# Amazon Bedrock AgentCore

Amazon Bedrock AgentCore is a platform for building, connecting, securing, debugging, evaluating, and scaling production AI agents across frameworks and models.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Held While Waiting: What LLM Agent Sessions Reserve on Serverless and Agent Runtimes

DevFeed: [Held While Waiting: What LLM Agent Sessions Reserve on Serverless and Agent Runtimes](<https://devfeed.tech/articles/held-while-waiting-what-llm-agent-sessions-reserve-on-serverless-and-agent-runtimes-145792.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.26480>)

Author: Mekhala Hithyshini Sreenivasa

Published: 2026-11-20T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Serverless](<https://devfeed.tech/topics/serverless.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [virtual machines](<https://devfeed.tech/topics/virtual-machines.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-runtimes](<https://devfeed.tech/tags/agent-runtimes.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-pf](<https://devfeed.tech/tags/cs-pf.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [llm](<https://devfeed.tech/tags/llm.md>), [runtimes](<https://devfeed.tech/tags/runtimes.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [waiting](<https://devfeed.tech/tags/waiting.md>)

### AI overview

On Amazon Bedrock AgentCore, each conversation reserves its own environment while waiting for model replies: the excerpt reports a 2.7-second median wait versus an estimated 5-40 milliseconds of computation. This can exhaust environment capacity well before processor capacity. Two remedies are described: clients can close conversations to release environments sooner (the benchmark found environments otherwise stayed reserved 15 minutes after conversations averaging 33 seconds), while sharing environments across conversations requires platform support. In simulation, sharing one environment among 64 conversations used 59 times fewer environments, with 99% of replies delayed by at most 40 milliseconds. The computation estimates are uncertain; three measurement approaches each produced plausible but too-low values. The excerpt says only one surveyed agent runtime permits sharing in part, and identifies safe isolation of model-selected tools or code as an open problem.

### Source excerpt

arXiv:2611.26480v1 Announce Type: cross Abstract: LLM agents spend nearly all their time waiting for the model. On Amazon Bedrock AgentCore, our agents waited a median of 2.7 seconds for each model reply, then computed for an estimated 5 to 40 milliseconds. AgentCore does not charge for CPU during the wait. But it reserves a separate environment, a virtual machine with its own memory, for every conversation, and keeps it reserved until the conversation is closed. So 1,000 conversations reserve 1,000 environments to do the work of 2 to 15 processor cores. A service runs out of environments long before it runs out of processing power. The shortage has two causes, and each has a fix. An environment stays reserved after its conversation ends: in the customer-service benchmark we ran, a conversation lasts 33 seconds on average, but its environment is held for 15 minutes more unless the client closes it. And an environment serves only one conversation, which is mostly waiting: in our simulation, 64 conversations sharing one environment need 59 times fewer environments, and 99 of every 100 replies are delayed by at most 40 milliseconds. The milliseconds are an estimate because they are hard to measure: a stubbed model, a timer around the model call, and steps run back to back each gave a plausible number that was too low. We show how to avoid all three. Of the two fixes, closing needs only the client. Sharing needs the platform, and of the agent runtimes we surveyed only one allows it, in part. They keep conversations apart because an agent runs tools, and sometimes code, chosen by a model. The open problem is to keep them apart without reserving an environment for each while it waits.

## Enable AI agents to pay for AWS Marketplace x402 products with Amazon Bedrock AgentCore payments

DevFeed: [Enable AI agents to pay for AWS Marketplace x402 products with Amazon Bedrock AgentCore payments](<https://devfeed.tech/articles/enable-ai-agents-to-pay-for-aws-marketplace-x402-products-with-amazon-bedrock-agentcore-payments-144572.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/enable-ai-agents-to-pay-for-aws-marketplace-x402-products-with-amazon-bedrock-agentcore-payments/>)

Author: Madhu Samhitha Vangara

Published: 2026-11-19T23:02:16Z

Content type: release

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [aws-marketplace](<https://devfeed.tech/topics/aws-marketplace.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-billing](<https://devfeed.tech/tags/aws-billing.md>), [aws-marketplace](<https://devfeed.tech/tags/aws-marketplace.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bedrock-agentcore](<https://devfeed.tech/tags/bedrock-agentcore.md>), [bill](<https://devfeed.tech/tags/bill.md>), [billing](<https://devfeed.tech/tags/billing.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [marketplace](<https://devfeed.tech/tags/marketplace.md>), [payments](<https://devfeed.tech/tags/payments.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [x402](<https://devfeed.tech/tags/x402.md>)

