@alanonai: Engineering for Vibe Coders: Qdrant Here’s something important to understand if you’re building an AI chatbot that answers questions about your documents. Finding information that’s similar to a question is not the same as finding the right answer. You might use a tool like Qdrant, which is a vector database that helps your application search for information based on meaning rather than exact words. And that’s incredibly useful. But imagine your chatbot finds an old company policy instead of the current one. Or it retrieves a document that belongs to a different customer. Or it finds something that sounds relevant but doesn’t actually answer the question. Qdrant might be working exactly as designed. The problem is everything around the search. You still need to think about permissions, data freshness, and how you evaluate the results. Vibe coding makes it easy to build semantic search. Engineering means making sure the information you retrieve is actually appropriate to use. Link in comments #ai #vibecoding #programming #coding