Training course · AI Agent Development · Test Automation & QA

AI Agent Development for Test Automation and QA

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

“AI Agent Development for Test Automation and QA” is a hands-on course for roles such as Test automation engineers and SDETs, QA engineers and test managers and Developers responsible for test suites. Rather than learning AI Agent Development in the abstract, you work on tasks from your daily routine – with examples, exercises and templates from Test Automation & QA.

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.

Quality assurance is under pressure: release cycles are getting shorter, applications more complex, and AI-assisted coding produces more code in less time – all of which needs testing. Test automation engineers and QA professionals therefore benefit particularly from AI assistants and agents. These tools derive test cases from user stories and acceptance criteria, write Playwright or Cypress tests with robust selectors, generate API tests from OpenAPI specifications, analyse flaky tests and build test data generators. At the same time the role is shifting: QA becomes the function that systematically safeguards AI-generated code too. This course teaches you to use AI for test design, automation and failure analysis and to adapt your test strategy to the new pace of development.

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?

  • Test automation engineers and SDETs
  • QA engineers and test managers
  • Developers responsible for test suites
  • Business testers moving into automation

Typical challenges we address

  • Unstable end-to-end tests with timing issues and fragile selectors
  • High effort for test case creation, maintenance and test data
  • Gaps in coverage of APIs, edge cases and failure scenarios
  • Growing volumes of AI-generated code that need targeted safeguarding

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.
  • Derive test cases systematically from requirements with AI and automate them in Playwright, Cypress or API tests.
  • Analyse flaky tests and coverage gaps with AI support and fix them for good.
  • Adapt your test strategy to AI-assisted development and safeguard generated code in a targeted way.

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: Test Automation & QA
  • Deriving test cases from requirements
  • Writing Playwright and Cypress tests
  • Analysing flaky tests
  • API tests from specifications
  • Generating test data
  • Coverage and mutation testing
Module 7 Data protection, quality & transfer to daily work
  • Test data should be synthetic or effectively anonymised, as production data containing personal information must not be used unprotected in test environments or prompts (GDPR). Credentials for test systems belong in secret stores rather than test code, and in regulated sectors test results must be traceable and documented, for example as evidence under NIS2 or the Cyber Resilience Act.
  • 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

Deriving test cases from requirements

The assistant turns user stories and acceptance criteria into structured test cases with equivalence classes, boundary values and negative scenarios, optionally as Gherkin scenarios for behaviour-driven development.

Writing Playwright and Cypress tests

The AI writes end-to-end tests with role-based selectors, page objects or fixtures and proper waiting instead of fixed delays, and runs them iteratively until they are stable.

Analysing flaky tests

The agent examines test history, traces, screenshots and logs, identifies causes such as race conditions, test interdependencies or unstable test data, and proposes lasting fixes.

API tests from specifications

OpenAPI descriptions are turned into API tests for status codes, schemas, authentication and error cases, plus contract tests that surface interface changes between teams early.

Generating test data

The AI builds generators for realistic synthetic test data, factories and seed scripts that deliberately cover edge cases without relying on real personal data. Privacy issues in test environments are avoided.

Coverage and mutation testing

Coverage reports and mutation testing results are analysed, untested paths identified and missing tests added in a targeted way to increase the real value of the suite.

Possible hands-on projects

Flaky test report

A script that merges JUnit XML results from multiple CI runs, detects unstable tests and produces a prioritised list with failure patterns.

Test data generator

A CLI that creates realistic synthetic records, including edge cases, from a database schema or JSON schema. Data volume and distribution are fully configurable.

E2E suite for a demo app

A Playwright test suite with page objects, visual comparisons and CI integration, built by an AI agent for an existing web application.

Prerequisites

Solid programming skills in Python or TypeScript, experience with REST APIs and some hands-on experience with LLM APIs or AI assistants. Experience in software testing or test automation and a working knowledge of at least one programming language such as JavaScript, TypeScript, Python or Java.

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

Test data should be synthetic or effectively anonymised, as production data containing personal information must not be used unprotected in test environments or prompts (GDPR). Credentials for test systems belong in secret stores rather than test code, and in regulated sectors test results must be traceable and documented, for example as evidence under NIS2 or the Cyber Resilience Act.

Suggested dates

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

  • Thu, 26 November 2026 – Fri, 27 November 2026 Online Request
  • Mon, 7 December 2026 – Tue, 8 December 2026 Stuttgart Request
  • Mon, 18 January 2027 – Tue, 19 January 2027 Online Request
  • Tue, 26 January 2027 – Wed, 27 January 2027 Berlin Request
  • Tue, 9 February 2027 – Wed, 10 February 2027 Online Request
  • Tue, 23 February 2027 – Wed, 24 February 2027 Munich 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.

Do I need programming skills for this course?

A working knowledge of a programming language helps, since you should be able to read, understand and adapt generated tests. Business testers with little coding experience still benefit greatly, because the AI explains code and supports the move into automation. The exercises are designed to accommodate different levels of prior knowledge.

Will AI replace manual and exploratory QA?

No. AI automates recurring tasks such as test case creation, scripting and failure analysis, freeing up time for exploratory testing, risk assessment and acceptance. With AI-generated code in particular, the critical judgement of experienced QA professionals becomes more important, not less.

How much does “AI Agent Development for Test Automation and QA” 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 Test Automation and QA

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