### AI overview

Amazon Bedrock AgentCore payments lets agents buy x402-enabled AWS Marketplace products per request, with charges billed in USD to the developer's AWS account. Sellers return a signed fixed-price quote in an HTTP 402 response; AgentCore checks the session budget and issues a payment token, which the agent uses to retry the request. A first purchase creates a seller agreement, and charges are metered to the AWS bill asynchronously. Setup requires a Payment Manager with an AWS Billing connector and the AWS Marketplace service-linked role; an optional AgentCore Gateway connector supports seller discovery. Session caps, approved-seller policies, Private Marketplace allowlists, IAM roles, CloudTrail and Cost Explorer provide controls and audit records. At launch, AWS Billing supports only the x402 exact scheme. Tokens last about five minutes, and the excerpt's sample uses a $0.05 session budget and $0.02 per-request cap.

### Source excerpt

Amazon Bedrock AgentCore payments now supports AWS Marketplace, so agents can discover and buy x402-enabled products, APIs, data, and content and pay in USD on the developer's AWS bill, with no stablecoin wallets or API keys. This post walks through a research agent that finds a tool, pays per request through AWS Billing, and answers with sources.

## From learning to leaderboard: How Cisco upskilled 1,200 engineers in agentic AI with AWS AI League

DevFeed: [From learning to leaderboard: How Cisco upskilled 1,200 engineers in agentic AI with AWS AI League](<https://devfeed.tech/articles/from-learning-to-leaderboard-how-cisco-upskilled-1-200-engineers-in-agentic-ai-with-aws-ai-league-144060.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/from-learning-to-leaderboard-how-cisco-upskilled-1200-engineers-in-agentic-ai-with-aws-ai-league/>)

Author: Rakesh Vangari

Published: 2026-11-19T18:26:22Z

Content type: news

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [Amazon SageMaker](<https://devfeed.tech/topics/amazon-sagemaker.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [Cisco](<https://devfeed.tech/topics/cisco.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Learning](<https://devfeed.tech/topics/learning.md>)

Tags: [2025](<https://devfeed.tech/tags/2025.md>), [2026](<https://devfeed.tech/tags/2026.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-learning](<https://devfeed.tech/tags/ai-learning.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-sagemaker-ai](<https://devfeed.tech/tags/amazon-sagemaker-ai.md>), [aws](<https://devfeed.tech/tags/aws.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bedrock-agentcore](<https://devfeed.tech/tags/bedrock-agentcore.md>), [building](<https://devfeed.tech/tags/building.md>), [cisco](<https://devfeed.tech/tags/cisco.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [engineers](<https://devfeed.tech/tags/engineers.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [leaderboard](<https://devfeed.tech/tags/leaderboard.md>), [learning](<https://devfeed.tech/tags/learning.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

Cisco and AWS used the annual Transformation Fest and AWS AI League to move engineers from AI training into hands-on building: 1,200 Cisco engineers competed in the 2026 agentic AI tournament, following a 2025 Cisco engineer's global win. The league combines a two-hour workshop, self-paced submissions with automated leaderboard feedback, and a live finale. In the 2026 challenge, the winning agent used one agent instead of specialist sub-agents to reduce coordination tokens, put route optimization in an AWS Lambda tool, and prioritized high-value challenges over many low-value coins. The article reports that output tokens--including tool-call arguments--affected scoring, while tool results and the system prompt did not. These are lessons from this competition's scoring setup, not a claim that multi-agent designs are generally inferior.

### Source excerpt

Cisco and AWS used Cisco Transformation Fest and AWS AI League to turn hands-on AI learning into a culture of building. A Cisco engineer won the 2025 AWS AI League global title and 1,200 engineers competed in 2026. This post shares Cisco's journey, lessons from the 2026 winning agent built on Amazon Bedrock AgentCore, and how to host your own league.

## 13 Best Agent Gateways in 2026 for MCP, A2A and LLM Traffic: Kong, Bifrost, AgentCore, Arcade

DevFeed: [13 Best Agent Gateways in 2026 for MCP, A2A and LLM Traffic: Kong, Bifrost, AgentCore, Arcade](<https://devfeed.tech/articles/13-best-agent-gateways-in-2026-for-mcp-a2a-and-llm-traffic-kong-bifrost-agentcore-arcade-144511.md>)

Original publisher: [Read original article](<https://www.marktechpost.com/2026/11/19/best-agent-gateways-2026/>)

