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.
First seen by Oriel on .
AI summary
IskayPet built a multilingual corporate knowledge assistant on Amazon Bedrock Managed Knowledge Bases, using existing SharePoint content and permission-aware retrieval to answer employees’ operational questions with citations.
- A dedicated knowledge base per assistant isolates business areas and countries, while SharePoint inclusion paths restrict indexing to relevant sites, libraries, or folders.
- Hybrid search, reranking, and advanced indexing retrieve keyword matches and content embedded in documents; SharePoint permissions are enforced both when assistants are shown and when passages are retrieved.
- The assistant retrieves 25 passages and injects up to 15 after removing duplicates and short fragments; the number of prompt passages is a major input-token cost lever.
- In its first roughly two months, time to find an answer fell from 3–5 minutes to about 7 seconds, reducing search time by around 95 percent.
- The system serves three countries and four languages and is expected to handle roughly 100,000 monthly queries; IskayPet built it with Kiro and Claude Haiku 4.5.
#amazon bedrock #rag #sharepoint #knowledge management
Generated by gpt-5.6-sol. Check the original for details.
Aliases
| Source | External ID | URL |
|---|---|---|
| AWS Machine Learning Blog | 4c086dcfa95658eafa8d777d0aa2a5fcb4edc64f | https://aws.amazon.com/blogs/machine-learning/how-iskaypet-unified-corporate-knowledge-with-amazon-bedrock-managed-knowledge-bases/ Read discussion |