{"version":1,"type":"story","url":"https://digestai.news/story/iskaypet-builds-corporate-knowledge-assistant-on-amazon-bedrock-manage","json":"https://digestai.news/story/iskaypet-builds-corporate-knowledge-assistant-on-amazon-bedrock-manage.json","markdown":"https://digestai.news/story/iskaypet-builds-corporate-knowledge-assistant-on-amazon-bedrock-manage.md","slug":"iskaypet-builds-corporate-knowledge-assistant-on-amazon-bedrock-manage","headline":"IskayPet builds corporate knowledge assistant on Amazon Bedrock Managed Knowledge Bases","summary":"IskayPet, a leading pet‑care company in Iberia operating more than 330 stores across Spain, Portugal and France, built a corporate knowledge assistant on Amazon Bedrock Managed Knowledge Bases. The assistant answers employee questions about retail operations, veterinary care, onboarding and procurement in four languages—Spanish, Portuguese, French and English—using the company’s existing SharePoint repositories.\n\nBy using Bedrock’s managed RAG stack, IskayPet avoided running its own vector database, embedding pipeline or ingestion jobs. The native SharePoint connector imported documents with advanced indexing, including text from images, and document‑level permissions were enforced at query time. The system retrieves up to 25 passages, injects up to 15 into a prompt for Claude Haiku 4.5, and returns a cited answer.\n\nIn the first two months of production, answer‑finding time dropped from 3–5 minutes to about 7 seconds, and employees spent roughly 95 percent less time searching for procedures. The assistant now handles roughly 100,000 queries per month across all business areas and countries.","keyPoints":["IskayPet serves 330 stores in Spain, Portugal, France with a Bedrock knowledge assistant.","Query time fell from 3–5 minutes to about 7 seconds, cutting search time by about 95 %.","The system handles roughly 100,000 queries per month across four languages."],"whyItMatters":"Provides a managed RAG solution that lets large enterprises add multilingual corporate assistants without building vector infrastructure, improving employee productivity and reducing search costs.","category":{"slug":"enterprise","name":"Enterprise & Industry","url":"https://digestai.news/category/enterprise"},"entities":{"companies":["IskayPet","Amazon","Kiro"],"models":["Claude Haiku 4.5"],"people":[]},"firstPublishedAt":"2026-10-22T18:01:53Z","updatedAt":"2026-10-22T18:01:53Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"AWS Machine Learning Blog","title":"How IskayPet unified corporate knowledge with Amazon Bedrock Managed Knowledge Bases","url":"https://aws.amazon.com/blogs/machine-learning/how-iskaypet-unified-corporate-knowledge-with-amazon-bedrock-managed-knowledge-bases","publishedAt":"2026-10-22T18:01:53Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"IskayPet builds corporate knowledge assistant on Amazon Bedrock Managed Knowledge Bases\", 22 October 2026, https://digestai.news/story/iskaypet-builds-corporate-knowledge-assistant-on-amazon-bedrock-manage","publisher":"Digest AI","title":"IskayPet builds corporate knowledge assistant on Amazon Bedrock Managed Knowledge Bases","datePublished":"2026-10-22T18:01:53Z","url":"https://digestai.news/story/iskaypet-builds-corporate-knowledge-assistant-on-amazon-bedrock-manage"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}