Author: Asif Razzaq

Published: 2026-11-19T18:13:21Z

Content type: comparison

Language: en

Sources: [MarkTechPost](<https://devfeed.tech/sources/marktechpost.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [A2A protocol](<https://devfeed.tech/topics/a2a-protocol.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [a2a](<https://devfeed.tech/tags/a2a.md>), [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-gateway](<https://devfeed.tech/tags/agent-gateway.md>), [agent-identity](<https://devfeed.tech/tags/agent-identity.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-infrastructure](<https://devfeed.tech/tags/ai-infrastructure.md>), [ai-shorts](<https://devfeed.tech/tags/ai-shorts.md>), [applications](<https://devfeed.tech/tags/applications.md>), [arcade](<https://devfeed.tech/tags/arcade.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [best](<https://devfeed.tech/tags/best.md>), [bifrost](<https://devfeed.tech/tags/bifrost.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [editors-pick](<https://devfeed.tech/tags/editors-pick.md>), [for-devs](<https://devfeed.tech/tags/for-devs.md>), [gateways](<https://devfeed.tech/tags/gateways.md>), [harness](<https://devfeed.tech/tags/harness.md>), [llm](<https://devfeed.tech/tags/llm.md>), [marketing](<https://devfeed.tech/tags/marketing.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-tool](<https://devfeed.tech/tags/mcp-tool.md>), [model](<https://devfeed.tech/tags/model.md>), [new-releases](<https://devfeed.tech/tags/new-releases.md>), [pricing](<https://devfeed.tech/tags/pricing.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [staff](<https://devfeed.tech/tags/staff.md>), [tech-news](<https://devfeed.tech/tags/tech-news.md>), [technology](<https://devfeed.tech/tags/technology.md>), [tool](<https://devfeed.tech/tags/tool.md>), [top](<https://devfeed.tech/tags/top.md>), [traffic](<https://devfeed.tech/tags/traffic.md>)

### AI overview

The excerpt identifies Kong, Bifrost, Gravitee, and Prisma AIRS as the only listed gateways that natively govern LLM, MCP, and A2A traffic. It says A2A support is weaker elsewhere, often limited to preview, passthrough, or JSON-RPC, and that many identity features such as SSO and token exchange require enterprise licenses. The options differ in deployment and focus: Bifrost is open source and supports self-hosting or air-gapped use; AWS, Azure, and Google offerings integrate with their own platforms but are cloud-specific; and Arcade governs user-authorized tool actions rather than routing models. The excerpt recommends choosing based on traffic types, execution-time identity checks, and where the gateway must run. Its rankings and vendor-specific claims are described as editorial or attributed to vendors and other sources.

### Source excerpt

We ranked the 13 best agent gateways of 2026 by how they govern model, MCP tool and agent-to-agent traffic, with verified pricing, deployment options and the trade-offs each vendor's marketing leaves out. The post 13 Best Agent Gateways in 2026 for MCP, A2A and LLM Traffic: Kong, Bifrost, AgentCore, Arcade appeared first on MarkTechPost.

## OVHcloud AI Summit 2026: 55 launches to take AI into production

DevFeed: [OVHcloud AI Summit 2026: 55 launches to take AI into production](<https://devfeed.tech/articles/ovhcloud-ai-summit-2026-55-launches-to-take-ai-into-production-144298.md>)

Original publisher: [Read original article](<https://blog.ovhcloud.com/en/posts/ai-summit-2026-announcements/>)

Author: OVHcloud Team

Published: 2026-11-19T06:30:00Z

Content type: article

Language: en

Sources: [OVHcloud Blog](<https://devfeed.tech/sources/ovhcloud-blog.md>)

Topics: [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [model-deployment](<https://devfeed.tech/topics/model-deployment.md>), [The Three Main Cloud Service Models](<https://devfeed.tech/topics/the-three-main-cloud-service-models.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [Internationalization (i18n)](<https://devfeed.tech/topics/i18n.md>), [OpenAPI Specification](<https://devfeed.tech/topics/openapi.md>)

Tags: [17](<https://devfeed.tech/tags/17.md>), [2026](<https://devfeed.tech/tags/2026.md>), [accessible](<https://devfeed.tech/tags/accessible.md>), [act](<https://devfeed.tech/tags/act.md>), [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agentic-platform](<https://devfeed.tech/tags/agentic-platform.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-act](<https://devfeed.tech/tags/ai-act.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [gpus](<https://devfeed.tech/tags/gpus.md>), [launches](<https://devfeed.tech/tags/launches.md>), [ovhcloud](<https://devfeed.tech/tags/ovhcloud.md>), [product-news](<https://devfeed.tech/tags/product-news.md>), [production](<https://devfeed.tech/tags/production.md>), [summit](<https://devfeed.tech/tags/summit.md>), [workspace](<https://devfeed.tech/tags/workspace.md>)

