High-Performance Computing Center Stuttgart

Making Waves with AI Agents: Practical Agentic AI and AI-Assisted Coding for SMEs and Start-ups

Agentic AI is rapidly changing how organisations explore automation, software development, data-driven decision-making, and digital innovation. Unlike standard chat-based AI tools, agentic AI systems can reason over tasks, interact with tools, use external information, and support users in planning, executing, and refining workflows.

This course provides an accessible and practical introduction to agentic AI for SMEs, start-ups, researchers, developers, and innovation teams. It is designed for participants who want to understand what agentic AI can realistically do, where it can create value, and how to decide which tools or approaches are suitable for their own organisational context.

The course introduces key concepts, tools, and frameworks in the agentic AI ecosystem, including LangGraph, OpenAI Agents SDK, Model Context Protocol (MCP), Claude Code, Cursor, Codex, and OpenCode. Participants will learn how agentic workflows differ from standard AI assistants, where they may be useful, and what limitations, risks, and decision points should be considered before implementation.

The course is structured in three parts. The first part introduces the fundamentals of agentic AI, including key concepts, motivations, tools, and frameworks. The second part focuses on practical applications for SMEs and start-ups, highlighting business-relevant use cases and suitable entry points. The third part offers an optional hands-on session in which participants gain practical exposure to AI-assisted coding using OpenCode through a simple task/message board exercise.

SMEs and start-ups are especially encouraged to join us.

This event is co-organised by HammerHAI and EPCC.

Location

Online course
Organizer: HLRS, University of Stuttgart, Germany

Start date

Sep 01, 2026
10:30

End date

Sep 01, 2026
13:30

Language

English

Entry level

Basic

Intermediate

Course subject areas

Data in HPC / Deep Learning / Machine Learning

Topics

Artificial Intelligence

Python

Back to list

Prerequisites and content levels

Prerequisites

For the optional hands-on session, participants should have:

  • A laptop on which they can install and run local tools.
  • Basic familiarity with using a terminal or command-line interface.
  • Willingness to interact with an AI coding tool by describing tasks, reviewing outputs, and iterating on results.

Recommended, but not required:

  • Basic Git usage.
  • Basic understanding of APIs, automation workflows, or scripting.
  • Prior experience with ChatGPT, Claude, Cursor, Claude Code, Codex, OpenCode, or similar AI tools.
  • Basic familiarity with Python and uv, a package and project manager.
  • No GPU programming knowledge is required.

Content levels

  • Beginners: 2 hours
  • Intermediate: 1 hour

Learn more about course curricula and content levels.

Target audience

This course is intended for, but not limited to:

  • SMEs and start-ups interested in understanding where agentic AI can create practical business value.
  • Managers, project leads, and innovation teams who need a practical framework for deciding whether to use general AI tools, automation tools, custom agents, coding agents, or vendor solutions.
  • Researchers, engineers, and developers who want an overview of agentic AI concepts, tools, and frameworks without requiring deep technical expertise.

Learning outcomes

After completing this course, participants will be able to:

  • Explain what agentic AI is and how it differs from standard AI assistants or chat-based tools.
  • Recognise key concepts, tools, and frameworks in the agentic AI ecosystem, including LangGraph, OpenAI Agents SDK, MCP, Claude Code, Cursor, Codex, and OpenCode.
  • Identify concrete low-barrier use cases for SMEs and start-ups.
  • Apply a basic Build vs. Buy vs. Configure decision framework to choose between generative AI tools, automation tools, custom agents, coding agents, and vendor solutions.
  • Gain practical exposure to AI-assisted coding through an optional hands-on exercise using OpenCode.

Instructors

Charaka Palansuriya (EPCC), c.palansuriya(at)epcc.ed.ac.uk,
Jaison Lewis (GWDG) jaison.lewis(at)gwdg.de, and
Junghwa Lee (HLRS) junghwa.lee(at)hlrs.de

Agenda

  • Part 1: Introduction to agentic AI — key concepts, motivation, tools, and frameworks such as LangGraph, OpenAI Agents SDK, MCP, Claude Code, Cursor, Codex, and OpenCode
  • Part 2: Agentic AI for SMEs and start-ups — why it matters, what business problems it can solve, and how to get started with practical use cases and suitable tools
  • Part 3: Hands-on session — AI-assisted prototyping with OpenCode using a simple task/message board exercise

Registration information

Apply for this course via the button at the top of this page.

Registration closes on August 25, 2026.

Late applications may still be accepted depending on course capacity. 

Fees

This course is free of charge.

Contact

Junghwa Lee (HLRS), phone 0711 685 87228, training(at)hlrs.de

Further courses and training team

See the training overview and the Supercomputing Academy pages.
See also information about the HLRS training department and staff.

HLRS Training Collaborations in HPC and AI

HLRS is part of the Gauss Centre for Supercomputing (GCS), together with JSC in Jülich and LRZ in Garching near Munich. SIDE is the German National Competence Centre (NCC) for High-Performance Computing. HLRS is also a member of the Baden-Württemberg initiative bwHPC. 
Since 2025, HLRS has been coordinating one of the AI Factories of the EuroHPC JU: HammerHAI. 

This event is offered as part of HammerHAI, Germany’s first AI Factory, which has a dedicated focus on industry, manufacturing, engineering, and research. HammerHAI provides AI resources and solutions, an upcoming AI-optimized supercomputer, and personalized expert support for AI users at all stages in the AI lifecycle. This project has received funding from the European High Performance Computing Joint Undertaking under grant agreement No. 101234027. This project is co-funded by the European Commission, the German Federal Ministry of Research, Technology and Space (BMFTR), the Baden-Württemberg Ministry of Science, Research and the Arts, the Bavarian State Ministry of Science and the Arts and the Lower Saxony Ministry of Science and Culture.

Related training
All training

Jul 14 - 17, 2026

Stuttgart

English

Multi-GPU Deep Learning (cancelled)

Jul 20 - 22, 2026

Online

English

European Agentic AI Bootcamp

Sep 07 - Oct 09, 2026

Online (flexible)

English

Supercomputing Academy: Deployable Data Analysis & AI Pipelines with HPC

Oct 06 - 29, 2026

Hybrid, Stuttgart

English

European AI Hackathon

Nov 16 - Dec 04, 2026

Hybrid, Stuttgart

English

Hackathon: Porting and Optimization for Hunter

Back to list

High-Performance Computing Center Stuttgart Nobelstraße 19, 70569 Stuttgart, Germany

Contact & Location

+49 711 685-87269 info(at)hlrs.de

A member of the Gauss Centre for Supercomputing, HLRS is one of three German national centers for high-performance computing.

www.gauss-centre.eu

HLRS is a central unit of the University of Stuttgart.

www.uni-stuttgart.de/en/

© 2026 HLRS. All rights reserved.