Day 13: Why chunk boundaries shape answer quality
How chunk boundaries decide what evidence the system can actually retrieve.
Jun 3, 20263 min read
Command Palette
Search for a command to run...
Series
Retrieval Foundations
A practical foundation for retrieval systems. This series explains how chunking, embeddings, vector databases, keyword search, semantic search, hybrid retrieval, metadata, and access filters decide what evidence an AI system can safely use.
Day 14: Why embeddings are useful and easy to overtrust
Why semantic similarity is useful, but not the same as correctness or trust.
Jun 5, 20263 min read
Day 15: Why vector stores are infrastructure, not magic memory
Why vector databases need to be operated like infrastructure, not treated like magic memory.
Jun 6, 20263 min read
Day 16: Why keyword search and semantic search both matter
Why exact words and semantic meaning both matter in production retrieval.
Jun 6, 20263 min read
Day 17: Why hybrid search is often the practical default
Why combining retrieval signals is often more practical than betting on one search method.
Jun 6, 20263 min read
Day 18: Why relevant data can still be unauthorized data
Why relevant evidence is still wrong evidence if the user was not allowed to see it.
Jun 7, 20263 min read