### AI overview

OVHcloud announced 55 launches at its 19 November 2026 AI Summit: 38 across cloud foundations and 17 spanning the AI stack. The excerpt emphasizes private networking and security features intended to support production workloads, alongside GPUs, orchestration, inference routing, agents, search, and applications. Olala 1.0 mini 7A1B is an open model with 7 billion parameters and 1 billion active per request; OVHcloud says it can run on an 8 GB GPU or a standard CPU and plans to release it under Apache 2.0. OVHai Workspace combines productivity, website creation, and company-data search; its free alpha launched in France with 5 GB per user, European data hosting, and a commitment not to use customer data for model training. These details describe the supplied excerpt, not necessarily all 55 launches.

### Source excerpt

Olala, OVHai Workspace, GPUs, and AI agents: discover the 55 launches from the OVHcloud AI Summit 2026, and the ones you can try right now.

## Private certificate authority support in Amazon Bedrock AgentCore Identity

DevFeed: [Private certificate authority support in Amazon Bedrock AgentCore Identity](<https://devfeed.tech/articles/private-certificate-authority-support-in-amazon-bedrock-agentcore-identity-141213.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/private-certificate-authority-support-in-amazon-bedrock-agentcore-identity/>)

Author: Aastha Paul

Published: 2026-11-18T20:53:41Z

Content type: tutorial

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [certificates](<https://devfeed.tech/topics/certificates.md>), [OpenID connect (OIDC)](<https://devfeed.tech/topics/oidc.md>), [AWS Certificate Manager](<https://devfeed.tech/topics/aws-certificate-manager.md>), [Keycloak](<https://devfeed.tech/topics/keycloak.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agents](<https://devfeed.tech/tags/agents.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-cloudwatch](<https://devfeed.tech/tags/amazon-cloudwatch.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [amazon-vpc-lattice](<https://devfeed.tech/tags/amazon-vpc-lattice.md>), [application-load-balancer](<https://devfeed.tech/tags/application-load-balancer.md>), [authorization](<https://devfeed.tech/tags/authorization.md>), [aws](<https://devfeed.tech/tags/aws.md>), [certificate](<https://devfeed.tech/tags/certificate.md>), [certificate-authorities](<https://devfeed.tech/tags/certificate-authorities.md>), [certificate-authority](<https://devfeed.tech/tags/certificate-authority.md>), [identity](<https://devfeed.tech/tags/identity.md>), [identity-providers](<https://devfeed.tech/tags/identity-providers.md>), [idp](<https://devfeed.tech/tags/idp.md>), [private](<https://devfeed.tech/tags/private.md>), [self-hosted](<https://devfeed.tech/tags/self-hosted.md>), [support](<https://devfeed.tech/tags/support.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [trust](<https://devfeed.tech/tags/trust.md>)

### AI overview

Amazon Bedrock AgentCore Identity can validate self-hosted private IdPs using a PEM root or intermediate CA certificate stored in Secrets Manager or S3 and referenced by a credential provider. The provider must use a private endpoint and VPC Lattice; the certificate must be valid, PEM encoded, no larger than 16 KB, and stored in the same Region. Secrets Manager also requires the same account, while cross-account S3 requires a bucket owner account ID and access policy. AgentCore reads the certificate at provider creation or update, so changes to the stored file require an update call that includes certificateConfigurations. To rotate with less downtime, trust both old and new CAs, update the IdP server certificate, then remove the old CA and update again. CloudWatch exposes EarliestCertificateDaysToExpiry. AgentCore does not check CRLs or OCSP, so trust persists until the server certificate expires or its CA is removed. Protect write access to the trust store; the certificate itself contains no private key.

### Source excerpt

Amazon Bedrock AgentCore Identity now supports private certificate authorities (CAs), so your agents can connect to self-hosted identity providers that use a private CA. This post shows how to issue an IdP certificate with AWS Private CA, configure a credential provider to trust it, rotate the CA, and protect the certificate.

