Industrializing Prediction-Powered Inference: The GLIDE Library for Reliable GenAI and Agentic Systems Evaluation

Reliable evaluation of agentic systems requires unbiased estimates with valid uncertainty, but standard practice navigates between costly hu- man annotation and biased LLM-as-judge prox- ies. Prediction-powered inference (PPI) combines both into debiased estimates with valid confi- dence intervals, yet its various methods remain scattered across papers under partial implemen- tations. We introduce GLIDE, an open-source Python library that unifies state-of-the-art PPI estimators (PPI++, Stratified PPI, Predict-Then- Debias and its stratified variants, Active Statisti- cal Inference) and samplers (uniform, stratified, active, cost-optimal) under a scipy-style API spe- cialized to mean estimation. GLIDE ships with a reproducible Monte Carlo validation suite, an empirically grounded decision tree for method selection, and an agentic evaluation case study showing substantial annotation savings at equiv- alent precision. An anonymized version of the codebase is provided as supplementary material; the package will be made publicly available under a permissive open-source license at the camera- ready stage.