Development

Golden sets and labeled samples

• A Golden-Set Check That Blocks a Gateway Rule Change
• Anonymized Data for Model Evaluation: Building a Held-Out Set
• Evaluating a RAG Pipeline End to End: Golden Sets, Judges, Drift
• Golden Sets for Support Agents: Intents and Escalation Paths
• A Golden Set of Context Tuples for Key Regression
• A Golden Set That Ranks Models by Cost Per Accepted
• A Second Golden Set for the Cheap Model's Strengths
• Building a Golden Dataset for Retrieval Evals
• Building the Labeled Sample Behind a Routing Cutoff
• Generating Golden Cases from Support Tickets and Traces
• Labeling a Test Set Without Burning Out Your Team
• Refreshing a Golden Set When Documents Change
• Sampling Production Traffic for an Eval Set: Strata and Gaps
• Sampling Strata for a Gate's Labeled Set
• Sampling Tickets into a Golden Set: Strata and Held-Out Cases
• Versioning a Golden Set Alongside Your Embedding Model
• When a Golden Set Gets Stale: Refresh Triggers from Ticket Drift