## Choosing the right network architecture for Amazon Bedrock AgentCore

DevFeed: [Choosing the right network architecture for Amazon Bedrock AgentCore](<https://devfeed.tech/articles/choosing-the-right-network-architecture-for-amazon-bedrock-agentcore-141163.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/networking-and-content-delivery/choosing-the-right-network-architecture-for-amazon-bedrock-agentcore/>)

Author: Daniel Neri

Published: 2026-11-18T19:50:20Z

Content type: comparison

Language: en

Sources: [Networking & Content Delivery](<https://devfeed.tech/sources/networking-content-delivery.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Cloud Networking](<https://devfeed.tech/topics/cloud-networking.md>), [Cloud Architecture](<https://devfeed.tech/topics/cloud-architecture.md>), [Resource Access Manager (RAM)](<https://devfeed.tech/topics/resource-access-manager-ram.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [access-management](<https://devfeed.tech/tags/access-management.md>), [account](<https://devfeed.tech/tags/account.md>), [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agentcore-runtime](<https://devfeed.tech/tags/agentcore-runtime.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-elastic-compute-cloud-amazon-ec2](<https://devfeed.tech/tags/amazon-elastic-compute-cloud-amazon-ec2.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [lattice](<https://devfeed.tech/tags/lattice.md>), [network](<https://devfeed.tech/tags/network.md>), [network-architecture](<https://devfeed.tech/tags/network-architecture.md>), [networking](<https://devfeed.tech/tags/networking.md>), [vpc](<https://devfeed.tech/tags/vpc.md>)

### AI overview

AgentCore runtime VPC support and AgentCore Gateway with VPC Lattice are independent options for reaching private resources; either or both can be used. Runtime VPC support gives agents direct access through ENIs shared by agents with the same subnet and security group configuration. ENI and IP use therefore grow with distinct access patterns, as do security group rules on reachable resources, making this option a better fit when access patterns stay few. Gateway puts authorization and configured access policies at a central point, then routes requests through VPC Lattice resource gateways. In managed mode, AgentCore operates gateways for resources in its own account, reusing them for matching configurations; each gateway consumes one IP per subnet. Self-managed mode lets teams share a gateway across resource configurations and is required for resources in other accounts, which share configurations through AWS RAM. Gateway reduces distributed security group rule sprawl, but targets, policies, credentials, certificates, shares, and quotas still require management. Gateway targets also require publicly trusted TLS certificates, with specific endpoint setup for private API Gateway and

### Source excerpt

As enterprises move AI agents from pilot to production, networking often decides whether a deployment scales. This post compares two Amazon Bedrock AgentCore options for reaching private resources in your VPCs: AgentCore runtime VPC support and AgentCore Gateway with VPC Lattice, and shows how each scales with your access patterns and accounts.

## Securely exposing Amazon Bedrock AgentCore Runtime

DevFeed: [Securely exposing Amazon Bedrock AgentCore Runtime](<https://devfeed.tech/articles/securely-exposing-amazon-bedrock-agentcore-runtime-140906.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/security/securely-exposing-amazon-bedrock-agentcore-runtime/>)

Author: Meriem SMACHE

Published: 2026-11-17T20:31:30Z

Content type: article

Language: en

Sources: [AWS Security Blog](<https://devfeed.tech/sources/aws-security-blog.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Secure token management](<https://devfeed.tech/topics/secure-token-management.md>), [Amazon Cognito](<https://devfeed.tech/topics/amazon-cognito.md>), [rate-limiting](<https://devfeed.tech/topics/rate-limiting.md>), [Amazon DynamoDB](<https://devfeed.tech/topics/amazon-dynamodb.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [access-management](<https://devfeed.tech/tags/access-management.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agentcore-runtime](<https://devfeed.tech/tags/agentcore-runtime.md>), [agentic-workflow](<https://devfeed.tech/tags/agentic-workflow.md>), [agentic-workloads](<https://devfeed.tech/tags/agentic-workloads.md>), [amazon-api-gateway](<https://devfeed.tech/tags/amazon-api-gateway.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-bedrock-guardrails](<https://devfeed.tech/tags/amazon-bedrock-guardrails.md>), [amazon-cloudwatch](<https://devfeed.tech/tags/amazon-cloudwatch.md>), [amazon-cognito](<https://devfeed.tech/tags/amazon-cognito.md>), [amazon-dynamodb](<https://devfeed.tech/tags/amazon-dynamodb.md>), [amazon-vpc](<https://devfeed.tech/tags/amazon-vpc.md>), [api-gateway](<https://devfeed.tech/tags/api-gateway.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [data-governance](<https://devfeed.tech/tags/data-governance.md>), [expert-400](<https://devfeed.tech/tags/expert-400.md>), [microvm](<https://devfeed.tech/tags/microvm.md>), [security-blog](<https://devfeed.tech/tags/security-blog.md>), [security-identity-compliance](<https://devfeed.tech/tags/security-identity-compliance.md>), [serverless](<https://devfeed.tech/tags/serverless.md>), [session](<https://devfeed.tech/tags/session.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

