How IskayPet unified corporate knowledge with Amazon Bedrock Managed Knowledge Bases
Learn how IskayPet, a leading pet care company in Iberia, built a multilingual corporate knowledge assistant on Amazon Bedrock Managed Knowledge Bases. The assistant answers employee questions across retail, veterinary, onboarding, and procurement in four languages and three countries, with no RAG infrastructure to manage.
IskayPet, a leading pet care company in Iberia, faced a knowledge challenge with answers to operational questions scattered across hundreds of Microsoft SharePoint documents in multiple languages and countries. To solve this, they turned to Amazon Bedrock Managed Knowledge Bases, a managed RAG infrastructure that handled data ingestion, multimodal parsing, vector storage, embedding generation, retrieval, and more.
With its native SharePoint connector, IskayPet was able to ingest documents directly from their existing environment, avoiding a costly data migration. The solution used Kiro with Claude Haiku 4.5 for the store-facing frontend, and the retrieval and generation process involved hybrid search (semantic and keyword) over indexed content, reranking results, and generating grounded, cited answers from retrieved passages using a foundation model.
IskayPet's solution also included document-level access control, allowing it to reuse SharePoint permissions and provide accurate, up-to-date answers in the employee's language.
Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
