{
  "id": 19672989,
  "title": "Migrate to Amazon Bedrock Managed Knowledge Base with your coding agent",
  "url": "https://urgent.news/2026/11/12/migrate-to-amazon-bedrock-managed-knowledge-base-with-your-coding",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-12T16:16:45.000Z",
  "source": {
    "name": "AWS Machine Learning",
    "slug": "aws-machine-learning",
    "url": "https://aws.amazon.com/blogs/machine-learning/migrate-to-amazon-bedrock-managed-knowledge-base-with-your-coding-agent/"
  },
  "original_language": "en",
  "account": "Migrating to Amazon Bedrock's Managed Knowledge Base presents an opportunity for customers to benefit from a streamlined, cost-effective solution that handles ingestion, storage, indexing, and retrieval. This managed service takes over the heavy lifting, scaling automatically as content grows, and adds modern retrieval capabilities without requiring teams to manage vector stores, tune embeddings, or maintain index settings.\n\nThe migration process is designed to be seamless. It begins with a read-only discovery phase, followed by a detailed plan that is reviewed line by line. Upon approval, the migration agent creates the new knowledge base alongside the original one, or generates a migrated infrastructure as code (IaC) template for the existing pipeline. Ingestion and updating of application retrieval calls remain under the customer's control, with guidance provided throughout the process.\n\nManaged Knowledge Base offers several advantages over a customer-managed alternative. AWS manages the entire store, including ingestion, storage, indexing, and retrieval, with automatic scaling to accommodate growing content. Hybrid search, which combines keyword and semantic matching, is always on without the need for index configuration. The service includes a managed embedding model, reranker, and parser for multimodal file types, providing built-in capabilities that would typically require custom development.\n\nKey features include native connectors for sources like Amazon S3, Microsoft SharePoint, and Atlassian Confluence, enabling direct ingestion of content with automatic syncing of changes. Deletion safeguards and ACL awareness help protect against accidental data loss and ensure retrieval returns only accessible content. Agentic retrieval allows for multi-part questions and iterative retrieval across multiple knowledge bases, and integration with Amazon Bedrock AgentCore's Gateway enables query access via the Model Context Protocol (MCP).\n\nResource-based policies control access from other AWS accounts, and scope them to specific roles with granular permissions. Higher quotas on managed knowledge bases allow for more data sources and concurrent ingestion jobs compared to customer-managed options. While pricing and cost drivers differ, storage and retrieval charges are metered directly with a Managed Knowledge Base, potentially resulting in cost savings for low-utilization use cases. For specific pricing details and regional availability, consult the Amazon Bedrock pricing guide and supported regions documentation.",
  "summary": "The migration guide in the amazon-bedrock skill helps you migrate a customer-managed Amazon Bedrock knowledge base to a Managed Knowledge Base. Your coding agent plans the move with read-only discovery, creates the new knowledge base or an infrastructure-as-code template alongside the original, and validates retrieval before you cut over.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}