Zürich AI Meetup

Agentic Autumn will be hosted in partnership with mesoneer AG

Agenda
- Luca Campanella (CuratedAI) - Agents lessons learned
- Max Buckley (Google) - Agentic RAG
- Dirk Budke (mesoneer) – Where Workflow Automation Ends and Agentic AI Begins

Agenda

• 17:00 – Doors open
• 17:00–17:30 – Snacks, drinks & networking
• 17:30–17:40 – Opening
• 17:40–18:15 – Luca Campanella (CuratedAI) – Agents: Lessons Learned
• 18:15–19:00 – Max Buckley (Google) – Agentic RAG
• 19:00–19:45 – Dirk Budke (mesoneer) – Where Workflow Automation Ends and Agentic AI Begins
• 19:45–21:00 – Additional Q&A & networking

Abstract:
Luca Campanella (CuratedAI) - Agents lessons learned
We build narrow, citation-first systems for lawyers: CuratedAI automates EU privacy work (review, research anchored to EUR-Lex/EDPB with daily updates, and privacy-notice drafting from live site scans), while Praven Intelekt serves Bulgarian practitioners with retrieval-based answers, drafting, and document analysis—always linked to the exact article/paragraph and without using client uploads to train AI.
In the talk, I’ll share lessons: when to pivot vs. persist, sales and locality, in-person vs. remote, workflows vs. agents, why robust RAG is hard (many moving parts), and the value of a tight test set for search.

Max Buckley (Google) - Agentic RAG
Beyond Single Shot Retrieval: Agentic RAG Systems
Retrieval-Augmented Generation (RAG) has become foundational for building LLM applications that require access to external knowledge. However, traditional RAG pipelines — with their static retrieve-then-generate approach — struggle with complex queries that require multi-step reasoning, diverse information sources, or dynamic decision-making. This talk will explore the emerging paradigm of agentic RAG, where LLM agents orchestrate the retrieval process through iterative planning, tool use, and self-reflection. This enables query decomposition, sequential querying, and querying different tools and systems across diverse knowledge sources.

Dirk Budke (mesoneer) – Workflow Automation Ends and Agentic AI Begins
At mesoneer, we help organizations turn manual, fragmented processes into intelligent systems that actually work in production. Our projects span classic workflow automation - where business logic, approvals, and integrations are clearly defined — to agentic AI, which handles ambiguity, exceptions, and unstructured data.
In the talk, I’ll share lessons from client projects: when structured automation outperforms AI, when reasoning agents create real value, and how combining both approaches leads to scalable, compliant, and adaptive enterprise systems. We’ll explore what happens when automation meets autonomy - and how to design for reliability in a world that’s getting less predictable.