Learning Path · Module 05 · AI Enthusiast

Agentic AI | Basics

As early as 2025, the year of "AI agents" was proclaimed as the next evolutionary stage of GenAI. Agents possess a memory, can perform tasks autonomously, formulate plans, write code, and collaborate with one another. This training demonstrates the opportunities and risks of using AI agents to increase efficiency and automate complex problem-solving, and prepares participants for the skillset required to successfully keep AI agents and their token hunger in check.

Who is this training for?

Interested parties who wish to acquire further competencies in this topic.

Why this training

AI models, especially the language models underlying AI agents, are not deterministic. Consequently, the quality of the work produced by AI agents varies greatly and can only be ensured if the underlying functionality is understood. Otherwise, there is a risk of efficiency loss instead of gain, and token costs will skyrocket.

Contents

  • Introduction to Large vs. Small Language Models
  • Introduction to a simple agentic harness architecture
  • Introduction to the quality requirements for prompt engineering
  • Introduction to the Model Context Protocol (MCP)
  • Practical examples of AI agents (e.g., for quality assurance along guidelines)

Methodology

  • Online presentation with examples
  • Q&A between individual chapters

Your trainers

Thomas Immich, Managing Director · Head of Digital Solutions

Thomas Immich

Managing Director · Head of Digital Solutions · Dipl. Computer Scientist (FH)

At a glance

Format
Live-Online-Talk
Duration
4 h (1x4h)
Group
6–12 pers.
Level
Awareness
Station
AI Enthusiast
Price
On request
Request in-house training

No obligation - we reply within 24 hours.

Ready for your next step?

Bring this format straight into your team - tailored to your tools, your roles and your context for human-centered AI.

Request in-house training

More formats for AI Enthusiast

Prompt Engineering | Basics

03

Awareness

Prompt Engineering | Basics

The training offers a wide spectrum, from the basics of prompt engineering to insider tips and tricks for professional prompts in the own domain. Prompting frameworks such as C.R.I.S.P.E., A.P.E., or R.A.C.E. and their use in daily UX work, combined with their application in various models like ChatGPT, Claude, or MS Copilot, will be covered. Participants will gain confidence in prompting and also learn how to create, reuse, and share prompt templates with colleagues.

8 h Live-Online-Workshop max. 12 pers.
Low-Code for No-Coders | Basics

04

Awareness

Low-Code for No-Coders | Basics

Whether it is AI usage, vibe-coding, automation, or the technically-feasible specification of requirements: nowadays, one repeatedly reaches a point where a basic understanding of coding is crucial to effectively achieve one's goals within a team. This training therefore introduces the basics of low-code and specifically addresses people who have had little to no programming knowledge so far.

4 h Live-Online-Talk max. 12 pers.
Metrics, Objectives & KPI | Basics

06

Awareness

Metrics, Objectives & KPI | Basics

Participants will learn how to make successes and failures measurable and visible for their stakeholders. An overview of common success metrics and KPIs will be provided, and the advantages of usage data tracking and evaluation will be highlighted.

2 h Live-Online-Talk max. 12 pers.

Everything starts with a good conversation.

So let's explore the possibilities for your digital product development together. We look forward to your inquiry.

Thomas Immich

Managing Director · Head of Digital Solutions
Book appointment
+49 681 959 3110 contact@centigrade.de
Contact
Please enter a valid email address.
Please enter a message.
Please agree to the privacy policy.