Tag
Recent paper investigates whether grep outperforms vector search for agentic retrieval, finding grep yields higher accuracy in conversational memory tests, but limitations around enterprise document corpora are noted.
A research paper from PwC finds that grep-style text search, when properly integrated into agent harnesses, can match or beat embedding-based retrieval for coding-agent tasks, suggesting vector databases may not be essential for many use cases.
DCI (Direct Corpus Interaction) proposes using simple terminal tools like grep and bash for agentic search, outperforming traditional retrieval methods without embeddings or vector indexes.