LLM Practitioners Meetup Karlsruhe #2

Hey there!

After our first successful Meetup in May (thanks again for joining!), it's time for round two.

The next LLM Practitioners Meetup Karlsruhe will take place on Tuesday, July 29th, 2025, at 6:30 PM, again in the SteamWork Coworking Space (Roonstraße 23a, 76137 Karlsruhe).

We'll provide food, drinks, and – most importantly – air-conditioning.

Our schedule (please read the talk descriptions at the bottom):
6:30 pm: Get together
7:00 pm: Session #1: Fighting Cloud Computing Fraud with local LLMs* (Talk by Jonas Scholz)
7:30 pm: Break with pizza and drinks
8:00 pm: Session #2: Choosing AI Agent Frameworks: 3 Mistakes to Avoid (LangChain Included)** (Talk by Viktor Malyi)
8:30 pm: Discussions, pizza and drinks (until approx. 10 pm)

Looking forward to seeing you all again and diving into all things LLMs. Stay cool out there!

Best,
Leon & Ian

--------

Talk descriptions:
*) Talk #1: Fighting Cloud Computing Fraud with local LLMs (Jonas Scholz)
„At Sliplane, a managed container hosting platform, we offer developers an easy way to deploy their apps, with the unfortunate side effect of attracting abuse. From crypto miners to phishing kits, attackers love free trials. Traditional heuristics can detect DDoS or mining, but phishing and spam bots often hide behind innocuous-looking code.

In this talk, I’ll share how we built a lightweight AI agent pipeline that inspects user repositories when abuse is suspected. It runs on a self-hosted, small Mistral model and applies natural language policies to flag suspicious behavior, such as fake login pages or spam scripts. The agent picks and summarizes key files, checks them against soft rules, and helps a human-in-the-loop make faster decisions — all without sending private customer code to a third-party API.

We'll dive into the architecture, cost optimizations to run small models, and why this beats rule-based filters at scale.“

*) Talk #2: Choosing AI Agent Frameworks: 3 Mistakes to Avoid (LangChain Included) (Viktor Malyi)
„Most developers waste months on the wrong AI agent framework (to later rebuild everything from scratch). Learn the 3 critical mistakes causing that, why even LangChain can be a trap, and get a battle-tested decision framework from 3 successful projects. You'll leave knowing exactly how to evaluate frameworks for your particular use case, not just follow the hype.“