YuTing Chiu·Just nowCan the Source Support the AI Answer You’re About to Use?Audit one consequential claim against the exact passage, scope and date behind its citation.
Tabish alam·7h agoEvaluating Retrieval in RAG SystemsA retrieval-augmented system can give a clear, fluent answer that is supported by the text it was shown, and still be wrong. The reason is…
InTowards AIbyJames Luan·20h agoHybrid Search Starts with Two Good Candidate ListsConsider a support query containing both an error code and an ordinary description of what went wrong. Exact matching helps find the code…A response icon1A response icon1
Terry Migwi·23h agoBuilding a Search System, Part 3: RAG ArchitectureThis article explains how the retrieval and generation stages of this pipeline connect, why that connection matters, and what the results…
Terry Migwi·1d agoBuilding a Search System, Part 2: Hybrid Search and Re-rankingThis article documents how I extended the semantic search engine built over business proposals to use hybrid search and cross-encoder…
Terry Migwi·1d agoBuilding a Search System, Part 1: Semantic Search and Its LimitsThis article documents how I built a semantic search engine over a corpus of business proposals, what semantic search is and how it works…
Sahillenka·2d agoMy RAG app scored 0.973. Then I gave it a real test.What happened when I built a document Q&A app that would rather say “I don’t know” than make something up
Sirsh Amarteifio·4d agoMIDB: Multi-index, Iterative, Durable, BitemporalA database design for AI agents that search, follow links, and build answers across documents.
Tejas Sumukh KL·5d agoSmall Knowledge Graphs vs. RAG for Conversation MemoryIn my previous article, I explained how I built a Small Knowledge Graph (SKG) to navigate conversation history. The idea was to explore a…
InBCS IRSG InformerbyBCS IRSG Informer Editor·6d agoA Reflection on ESSIR 2026 in BucharestBy Shuoqi Sun.
