Development

Retrieval quality evaluation

• A Retrieval Test Set for Embedding Model Swaps
• Measuring Retrieval Quality: Recall and Precision
• Writing a Regression Query for Every Retrieval Bug
• A Query Rewrite Step: When the Model Paraphrases First
• A Relevance Floor on Context: Setting It from the Judged Set
• Connecting Retrieval Scores to Support Outcomes
• Generating Realistic Query Sets for Retrieval Tests
• Measuring Recall@k and Precision on a Golden Set
• Putting a Relevance Floor on Retrieved Context
• Quoting a Retrieved Passage Without Blending It Into the Answer
• Reading a Retrieval Bug in Traces: Query, Chunks, Scores
• Retrieval That Returns Zero Chunks: Rules for the Next Turn
• Sampling Queries to Measure Recall on a Live Index
• Scheduling a Nightly Recall Check on a Fixed Query Sample
• Tying Retrieval Scores to User Behavior
• When a Support Agent Should Quote a Policy vs Summarize It
• When a Test Set Is Not Enough: Add Production Monitoring