MAMundher Al-Shabi, PhDinmundher.com·4d ago · 4 min readUsing Simulators to Evaluate Multi-Turn AI AgentsBuilding a multi-turn conversational AI is surprisingly easy right now. Evaluating it is incredibly hard. For single-turn tasks, a standard static dataset works fine: you just feed in a prompt and ass00
MAMundher Al-Shabi, PhDinmundher.com·Jun 9 · 3 min readWhy Grep Won't Save Your RAG PipelineI’ve been reading through a recent paper titled "Is Grep All You Need? How Agent Harnesses Reshape Agentic Search". It’s a provocative piece with a premise I normally love. The authors claim that simp00
MAMundher Al-Shabi, PhDinmundher.com·May 24 · 3 min readHarnessing Conversational AII’ve been spending the last few weeks messing around with open-weight models to build conversational interfaces. By now, the new reality is obvious: generating natural language is no longer the bottle10
MAMundher Al-Shabi, PhDinmundher.com·May 17 · 5 min readVectorless RAGIf you’ve built anything with LLMs in the past couple of years, you’ve probably wired up a Retrieval-Augmented Generation (RAG) pipeline. The playbook is burned into our brains: take a PDF, smash it i00
MAMundher Al-Shabi, PhDinmundher.com·May 4 · 3 min readThoughts on Advanced Chunking Strategies for RAGI’ve been thinking a lot recently about the "chunking problem" in Retrieval-Augmented Generation. If you've played around with the llm CLI tool or built anything with vector embeddings, you've probabl00