AgentCore Runtime's per-session microVM isolation does not control who reaches it or preserve user identity across the ingress path, so the document presents two layered access patterns. Amazon API Gateway validates the Cognito JWT at the edge and again through AgentCore Identity, binds sessions to users, and forwards the original token through a proxy Lambda and VPC endpoint. This suits teams with existing API Gateway and VPC controls, though long-running calls may exceed API Gateway timeouts. AgentCore Gateway validates the JWT, applies Cedar policies and Guardrails, binds identity claims for unattended work, and exchanges them for a machine token that Runtime requires; its managed entry point and native rate limiting reduce custom infrastructure. Both patterns call for WAF, least-privilege authorization, identity propagation, and audit logging. The document says both CDK samples are starting points, not production-ready deployments.

### Source excerpt

Amazon Bedrock AgentCore Runtime delivers a secure serverless environment to deploy AI agents and tools at scale. When you start talking to your agent, the runtime launches a dedicated isolated session that runs in its own dedicated microVM with a completely sandboxed CPU, memory, and filesystem allocation. This provides strict data governance, helps to prevent [...]

## Secure MCP integrations for AWS DevOps Agent with Amazon Bedrock AgentCore

DevFeed: [Secure MCP integrations for AWS DevOps Agent with Amazon Bedrock AgentCore](<https://devfeed.tech/articles/secure-mcp-integrations-for-aws-devops-agent-with-amazon-bedrock-agentcore-139361.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/devops/secure-mcp-integrations-for-aws-devops-agent-with-amazon-bedrock-agentcore/>)

Author: Lakshmi Kumkala

Published: 2026-11-17T18:24:37Z

Content type: article

Language: en

Sources: [AWS DevOps & Developer Productivity Blog](<https://devfeed.tech/sources/aws-devops-developer-productivity-blog.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [AWS IAM](<https://devfeed.tech/topics/aws-iam.md>), [Amazon CloudWatch](<https://devfeed.tech/topics/amazon-cloudwatch.md>), [DevOps](<https://devfeed.tech/topics/devops.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [admin](<https://devfeed.tech/tags/admin.md>), [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [amazon-athena](<https://devfeed.tech/tags/amazon-athena.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-cloudwatch](<https://devfeed.tech/tags/amazon-cloudwatch.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [amazon-vpc-lattice](<https://devfeed.tech/tags/amazon-vpc-lattice.md>), [audit](<https://devfeed.tech/tags/audit.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [devops-agent](<https://devfeed.tech/tags/devops-agent.md>), [mcp-tools](<https://devfeed.tech/tags/mcp-tools.md>), [model-context-protocol](<https://devfeed.tech/tags/model-context-protocol.md>), [model-context-protocol-mcp](<https://devfeed.tech/tags/model-context-protocol-mcp.md>), [observability](<https://devfeed.tech/tags/observability.md>), [private](<https://devfeed.tech/tags/private.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [rotation](<https://devfeed.tech/tags/rotation.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

AWS DevOps Agent can connect to MCP servers directly or through Amazon Bedrock AgentCore Gateway. Direct registration suits one or two servers in a single account and supports private endpoints through VPC Lattice; each tool must use streamable HTTP and a supported authentication method, and admins classify tools as read-only, mutating, or destructive. AgentCore Gateway offers a single registration and SigV4 connection, centralizes backend credentials, and can apply Cedar policies, unified CloudWatch audit logs, and X-Ray tracing across targets. It is useful when servers or accounts multiply or shared policy and observability are needed; private Gateway targets add central controls, while a direct private connection requires less configuration. The article recommends checking native integrations and existing vendor or sample MCP servers before building a custom one, and starting with a read-only tool in a non-production agent space.

### Source excerpt

As you connect more Model Context Protocol (MCP) tools to AWS DevOps Agent, each one adds its own authentication, credential rotation, and audit overhead. This post shows how to extend AWS DevOps Agent with MCP tools securely using Amazon Bedrock AgentCore, so new tools inherit consistent security, access control, private connectivity, and observability.

