Agentics Meetup in Vienna: Building Agents That Work

Description

AI Agents are easy to demo and hard to trust.They can act on outdated context, hide what they are doing, and say “done” before the work is verified.On July 30th, five professionals from London, Seattle, Novi Sad, and Kansas City will bring their perspectives to Vienna. Their talks will examine what agents need beyond the model: usable interfaces, empowered people and organizations, reliable verification, organizational memory, and infrastructure based on real systems.Each session follows the same format: a 10-minute presentation followed by 5 minutes of questions. After the talks, we will continue with an hour of open networking and informal project sharing.The event is free, organized by volunteers, and non-commercial.Agenda18:00 — Doors openArrive, grab food or a drink, and meet other participants.18:30–20:00 — Lightning talks and Q&A20:00–21:00 — Open networking and informal project sharingContinue the conversations, compare approaches, open a laptop, or show people something you are building, testing, or trying to understand.Bring something to shareBring a functional system, prototype, useful failure, framework, or unresolved problem. After 20:00, participants are welcome to share projects informally, ask for feedback, or find collaborators.You don’t need a polished presentation. Please share what you learned, not what you’re selling.Who should attend?This meetup is for people who build, deploy, evaluate, design, govern, research, or prepare organizations for agent systems. You do not need to be a member of the Agentics Foundation or an expert.Join in Vienna or onlineIn-person: Pappala Pub, private event room U-Bahn-Bogen 156–157, 1090 ViennaFood and drinks will be available for purchase.Online: Register to receive the Zoom access link. Remote participants can follow the scheduled talks; networking and informal project sharing will primarily take place in the room.About the Agentics FoundationThe Agentics Foundation is a global non-profit organization working to make AI innovation and education more accessible by supporting the development and deployment of open-source agent AI systems.Its community brings together developers, researchers, founders, and practitioners through education, collaborative projects, events, and regional chapters.TalksIntroduction — Welcome to the Agentics FoundationA brief introduction to the Foundation, its international community, and the role of open knowledge sharing, open collaboration, education, and open-source work in the development of agent systems.Bence Csernak — From Screens to Relationships: Designing UX for Agents that Remember and Act (LinkedIn - GitHub)Traditional software expects a user to click. Agents can remember context, start tasks, continue acting after an interaction, and make decisions on behalf of a user. Bence will explore what this changes in product design and UX.Bence Csernak (ex EY, HSBC, NatWest) is an Applied AI Product Leader and Agent AI Engineer with experience in designing and deploying LLM systems in healthcare, enterprise, and regulated environments. Board member of the Agentics Foundation (volunteer)Klara Hermesz — The AI Competency Framework & Diagnostic Tool for Businesses and Individuals (LinkedIn - GitHub)Strategic AI enablement needs a starting point and a clear map of where to go. Without a shared framework, individuals, teams, and organizations struggle to see where they are, what capabilities their work requires, and what they should develop next.Klara will present the AI Competency Framework she developed with Adam Kovacs and demonstrate a diagnostic tool built around it for individuals and organizations.Klara Hermesz is co-founder and Chief Learning Strategist at the AI Enablement Academy. She previously built and scaled global learning programs at Meta and Uber, including Meta's first metaverse education strategy for a 3,000-person global organization and a revamp of Uber's mentoring and coaching program for over 50,000 employees. A self-confessed learning enthusiast, she has built her career around a consistent belief: tools are rarely the hardest part; it’s bringing people along that is.Dragan “Profa” Spiridonov — Conclusion Theatre: When Your Agent Says “Done” — and Minds (LinkedIn - GitHub)Every agent builder has seen an agent confidently assert success on a broken job. This talk names the problem — conclusion theatre — shows the failure modes behind it and provides practical verification patterns to increase confidence in your agents' outcomes.Dragan “Profa” Spiridonov is Head of Agent Quality Engineering at Cognitum One, creator of PACTS and the agent QE platform and framework. A 30-year IT veteran building quality into agent systems rather than testing it afterwards. Secretary of the Board of the Agentics Foundation and ambassador of the AF Chapter in Serbia.Adam Kovacs — Surveillance or Observability? The Level of Context an AI Chief of Staff Needs (LinkedIn - GitHub)Organizations already generate messages, documents, tickets, code, meetings, and system logs. These traces are not automatically usable knowledge.An agent style led by a chief of staff needs structured, current, permission-aware context. Adam will explain five properties that this level of context needs: shared meaning, time, provenance, permission, and purpose. He will then use them to examine an uncomfortable question: when does useful organizational observability become workplace surveillance?The session is adapted from Adam and Klara's presentation at the 2026 Craft Conference, “Make Your Systems Define the Story of Your Organization: Is it Work Surveillance or Hyper-Optimized Operational Excellence?”Adam Kovacs is co-founder and Chief AI Strategist at the AI Enablement Academy and a Co-founding Member and International Ambassador of the Agentics Foundation and its Seattle Chapter. He was a founding member of AWS’s Talent Intelligence service and is Executive Director of OPEN Talent Society, a non-profit organization based in Seattle exploring the future of work. His work focuses on enterprise AI adoption, agent-ready operations, organizational memory, and responsible governance.Chris Royse — Eyes, Hands, and Fundamental Truth: Building the Full Stack of Autonomous Agents — from Database Up (LinkedIn - GitHub)Chris will chart a stack of autonomous agents from their data level to use of computation: how an agent represents associations, builds structured context around code and other domains, perceives software, and takes actions through tools.Chris Royse is a systems engineer building the full stack of autonomous AI agents (20,000 commits in the last year). He is the creator of Synapse, an open-source MCP server that gives any AI the eyes and hands it needs to use a computer like a human. Calyx is a native association database built using the mathematical formula for intelligence. My current work involves building projects on top of this intelligent database. Astrolabe applies Calyx to code in 158 programming languages. Poly tracks the flow of money around the globe and analyzes how everything is associated. Some of my other work with Calyx includes a Biomedical Hypothesis Engine as well as an engine designed for legal court cases in the US.Learn more about the Agentics Foundation