Building Reliable Retrieval for AI Agents

A practice-oriented webinar on how RAG works, what is agentic search, different retrieval strategies and how to choose tools that suit your business goals.

Many enterprises have started integrating AI agents into their workflows. But the retrieval infrastructure powering these agents - vector search, RAG pipelines, search APIs - was designed for a simpler era. As agents take on complex research tasks across thousands of documents, teams are hitting the same walls: lost context, compounding hallucinations, and costs that spiral at scale.

This workshop gives technical teams a clear-eyed view of what retrieval approaches currently exist, how they differ, their advantages and disadvantages, and what’s emerging. Grounded in real production experience.

More specifically, participants will learn

• How retrieval works under the hood of AI agents - from basic keyword search to vector embeddings to agentic search pipelines
• RAG architectures in practice: how they’re built, where they work well, and where they start to break down (context fragmentation, hallucination propagation, cost at scale)
• The chunking problem: why splitting documents into pieces loses connections, and what the trade-offs are between chunk size, precision, and context
• Alternative retrieval strategies: graph-based retrieval, hybrid approaches, re-ranking, and how each handles different query complexity levels
• Choosing the right tool for the job: a practical decision framework for matching retrieval strategy to business requirements, data volume, and accuracy needs

Target audience

This webinar especially targets Technical Leads, Developers and eyerybody who wants to learn about modern Retrieval techniques. Particpants are expected to have knowledge of general RAG techniques and hands-on experience in bullding and planning AI projects. 

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

Particpants are expected to have knowledge of general RAG techniques and hands-on experience in bullding and planning AI projects. 

Agenda

16:00   Welcome & Presentation of AI Factory Austria AI:AT

16:05   Building reliable retrieval for AI agents

17:05   Questions & Discussion

Speakers

Xenia Galkina (AI BASELINE)
Xenia is the CEO & Co-founder of AI baseline. She brings over 7 years of experience building AI products. She led graph-based knowledge systems and information retrieval at BenevolentAI, a drug discovery unicorn, and built AI search infrastructure for media organisations. She is a second-time founder.

Alexander Czech (AI BASELINE)
Alexander is the CTO & Co-founder of AI baseline. His background is rooted in academic research on spatial information representation. He built RAG infrastructure serving over 4,000 users across finance and government, and designed AI Baseline's graph-native retrieval architecture.

Language

English

Date, time, and location

20.05.2026, 16:00 – 17:15 (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.

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).