## Building a gated review pipeline for AI coding agents on AWS

DevFeed: [Building a gated review pipeline for AI coding agents on AWS](<https://devfeed.tech/articles/building-a-gated-review-pipeline-for-ai-coding-agents-on-aws-139358.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/devops/building-a-gated-review-pipeline-for-ai-coding-agents-on-aws/>)

Author: Owen Hawkins

Published: 2026-11-17T17:29:01Z

Content type: article

Language: en

Sources: [AWS DevOps & Developer Productivity Blog](<https://devfeed.tech/sources/aws-devops-developer-productivity-blog.md>)

Topics: [ai code review](<https://devfeed.tech/topics/ai-code-review.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [Static code analysis](<https://devfeed.tech/topics/static-code-analysis.md>)

Tags: [acceptance-rate](<https://devfeed.tech/tags/acceptance-rate.md>), [access-management](<https://devfeed.tech/tags/access-management.md>), [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agent-hooks](<https://devfeed.tech/tags/agent-hooks.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [agentcore-runtime](<https://devfeed.tech/tags/agentcore-runtime.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [amazon-athena](<https://devfeed.tech/tags/amazon-athena.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-bedrock-knowledge-bases](<https://devfeed.tech/tags/amazon-bedrock-knowledge-bases.md>), [amazon-cloudwatch](<https://devfeed.tech/tags/amazon-cloudwatch.md>), [amazon-eventbridge](<https://devfeed.tech/tags/amazon-eventbridge.md>), [amazon-simple-storage-service-amazon-s3](<https://devfeed.tech/tags/amazon-simple-storage-service-amazon-s3.md>), [amazon-sns](<https://devfeed.tech/tags/amazon-sns.md>), [application-security-testing](<https://devfeed.tech/tags/application-security-testing.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [aws](<https://devfeed.tech/tags/aws.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [kiro](<https://devfeed.tech/tags/kiro.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [policy](<https://devfeed.tech/tags/policy.md>), [review](<https://devfeed.tech/tags/review.md>), [risk](<https://devfeed.tech/tags/risk.md>)

### AI overview

The article proposes a six-control pipeline to manage the review bottleneck created by AI coding agents: centralize versioned standards; run deterministic checks with bounded agent self-correction; use a diverse AI review panel whose findings are checked against code and semantically verified; apply risk-tiered merge policy in a deterministic gate; preserve human approval with review depth matched to risk; and validate generated tests and operational recommendations after merge. On AWS, it maps these controls to services including AgentCore, CodeBuild, S3, Lambda, CodePipeline, EventBridge, and Athena. The panel advises but does not approve or block; humans retain consequential decisions. Rollout starts with a four-week quality baseline, then deterministic gates, an advisory panel, and only later blocking policy after findings earn trust. Measure review time alongside defect escape, rework, stability, panel quality, change size, and cost, since faster decisions alone may not improve quality.

### Source excerpt

AI coding agents generate code faster than humans can review it. This post lays out a gated review pipeline of six controls that pairs deterministic checks with a verified AI review panel, applies risk-tiered policy gates, and keeps humans in charge of every consequential decision, with a concrete AWS implementation for each control.

## How LoanPro built an agentic AI loan servicing assistant with Amazon Bedrock AgentCore

DevFeed: [How LoanPro built an agentic AI loan servicing assistant with Amazon Bedrock AgentCore](<https://devfeed.tech/articles/how-loanpro-built-an-agentic-ai-loan-servicing-assistant-with-amazon-bedrock-agentcore-138238.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/how-loanpro-built-an-agentic-ai-loan-servicing-assistant-with-amazon-bedrock-agentcore/>)

Author: Mariah Miller

Published: 2026-11-17T17:01:08Z

Content type: article

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [AI for customer service automation](<https://devfeed.tech/topics/ai-for-customer-service-automation.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [Amazon EC2](<https://devfeed.tech/topics/amazon-ec2.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agentcore-runtime](<https://devfeed.tech/tags/agentcore-runtime.md>), [agentic-ai-architecture](<https://devfeed.tech/tags/agentic-ai-architecture.md>), [agents-sdk](<https://devfeed.tech/tags/agents-sdk.md>), [ai-assistant](<https://devfeed.tech/tags/ai-assistant.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-bedrock-guardrails](<https://devfeed.tech/tags/amazon-bedrock-guardrails.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [multi-agent-ai](<https://devfeed.tech/tags/multi-agent-ai.md>)

### AI overview

LoanPro built a multi-agent loan servicing assistant that retrieves borrower data, summarizes account status, and recommends actions, helping agents orient faster during calls. A composer routes requests to specialized agents built with the Strands Agents SDK; Amazon Bedrock supplies Claude models, while AgentCore Runtime and Gateway connect agents to LoanPro APIs through Lambda tools. The gateway centralizes authentication and allows tools to be added without redeploying agents. LoanPro applies permission checks, compliance controls, and audit logging; Bedrock Guardrails add content filtering and grounding validation. On 150 SME-labeled accounts, the system met its 99% accuracy target. Reported outcomes include up to 15% shorter calls, summaries in under 15 seconds, and nearly 8% fewer internal tickets. The call-time reduction is attributed to an AllCloud case study; other figures are attributed to LoanPro or its internal benchmarks.

