# onPanda: Efficient Annotation of On-Policy Alignment Data for LLMs and Agents via Token-Level Correction > Source: > Published: 2026-09-22 05:00:00+00:00 We present onPanda, an interactive tool for efficiently annotating LLM alignment data and agent trajectories. onPanda adopts token-level correction as its core interaction: while reading a model response, the annotator locates the first inappropriate token and either picks a substitute from the mode