← All patterns
Evaluation & Feedback Loops
Knowing whether a change helped, before and after it reaches real traffic.
5 patterns
Golden Set Regression Gate
Block any prompt, model, or pipeline change that regresses a curated set of known-correct cases.
9 minaka eval suite in CI
LLM-as-Judge with a Calibrated Rubric
Score subjective quality with a model, but only against an explicit rubric that has been calibrated against human labels.
10 minaka model-graded evaluation
Online Feedback Capture
Instrument the product so real usage produces labelled data, then turn that data into evaluation cases and fixes.
9 minaka implicit signals
Shadow and Canary Evaluation
Run the new version against real traffic without showing it, then expose it to a small slice before rolling it out.
9 minaka dark launch
Trace-Driven Failure Triage
Record every stage of every request as a structured trace, then attribute failures to the stage that actually caused them.
9 minaka observability for LLM apps