Training course · AI Agent Development · Citizen Developers & Low-Code

AI Agent Development for Citizen 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

“AI Agent Development for Citizen Developers” is a hands-on course for roles such as Business users with automation ideas in administration, sales, procurement or HR, Power users of Excel, Power Platform or similar low-code tools and Process owners and business analysts. Rather than learning AI Agent Development in the abstract, you work on tasks from your daily routine – with examples, exercises and templates from Citizen Developers & Low-Code.

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.

Citizen developers are business users who build their own applications and automations without being professional software engineers. Until recently, low-code platforms quickly hit their limits whenever custom logic, integrations or data transformations were needed. AI coding tools push that boundary much further: a plain-language description becomes forms, workflows, scripts and small web apps, and AI explains error messages, formulas and expressions in understandable terms. Responsibility grows at the same time, because home-built solutions also process company data and need maintenance. In this course you learn to use vibe coding and AI agents to build useful solutions for your department, combine them sensibly with low-code platforms and stay within your IT governance rules.

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?

  • Business users with automation ideas in administration, sales, procurement or HR
  • Power users of Excel, Power Platform or similar low-code tools
  • Process owners and business analysts
  • Members of digitalisation and innovation teams
  • IT leads setting up a citizen development programme

Typical challenges we address

  • Recurring manual tasks that IT has no capacity to automate
  • Low-code platforms hit limits with custom logic, integrations or data preparation
  • Little know-how on testing, documenting and running solutions safely
  • Risk of shadow IT without alignment with data protection and IT security

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.
  • Build your own automations, forms and small applications for your department with AI support.
  • Combine low-code platforms with generated code for logic, data preparation and integrations.
  • Document, test and run your solutions in line with your IT governance rules.

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: Citizen Developers & Low-Code
  • Automating workflows
  • Building forms and small apps
  • Explaining formulas and expressions
  • Cleaning and transforming data
  • Connecting to interfaces
  • Documenting and testing solutions
Module 7 Data protection, quality & transfer to daily work
  • Home-built solutions also process company and employee data: you learn to respect GDPR requirements, IT approval processes, secure handling of credentials and the licence terms of platforms and generated code, so that no shadow IT emerges.
  • 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

Automating workflows

Describe approval processes, notifications and data transfers between email, spreadsheets, forms and business applications on low-code platforms, and have AI build the matching flows, expressions and conditions.

Building forms and small apps

Generate data entry forms, checklists or booking apps from a description, complete with validation, mandatory fields and simple data storage, and refine them step by step based on colleagues’ feedback.

Explaining formulas and expressions

Have complex Excel formulas, Power Fx or flow expressions explained in plain terms, track down errors and reliably write new calculations from a business description.

Cleaning and transforming data

Merge exports from different systems, remove duplicates, standardise formats and generate Python scripts or Power Query steps that make the preparation repeatable. Monthly preparation then takes minutes, not hours.

Connecting to interfaces

Use AI to understand how a REST interface works, configure connectors and set up simple API calls that bring data from business systems into your own solutions.

Documenting and testing solutions

Produce user guides, short technical documentation and test cases for home-built applications so colleagues and IT can understand, take over and keep running the solution.

Possible hands-on projects

Leave and cover planner

A small web app where team members enter absences, assign cover and give the team lead a monthly overview. Overlaps are flagged automatically.

Incoming invoice checker

A script that reads incoming PDF invoices, checks mandatory details and transfers the data into a structured spreadsheet for approval.

Request tracker

A simple ticketing tool for internal requests with a form, status history, assignments and automatic email notifications. Everyone keeps track of open and completed requests.

Prerequisites

Solid programming skills in Python or TypeScript, experience with REST APIs and some hands-on experience with LLM APIs or AI assistants. You are confident with office applications and spreadsheets; no programming skills are required, though experience with a low-code platform helps.

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

Home-built solutions also process company and employee data: you learn to respect GDPR requirements, IT approval processes, secure handling of credentials and the licence terms of platforms and generated code, so that no shadow IT emerges.

Suggested dates

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

  • Wed, 25 November 2026 – Thu, 26 November 2026 Online Request
  • Tue, 8 December 2026 – Wed, 9 December 2026 Bremen Request
  • Thu, 21 January 2027 – Fri, 22 January 2027 Salzburg Request
  • Thu, 4 February 2027 – Fri, 5 February 2027 Online Request
  • Mon, 8 February 2027 – Tue, 9 February 2027 Kaiserslautern Request
  • Wed, 17 February 2027 – Thu, 18 February 2027 Online 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 to work with AI as a citizen developer?

No. You describe what your solution should do and the AI generates forms, flows, formulas or scripts. What matters is stating your requirements clearly and checking results systematically. In the course you learn the essential concepts such as data, logic, interfaces and testing so you can steer precisely and narrow down errors yourself.

How do we avoid shadow IT?

With clear rules rather than bans: approved platforms and tools, defined data classes, a simple register of home-built solutions and a route for handing over to IT once an application becomes business-critical. In the course you learn to apply such rules, and IT leads gain ideas for setting up a citizen development programme.

How much does “AI Agent Development for Citizen 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 Citizen 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