[rag]FEB 5
Mining Reranker Training Data from RAG Citations
Using citation behavior in production RAG systems to generate labeled training data for domain-specific reranking models.
AI Engineering Blog
Cole Hoffer
Making AI do the thing.
Practical notes on building production RAG systems, LLM evaluations, and retrieval optimization.
[evals]FEB 5
Evaluating LLM Chat Agents with Real World Signals
How human follow-up behavior reveals response quality, and why specific instruction adherence outperforms vague relevance scoring.
[rag]JAN 29
Relevancy Filtering in Retrieval Pipelines
Using LLM-based classification as a second pass to filter retrieval candidates when similarity thresholds fail to generalize.
Latest
Reciprocal Rank Fusion for Hybrid Search
A comprehensive guide to using Reciprocal Rank Fusion (RRF) to combine BM25 and semantic search results for production RAG systems.
JAN 23, 2026[GUIDE]
Applying HyDE to Domain-Specific Search
Using Hypothetical Document Embeddings to bridge vocabulary gaps between user queries and specialized document corpora.
JAN 22, 2026[rag]
Structured Pre-Filtering for RAG Systems
Why decomposing queries into structured filters before semantic search improves retrieval precision and performance.
JAN 15, 2026[rag]
BM25 Search in LLM Systems
A comprehensive, interactive guide to understanding the BM25 ranking algorithm for AI engineers building RAG systems and search applications.
JAN 3, 2026[GUIDE]
Structured Logprobs for Better Classification
Combining chain-of-thought reasoning with logprob extraction improves LLM classification accuracy while giving you real confidence scores.
DEC 14, 2025[classification]