Training course · AI Agent Development · DevOps & Cloud

AI Agent Development for DevOps and Cloud Teams

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 DevOps & Cloud. 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.

DevOps and cloud teams own infrastructure as code, CI/CD pipelines, monitoring, cost control and security – often across several cloud providers and on-premises environments. Much of the work is configuration in HCL, YAML and shell, troubleshooting through logs and cross-checking documentation. AI coding assistants and agents speed up exactly that: they write reusable Terraform modules, fix failing pipelines, create Ansible roles, analyse incident logs and propose cost optimisations. At the same time the stakes are high, because a single wrong command can hit production. This course teaches you to use agents productively with clear permission boundaries, plan-and-review workflows and safeguarded environments.

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?

  • DevOps engineers and platform teams
  • Cloud architects working with AWS, Azure or Google Cloud
  • Site reliability engineers responsible for operations and incidents
  • System administrators moving towards infrastructure as code
  • Developers who maintain their own CI/CD pipelines

Typical challenges we address

  • Growing volumes of Terraform, YAML and pipeline configuration with drift and duplication
  • Time-consuming troubleshooting of failing pipelines and distributed logs
  • Rising cloud costs without clear visibility
  • High demands on security, compliance and traceability of changes

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.
  • Use AI agents safely for infrastructure as code, pipelines and configuration management.
  • Analyse incidents, pipeline failures and cloud costs faster with AI support.
  • Define permission boundaries and approval processes so agents cannot make uncontrolled changes to production.

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: DevOps & Cloud
  • Developing Terraform modules
  • Fixing CI/CD pipelines
  • Ansible and configuration management
  • Incident analysis
  • Optimising cloud costs
  • Policy as code and hardening
Module 7 Data protection, quality & transfer to daily work
  • Agents with access to cloud accounts and pipelines are a security matter: work with least privilege, separate environments and human approval, and keep cloud credentials, state files and secrets out of prompts. Operators of essential and important services must also meet NIS2 requirements on risk management, supply-chain security and traceability of changes.
  • 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

Developing Terraform modules

The agent creates reusable Terraform or OpenTofu modules with variables, validations and outputs, runs fmt, validate and plan, and explains every planned change before a human approves the apply.

Fixing CI/CD pipelines

Failed GitHub Actions, GitLab CI or Azure DevOps runs are analysed from their logs, root causes such as caching issues or missing permissions identified and corrected pipeline definitions proposed.

Ansible and configuration management

The AI writes idempotent Ansible roles, templates and inventories, replaces fragile shell scripts and adds Molecule tests so configuration stays reproducible. Existing roles are gradually standardised along the way.

Incident analysis

Logs, metrics and alerts from monitoring are brought together, a timeline reconstructed, likely causes narrowed down and a draft postmortem with actions produced. The team keeps the final judgement.

Optimising cloud costs

The assistant reviews cost reports and resource definitions, finds oversized instances, orphaned volumes or missing lifecycle rules and drafts the matching IaC changes. Each recommendation includes estimated savings.

Policy as code and hardening

IaC code is scanned with tools such as Checkov or tfsec, findings are fixed and rules for encryption, tagging or network access are expressed as policy as code.

Possible hands-on projects

Drift detector

A script that regularly runs terraform plan across several environments, detects drift and posts a summary to a chat channel.

Pipeline template library

Reusable CI/CD templates for build, test, security scanning and deployment, documented and accompanied by sample projects. Teams adopt them with just a few lines of configuration.

Cost report tool

A CLI that pulls cost data from a cloud account, breaks it down by tags and teams and clearly highlights optimisation candidates.

Prerequisites

Solid programming skills in Python or TypeScript, experience with REST APIs and some hands-on experience with LLM APIs or AI assistants. Practical experience with Linux, Git and at least one cloud platform, plus a working knowledge of Terraform, containers and CI/CD.

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

Agents with access to cloud accounts and pipelines are a security matter: work with least privilege, separate environments and human approval, and keep cloud credentials, state files and secrets out of prompts. Operators of essential and important services must also meet NIS2 requirements on risk management, supply-chain security and traceability of changes.

Suggested dates

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

  • Wed, 25 November 2026 – Thu, 26 November 2026 Online Request
  • Thu, 10 December 2026 – Fri, 11 December 2026 Salzburg Request
  • Tue, 15 December 2026 – Wed, 16 December 2026 Online Request
  • Mon, 18 January 2027 – Tue, 19 January 2027 Bremen Request
  • Thu, 4 February 2027 – Fri, 5 February 2027 Online Request
  • Thu, 18 February 2027 – Fri, 19 February 2027 Augsburg 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.

Should an AI agent be allowed to apply infrastructure changes itself?

That is something to limit deliberately. A proven workflow has the agent write code and run plan, a human review the result and the apply run through the regular pipeline. On the course you learn to design permissions, sandbox environments and approvals so that production systems stay protected.

Which cloud platform does the course use?

The methods are vendor-neutral and transfer to AWS, Azure and Google Cloud. Exercises use examples you can reproduce with local tooling or test accounts. You are welcome to bring scenarios from your own platform, provided no production credentials are used.

How much does “AI Agent Development for DevOps and Cloud Teams” 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 DevOps and Cloud Teams

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