--- format: "aidr-story-markdown/v1" id: "bfa8a2eb87150a2e0505a331228b42f669d2ea2acfe021cc8a2256d175b69eef" canonical_url: "https://aidr.today/bfa8a2eb?lang=en" title: "How Benchling secured multi-tenant AI agents with Amazon Bedrock AgentCore" lang: "en" requested_lang: "en" available_langs: ["en","vi"] translation_fallback: null fallback_fields: [] published_at: "2026-09-21T16:27:34.000Z" category: "Models" topics: ["anthropic","claude","multi-agent","open-source","agent","mcp","amazon","bedrock"] source_urls: ["https://aws.amazon.com/blogs/machine-learning/how-benchling-secured-multi-tenant-ai-agents-with-amazon-bedrock-agentcore/","https://aws.amazon.com/blogs/machine-learning/build-a-multi-account-ai-agent-with-agentcore-gateway-and-mcp/"] summary: "Learn how Benchling built a defense-in-depth security architecture to run untrusted, AI agent-generated scientific code across thousands of life sciences tenants using Amazon Bedrock AgentCore Code Interpreter in VPC mode, combined with Amazon Route 53 Resolver DNS Firewall and VPC endpoint policies to block data exfiltration, including through DNS." --- # How Benchling secured multi\-tenant AI agents with Amazon Bedrock AgentCore > [Open the canonical story]() **Published:** 2026-09-21T16:27:34.000Z **Category:** Models **Topics:** anthropic, claude, multi\-agent, open\-source, agent, mcp, amazon, bedrock ## Summary Learn how Benchling built a defense\-in\-depth security architecture to run untrusted, AI agent\-generated scientific code across thousands of life sciences tenants using Amazon Bedrock AgentCore Code Interpreter in VPC mode, combined with Amazon Route 53 Resolver DNS Firewall and VPC endpoint policies to block data exfiltration, including through DNS\. ## Sources - [Story source]() - [Story source]()