AI Cologne

  💡 RAG gets streamlined, Agents get smarter & AIOps Security gets event more critical! Another week has flown by in the world of AI. This week's round-up focuses on tools and agent architectures that bring AI closer to solving real-world business challenges—from simplifying RAG to tackling cyber threats. Gemini API File Search: A Web Developer Tutorial , Phil Schmid (Google, last accessed 2025-11-09 , https://www.philschmid.de/gemini-file-search-javascript ) Google released Gemini API File Search : an out-of-the-box, citation-supported RAG tool via the Gemini tools API. It handles parsing and chunking for private content grounding, simplifying AI-Architecture. Phil provides us with an introduction on how getting started and using it via JavaScript. Deep Agent - A General Reasoning Agent with Scalable Toolsets , Guru Baran (Cyber Attack News, last accessed 2025-11-09 , https://cybersecuritynews.com/claude-ai-misuse...

TLDR; Evaluation of AI systems is essential for safety and satisfaction of our users. Evaluation of stochastic AI systems is a lot more complex than your typical deterministic enterprise application. Not only does this require an understanding of user needs, non-functional system requirement, model capabilities but also their intersections to pick the right evaluation approach. A sound approach rests on a clear blue print, the right evaluation metrics, and automatization for transparency. A structured evaluation approach is a must. Industry grade LLM-application development frameworks facilitate implementation. Introduction AI assistants like chatbots excel in use cases where know-how needs to be mediated. Whether this is a cooking recipe, the explanation of a complex physical topic or a piece of interesting trivia. In our current project we apply LLMs to disseminate travel information to people interested in the beautiful city of Cologne. You want to know something about thi...