| Start date: | 17 March 2026, 16:00 (CET) | Entry level: | Intermediate | |
| End date: | 18 March 2026, 18:00 (CET) | Subject area: | Artificial Intelligence (AI) | |
| Location: | ONLINE (Zoom) | Topics: | Agentic AI, Data Sovereignty | |
| Language: | English | Target audience: | Academia, industry, public admin | |
| Price: | Free (for eligible participants) | Organizers: | AI:AT |
European organizations handle sensitive documents daily, e.g., contracts, financial reports, research data, patient records. Artificial Intelligence (AI) can now read, extract, and process these documents automatically. But where does that data go? Who trains their model with that data? Learn how to build agentic AI solutions to handle documents without compromising security, compliance, or control.
The EU AI Act mandates transparency, auditability, and data governance. European organizations need sovereign AI solutions that satisfy compliance today, not after an audit finds gaps.
This workshop shows you how to build agentic AI systems that handle documents with European data sovereignty, i.e., your data stays in the EU, is never used for model training, and you maintain full audit trails for compliance.
You'll learn two approaches:
- EU-hosted AI platforms: GDPR-compliant, zero data retention, no model training on your inputs
- Fully local deployment: run everything on your own infrastructure for maximum control
By the end of this workshop, you will have:
- a fully functional ready-to-use AI document-processing system
- know-how in EU data sovereignty vs. US cloud risks
- the ability to evaluate and build compliant AI workflows
- an understanding what audit trails you need and how to implement them for EU AI Act readiness
Agenda & Content
For a detailed timetable and additional information, please see Agenda & Content in the left menu.
Target audience, eligibility & prices
Researchers, data scientists, ML engineers, and domain experts who want to:
- handle sensitive documents (legal, financial, medical, research) and want AI automation
- need European data sovereignty, i.e., data must stay in EU and must not be used for training
- want to understand their options before committing to a platform or architecture
- are preparing for EU AI Act compliance requirements
- want to move from "AI is a chatbot" to "AI processes my documents"
This course 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
Intermediate – Basic familiarity with machine learning concepts is expected.
- participants are expected to have basic understanding of LLMs (prompting, chat interfaces)
- no coding skills required, all exercises use configuration files and natural language.
- no special hardware required, hands-on exercises use EU-hosted cloud platforms
- for participants interested in the fully local track a laptop with 16GB+ RAM is recommended
Costs: Hands-on exercises use Langdock, a commercial EU-hosted platform. Expect nominal costs of approximately 2–3 € for the workshop duration. Fully local alternatives (free) will be provided.
Course format
This course will be delivered as a LIVE ONLINE COURSE (using Zoom).
Hands-on labs
Hands-on exercises can be performed using Langdock, a commercial EU-hosted platform or completely local. For participants interested in the fully local track a laptop with 16GB+ RAM is recommended.
All participants will work with real document processing scenarios:
- set up Clawdbot with European data sovereignty guarantees (via Langdock)
- process sample documents (contracts, invoices) and extract structured data
- build a reusable agentic workflow for document processing
- understand the audit trail and see exactly where your data went
Two tracks are available:
- Track A: EU-hosted platform (Langdock): works from any browser, ~2–3 € cost
- Track B: Fully local setup (Ollama + open models) on your own machine (free).
Accepted participants will be contacted a few days before the course and might be asked to do a short pre-assignment that has to be completed before the course starts.
Lecturer
Dejan Đukić (External)
Dejan Đukić is an AI Software Expert with an extensive background in computer vision (cloud and edge), bioinformatics, and agentic AI systems. He holds a Master’s degree in Life Science Informatics from Rheinische Friedrich-Wilhelms-Universität Bonn and is experienced in building production CV pipelines in clinical, medical device, and manufacturing startup environments.
Language
English
Date, time, and location
17.–18.03.2026, 16:00 – 18:00 (CET), LIVE ONLINE COURSE (Zoom)
Registration
Registration is required, the registration form can be found on 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 an automatic confirmation by email (subject starting with "[Indico] Registration"), please check your Spam/Junk folders.
Following your successful registration, you will receive further information a few days before the course.
Please do not hesitate to contact us at training@ai-at.eu if you have any questions.
Waitinglist
After the number of registrations has reached its maximum or the registration form has been closed, you may want to send us an email (training@ai-at.eu) stating that you are interested to be put on the waiting list (vacancies may occur due to cancelations, etc.).
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 course 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).
