|
Date:
|
26 November 2026, 10:00 – 12:00 (CET)
|
Price:
|
Free (for eligible participants)
|
|
|
Format:
|
AI:AT Webinar, ONLINE (Zoom)
|
Target audience:
|
Industry, public admin, academia
|
|
|
Language:
|
English
|
Organizer:
|
AI:AT
|
See how current local, open-weight, and commercial AI coding tools compare on the same live coding tasks. Examine what they can do, how much control and privacy they offer, what infrastructure they require, and how much supervision they need.
Choosing among current AI coding tools often means weighing the capabilities of commercial systems against the control and privacy offered by local alternatives. These differences can be difficult to judge from benchmarks and product claims alone.
This webinar provides a practical comparison. A locally hosted open-weight model and a commercial system work on the same coding tasks using open Austrian weather data. The demonstrations progress from one-shot generation to plan-driven development, reusable project instructions, and an agent-driven bug fix verified by tests.
The comparison shows what each setup can do, where correction is required, and how the level of human supervision changes with the task. These observations are considered alongside infrastructure, privacy, speed, cost, setup effort, verification, and security. This webinar provides a practical basis for deciding which approach fits different requirements and constraints.
Learning outcomes:
- Understand how AI coding models connect to repositories, terminals, and development tools.
- Judge realistically what open-weight and local models can do across one-shot, plan-driven, skill-driven, and agent-driven workflows.
- Recognize the main trade-offs between local and commercial systems, including quality, speed, cost, privacy, setup effort, and safety.
Target audience
Anyone exploring current AI coding tools who wants greater control over their workflows, infrastructure, and privacy.
This webinar is open and free of charge for all participants from academia, industry, and public administration from EU and/or EuroHPC JU member countries.
Entry level & prerequisites
Basic programming experience; no prior experience with AI coding tools required.
Agenda
Welcome & Presentation of AI Factory Austria AI:AT
AI-assisted coding landscape; how models work; verification; local and commercial setups
- Level 1 — One-shot generation
- Level 2 — Plan-driven feature development
- Level 3 — Skill-driven reuse of project conventions
Break (15 min)
- Level 4 — Agent-driven, test-verified complex task
Comparison: quality, speed, cost, privacy, and setup effort
Risks and safeguards: overtrust, data and IP, and prompt injection
Durable workflows and setup guidance
Questions & Discussion
Speakers
Mehmet Alper Kuyumcu (AIT Austrian Institute of Technology)
Mehmet Alper Kuyumcu is a Scientist at the AIT Austrian Institute of Technology. He holds a master’s degree in Simulation Sciences from RWTH Aachen University. His research focuses on efficient numerical methods and parallel computing for power-system analysis. His work focuses on accelerating Newton–Raphson power-flow calculations. He brings this scientific-computing perspective to evaluating current AI coding tools.
Language
English
Date, time, and location
26.11.2026, 10:00 – 12:00 (CET), LIVE ONLINE WEBINAR (Zoom)
Registration
Registration is required, the link to the registration form can be found on the top of this page in the menu on the left. Please register with your official institutional email address to prove your affiliation.
You will get the Zoom link in the automatic confirmation by email (subject starting with „[Indico] Registration“), please check your Spam/Junk folders). We will also send 1–2 reminders before the webinar.
Please do not hesitate to contact us at training@ai-at.eu if you have any questions.
Modification, withdrawal & no-show policy
Your registration is binding. Please only register for the course if you are really going to attend.
You can update your registration data or withdraw your registration anytime before the registration form has been closed via the link „Manage my registration“ which you can find at the bottom of your automatic email confirmation (subject starting with „[Indico] Registration“).
Alternatively, or after the registration form has been closed, please inform us about your cancelation or any change in your registration data (especially your mobile-phone number) via email (training@ai-at.eu).
No-show policy: If you do not cancel and do not show up at the course you will be blacklisted and excluded from future training events.
Organizers
This webinar is organized by AI Factory Austria AI:AT.
Acknowledgements
AI Factory Austria AI:AT has received funding from the European High-Performance Computing Joint Undertaking (JU) under grant agreement No 101253078. The JU receives support from the Horizon Europe Programm of the European Union and Austria (BMIMI / FFG).