Who Evaluates the Evaluator? Testing AI Simulators in ProductionIn my last post, I wrote about using simulators to evaluate multi-turn AI agents. It is a powerful technique, but things can get confusing fast if we do not clearly define the testing architecture. In1B5d ago · 3 min readmundher.com
Why Dynamic Reasoning Beats Static GraphsStandard vector RAG is great for finding needles, but it’s terrible at describing the haystack. It relies entirely on semantic proximity. That means it often fails at multi-hop reasoning or answering Aug 15 · 3 min readmundher.com
How to Build Privacy into LLM Agents Without Breaking Their BrainsI've been spending a lot of time lately building autonomous agents with ReAct and RAG frameworks. The shift from stateless chatbots to stateful systems that can actually execute tools is incredibly usJul 19 · 3 min readmundher.com
Stacking Agent Memory: Checkpoints, Status Boards, and Active ContextI love the idea of autonomous coding agents. But one of the quickest ways to hit a wall when setting them up is the infinite context problem. Your context window is finite, but the work you want the aJul 4 · 3 min readmundher.com
Smart LLM RoutingBuilding LLM apps is easy, but scaling them without setting a pile of money on fire is hard. You really don't need the massive brainpower of GPT-5 for every single user query. Routing is how we fix thJun 26 · 4 min readmundher.com
