole tasks: it searches the repository, plans changes across several files, runs tests and commands, and corrects itself based on the results. You define the goal and review the outcome instead of steering every single line yourself.

Is Claude Code secure enough for enterprise use?

By default, Claude Code asks for approval before editing files or running commands. Permission rules, sandboxing, managed settings and hooks let you define precisely what the agent may do. During the course you learn to configure these mechanisms to match your security and data protection requirements and to assess risks such as prompt injection.

Does Claude Code work with my language and tech stack?

Yes. Claude Code is language-agnostic because it works with files, terminal commands and your existing build and test tooling. Whether you use Python, Java, TypeScript, Go, SAP-related code or infrastructure as code, what matters most is a well-written CLAUDE.md describing your commands and conventions. Each course variant adds the relevant domain focus.

Is spec-first still worth it when AI writes code so quickly?

More than ever. A precise specification is the best context you can give an AI assistant: it pins down data structures, error cases and security requirements, serves as a contract for consumers and underpins your tests. Without one, AI quickly produces inconsistent endpoints. In the course you use the spec as the single source for generation and validation.

What is the difference between a REST API and an MCP server?

A REST API is aimed at developers and applications, whereas an MCP server exposes capabilities in a standardised format for AI assistants and agents, including descriptions the model can interpret. An MCP server is often a thin layer on top of existing APIs. You learn when that step pays off and how to implement it securely.

How much does “Claude Code for API Developers” cost?

The course costs a flat €949 plus VAT per participant – whether online or on-site. This includes 2 training day(s) with a live trainer, course materials, a lab environment and a certificate of attendance.

Can I suggest my own date?

Yes. Our suggested dates are just a guide. In the request form you can always describe your preferred date or period in free text – we check availability and confirm within one working day.

Is the course online or on-site?

Both are possible: live online in a virtual classroom or on-site in Munich, Salzburg, Berlin, Augsburg, Hanover, Bremen, Stuttgart or Kaiserslautern. We can also run the course exclusively for your team.

More courses for API Developers

More Claude Code courses

All 77 Claude Code courses

Claude Code · MunichClaude Code · SalzburgClaude Code · BerlinClaude Code · AugsburgClaude Code · HanoverClaude Code · BremenClaude Code · StuttgartClaude Code · KaiserslauternClaude Code · Online