# Amazon — How IskayPet unified corporate knowledge with Amazon Bedrock Managed Knowledge Bases

- Company: Amazon (amazon.com)
- Announced: 2026-10-22T18:01:53+00:00
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://aws.amazon.com/blogs/machine-learning/how-iskaypet-unified-corporate-knowledge-with-amazon-bedrock-managed-knowledge-bases/
- Record: https://forck.live/items/26795-how-iskaypet-unified-corporate-knowledge-with-amazon-bedrock-managed-knowledge
- Subject: Bedrock / Nova
- Models affected: Claude Haiku 4.5

IskayPet built a corporate knowledge assistant on Amazon Bedrock Managed Knowledge Bases so office staff could stop searching hundreds of SharePoint documents by hand. The pet care company operates more than 330 stores across Spain, Portugal and France under the Kiwoko, Tiendanimal, Kivet, Clinicanimal and Animalis brands, with more than 4,500 employees and 7 million customers. Answers to everyday questions about return policies, veterinary protocols and onboarding steps were spread across four languages and three countries, and the answer was often outdated or wrong. The assistant answers in the employee's language, routes each question to the right body of knowledge, and cites its sources so employees can verify them. Amazon Bedrock handles ingestion, multimodal parsing, vector storage, embedding generation and retrieval, and IskayPet pays only for what it stores and retrieves. A native SharePoint connector avoided a data migration, and document-level access control enforces SharePoint permissions at retrieval time. The team built the whole solution, from the store-facing frontend to the AWS architecture and deployment, using Kiro with Claude Haiku 4.5.

## Evidence

Verbatim from https://aws.amazon.com/blogs/machine-learning/how-iskaypet-unified-corporate-knowledge-with-amazon-bedrock-managed-knowledge-bases/:

> IskayPet chose Amazon Bedrock Managed Knowledge Bases for its managed RAG infrastructure, which removed the need to run vector stores, embeddings, or ingestion pipelines.

---

Record: https://forck.live/items/26795-how-iskaypet-unified-corporate-knowledge-with-amazon-bedrock-managed-knowledge
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md