# Amazon shows how to distill a shopping agent with SeqKD on SageMaker AI

> Original title: Build efficient agents with knowledge distillation on Amazon SageMaker AI

- Source: AWS Machine Learning Blog
- Published: 2026-11-02T17:01:31.000Z
- Bad Influence: https://badinfluence.news/items/bcunll56oj0ytqr1ql547w096
- Original: https://aws.amazon.com/blogs/machine-learning/build-efficient-agents-with-knowledge-distillation-on-amazon-sagemaker-ai/

## Summary

AWS Machine Learning Blog explains sequence-level knowledge distillation (SeqKD), which fine-tunes a smaller student model on a frontier teacher's text outputs and needs no teacher weights or logits. The post applies it to a shopping agent on Amazon SageMaker AI, covering trajectory generation, supervised fine-tuning, serverless training, and evaluation against a held-out benchmark. The approach aims to cut per-task costs of multi-call agent loops while keeping much of the teacher's quality.