Training course · AI Agent Development · API Development

AI Agent Development for API Developers

Build AI agents professionally: architectures, tool use, agent SDKs, LangGraph, memory, evals, guardrails and deployment.

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 AI Agent Development with the everyday processes of API Development. Participants work on realistic scenarios and leave with prompts, workflows and checklists they can use straight away.

AI agents go beyond conventional chatbots: they break tasks down, call tools and APIs, evaluate the results and keep iterating until a goal is met. In this two-day course you learn to build such systems so that they work reliably, transparently and safely in day-to-day business. You compare architectural patterns ranging from simple workflows through the agent loop to multi-agent systems, and you implement them hands-on with the Claude Agent SDK, the OpenAI Agents SDK and LangGraph.

The focus is not on a quick demo but on the path to production. You design tool interfaces and context deliberately, connect tools via the Model Context Protocol, plan short-term and long-term memory and build evaluations that surface regressions early. On top of that come guardrails against prompt injection and harmful actions, human-in-the-loop approvals, tracing, cost control and deployment. By the end you can judge when an agent is worthwhile, when a deterministic workflow is enough and which framework fits your project.

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 choose the right pattern for a task, from a fixed workflow to an autonomous agent.
  • You design tools and context so that agents work reliably and cost-effectively.
  • You implement agents with the Claude Agent SDK, the OpenAI Agents SDK or LangGraph.
  • You set up evaluations and tracing to measure quality and detect regressions.
  • 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 Agent architectures and design patterns
  • Workflows versus agents: prompt chaining, routing, parallelisation, orchestrator-worker
  • The agent loop: plan, act, observe, reflect
  • Multi-agent systems, subagents and handoffs between agents
  • Criteria for choosing model, framework and level of autonomy
Module 2 Tool use and context engineering
  • Function calling and structured outputs with JSON Schema
  • Designing good tools: granularity, naming, error messages, idempotency
  • Connecting and reusing tools via MCP servers
  • Managing the context window: summarisation, compaction, retrieval and prompt caching
Module 3 Frameworks in practice
  • Claude Agent SDK: agent loop, tools, subagents, permissions and hooks
  • OpenAI Agents SDK: agents, handoffs, guardrails and tracing
  • LangGraph: stateful graphs, checkpointing and human-in-the-loop
  • Side-by-side comparison on the same task and criteria for choosing a framework
Module 4 Memory, evals and observability
  • Short-term and long-term memory, storage strategies and forgetting
  • Evaluation datasets, LLM-as-a-judge and task-based success metrics
  • Tracing tool calls, token usage and latency
  • Regression testing when prompts, models or tools change

Day 2

Module 5 Guardrails, security and deployment
  • Protecting against prompt injection, data exfiltration and over-privileged tools
  • Input and output checks, approval steps and sandboxing
  • Deploying as a service, asynchronous execution, retries and cost limits
  • Governance, audit logging and requirements under GDPR and the EU AI Act
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

Solid programming skills in Python or TypeScript, experience with REST APIs and some hands-on experience with LLM APIs or AI assistants. 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

A laptop with Python or Node.js, Git and a code editor, plus API access to at least one LLM provider such as Anthropic or OpenAI. Credentials for the exercises can be provided if needed.

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.

  • Mon, 23 November 2026 – Tue, 24 November 2026 Online Request
  • Tue, 1 December 2026 – Wed, 2 December 2026 Kaiserslautern Request
  • Tue, 8 December 2026 – Wed, 9 December 2026 Online Request
  • Tue, 15 December 2026 – Wed, 16 December 2026 Bremen Request
  • Thu, 14 January 2027 – Fri, 15 January 2027 Online Request
  • Tue, 26 January 2027 – Wed, 27 January 2027 Salzburg Request

Frequently asked questions

Which agent framework should we use?

It depends on your model strategy, the level of control you need and your team’s skills. Vendor SDKs offer a lean start with tightly integrated features, while LangGraph gives you finer control over state and flow. In the course you solve the same task with several frameworks and derive clear selection criteria for your own project.

How do you stop an agent from taking wrong or dangerous actions?

With several layers of protection: narrowly scoped tools with minimal permissions, input and output validation, approval steps for critical actions, sandboxing and continuous evaluation. Prompt injection via external content is treated as a realistic threat. You practise these measures directly on your own agent.

Does every automation need an agent?

No. Many tasks are handled more reliably, cheaply and transparently by a fixed workflow of a few LLM calls. Agents pay off when the solution path cannot be planned in advance and the system must react flexibly to intermediate results. We train exactly this trade-off using practical examples.

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 “AI Agent Development 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 AI Agent Development courses

All 30 AI Agent Development courses

AI Agent Development · MunichAI Agent Development · SalzburgAI Agent Development · BerlinAI Agent Development · AugsburgAI Agent Development · HanoverAI Agent Development · BremenAI Agent Development · StuttgartAI Agent Development · KaiserslauternAI Agent Development · Online