​Why Some AI Agents Actually Work, and Most Don’t

​Same Brain. Different Harness. Wildly Different Results.

​If you have ever used an AI agent that confidently gave you the wrong answer, this talk is about why that happens.

​Everyone argues about which model is “best,” but in practice, the model is rarely what makes or breaks an AI product. What often matters more is everything surrounding the model, the systems that determine whether it is reliable or embarrassing.

​Yaqoob and Veeresh, who have years of experience in data science and AI, will break this down in plain language and demonstrate it live: the same AI model, two different setups, and wildly different results.

​Schedule

​18:00 Doors open. Grab a drink or a snack and get to know the room.

​18:30 Talk and live demo begin

​19:30 Q&A

​20:00 to 21:00 Drinks and conversation

​About the Speakers

​Veeresh Dammur

​is a Senior Data Scientist at Lovehoney Group in Berlin, with a background in natural language processing and machine learning from the University of Passau.

​He builds and operates the AI systems behind the company’s e-commerce customer experience, including a production customer care chatbot that hands conversations over to human support agents and a product recommendation engine.

​Over the past year, much of his work has shifted from the models themselves to the machinery surrounding them, including agent harnesses, custom skills, evaluations, and automated end-to-end tests.

​https://www.linkedin.com/in/veeresh-prakash-dammur-1273157b/

​Yaqoob David

​is a Senior AI Engineer at PlentyONE, where he builds AI-powered features for one of Europe’s leading e-commerce platforms. He has an academic background from Berliner Hochschule für Technik, also known as BHT.

​Before joining PlentyONE, he worked at Lovehoney Group, where he built and launched four production AI systems across seven markets, including a customer service assistant, a recommendation engine, and an automated editorial pipeline.

​His rule of thumb is simple: if it is not reliable and observable, it is not done.

​https://www.linkedin.com/in/yaqoobdavid/

​Between them, Yaqoob and Veeresh have spent the last few years building AI systems that have gone into production, including customer service bots, recommendation engines, and editorial pipelines across multiple companies and markets.

​They keep encountering the same issue: everyone obsesses over which model to use, but the model is rarely what determines whether an AI agent works or falls apart in production.

​What matters is everything around the model: how it remembers information, what it is allowed to do, and what catches errors when something goes wrong.

​They call this the harness, and much of the difference between an impressive AI demo and a dependable AI product comes down to how that harness is designed.

​In this talk, they will share what they have learned from building and launching these systems in real-world environments, including a few expensive lessons.

​They will then demonstrate the concept live: the same underlying model, configured in two different ways, producing very different results.

​Same brain. Different harness.

​

​Ojin AixHaus:

​Ojin AixHaus: Berlin’s Hub for Human-Centric AI Innovation

​AI development is moving at a remarkable pace, but technical tools are only as powerful as the people using them. Ojin AixHaus is a dedicated Berlin-based hub designed to foster human connection, strategic execution, and the exploration of practical AI applications.

It is a curated environment where AI enthusiasts, engineers, founders, and creative builders can move beyond the hype cycle and develop practical, real-world expertise. By offering free residencies for startups to run sprints, events, workshops, and hackathons, Ojin AixHaus helps members and founders turn their ideas into action within a thriving community of experts.

Come for the talk and stay for the live demo and conversation afterwards. The event will bring together a relaxed and mixed crowd of engineers, product professionals, founders, and people who are simply curious about AI, with plenty of time to meet others over drinks.

​📅 Wednesday, 29 July, 18:00 to 21:00
📍 Ojin AixHaus, Chaussee 36, 10115 Berlin
🎯 Open to everyone, technical or nontechnical. Curiosity about AI is all that is required.

​Find out more: Ojin AixHaus Community
Follow on socials: Ojin AixHaus Community

​Accessibility

​Please note that the venue is accessible only via stairs. There are currently no ramps or elevators available.

​Anyone with accessibility questions or concerns is encouraged to contact the event organiser or the Ojin team before the event.

​Photo and Video Notice

​Photos and videos will be taken during the event.

​By attending, participants acknowledge that they may be photographed or recorded. Anyone with concerns should speak with the event organiser or a member of the Ojin team before or during the event.