---
format: "aidr-story-markdown/v1"
id: "a0c183c052df5c66bbee6f46f7082566358a0040bf094d0dd4f031db960f3cf4"
canonical_url: "https://aidr.today/a0c183c0?lang=en"
title: "How uniopen customized Amazon Nova to their retail moderation policies for production deployment"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-01T15:33:01.000Z"
category: "Models"
topics: ["amazon","llm"]
source_urls: ["https://aws.amazon.com/blogs/machine-learning/how-uniopen-customized-amazon-nova-to-their-retail-moderation-policies-for-production-deployment/"]
summary: "See how uniopen, a retail platform from Taiwan's Uni-President Enterprises Group, adapted Amazon Nova 2 Lite to its content-moderation policies using supervised fine-tuning in Amazon SageMaker AI and prompt optimization. Business-relevant evaluation and release gates kept quality in check."
---

# How uniopen customized Amazon Nova to their retail moderation policies for production deployment

> [Open the canonical story](<https://aidr.today/a0c183c0?lang=en>)

**Published:** 2026-10-01T15:33:01.000Z
**Category:** Models
**Topics:** amazon, llm

## Summary

See how uniopen, a retail platform from Taiwan's Uni\-President Enterprises Group, adapted Amazon Nova 2 Lite to its content\-moderation policies using supervised fine\-tuning in Amazon SageMaker AI and prompt optimization\. Business\-relevant evaluation and release gates kept quality in check\.

## Sources

- [Story source](<https://aws.amazon.com/blogs/machine-learning/how-uniopen-customized-amazon-nova-to-their-retail-moderation-policies-for-production-deployment/>)