### Source excerpt

LoanPro worked with AWS Partner AllCloud and the AWS Generative AI Innovation Center to build a multi-agent AI assistant on Amazon Bedrock and Amazon Bedrock AgentCore. It gives loan servicing agents instant borrower context and next-best-action recommendations, reducing customer call times by up to 15 percent.

## Build memory-aware AI agents with Agentic Retrieve on Amazon Bedrock Managed Knowledge Base

DevFeed: [Build memory-aware AI agents with Agentic Retrieve on Amazon Bedrock Managed Knowledge Base](<https://devfeed.tech/articles/build-memory-aware-ai-agents-with-agentic-retrieve-on-amazon-bedrock-managed-knowledge-base-136362.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/build-memory-aware-ai-agents-with-agentic-retrieve-on-amazon-bedrock-managed-knowledge-base/>)

Author: Peng Yang

Published: 2026-11-16T22:43:30Z

Content type: tutorial

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Amazon Cognito](<https://devfeed.tech/topics/amazon-cognito.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-bedrock-knowledge-bases](<https://devfeed.tech/tags/amazon-bedrock-knowledge-bases.md>), [base](<https://devfeed.tech/tags/base.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bedrock-agentcore](<https://devfeed.tech/tags/bedrock-agentcore.md>), [build](<https://devfeed.tech/tags/build.md>), [call](<https://devfeed.tech/tags/call.md>), [conversations](<https://devfeed.tech/tags/conversations.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-base](<https://devfeed.tech/tags/knowledge-base.md>), [managed](<https://devfeed.tech/tags/managed.md>), [memory](<https://devfeed.tech/tags/memory.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

Adding `memoryConfiguration` to `AgenticRetrieveStream` lets Amazon Bedrock Managed Knowledge Base restore a conversation, retrieve relevant AgentCore memory, use it to shape knowledge-base searches, and persist the question and answer in the same call. The example uses Cognito's verified email for ACL filtering and stable `sub` for per-user memory identity; IAM session tags and condition keys add defense against cross-user access. Memory summaries capture conversation facts, while preference strategies capture stated response preferences. Memory retrieval is planner-selected, and long-term extraction is asynchronous, so new facts may not be available immediately. Memory failures are best-effort: the trace reports the failure and the answer can continue from the knowledge base. The walkthrough also notes added session-restore latency and the need to manage deletion of both raw events and extracted records.

### Source excerpt

Amazon Bedrock Managed Knowledge Base and Amazon Bedrock AgentCore memory now store conversations, extract facts, and bring long-term memory into a single AgenticRetrieveStream call. This post shows how to build a memory-aware, multi-user assistant where each user sees only the documents they may read and each user's memory stays private.

## How Duco transforms financial data automation with Amazon Bedrock AgentCore

DevFeed: [How Duco transforms financial data automation with Amazon Bedrock AgentCore](<https://devfeed.tech/articles/how-duco-transforms-financial-data-automation-with-amazon-bedrock-agentcore-136363.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/how-duco-transforms-financial-data-automation-with-amazon-bedrock-agentcore/>)

Author: Rob Gates

Published: 2026-11-16T22:06:08Z

Content type: article

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [tenant data protection](<https://devfeed.tech/topics/tenant-data-protection.md>)

Tags: [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-stack](<https://devfeed.tech/tags/ai-stack.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [automation](<https://devfeed.tech/tags/automation.md>), [banks](<https://devfeed.tech/tags/banks.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bedrock-agentcore](<https://devfeed.tech/tags/bedrock-agentcore.md>), [context](<https://devfeed.tech/tags/context.md>), [costs](<https://devfeed.tech/tags/costs.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [data](<https://devfeed.tech/tags/data.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [financial](<https://devfeed.tech/tags/financial.md>), [financial-data](<https://devfeed.tech/tags/financial-data.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

Duco rebuilt its financial operations agent stack on Amazon Bedrock and Amazon Bedrock AgentCore, pairing model choice by task with dedicated per-tenant runtimes, gateways, identity controls, and isolated data infrastructure. To address 300-400 tools generating about 200,000 tokens of context per tenant, it loads MCP skill descriptions on demand; this reduced main context to about 20,000 tokens while preserving prompt caching, with response quality improvements validated through evaluations. Agents support reconciliation onboarding and first-mile exception investigation, with analysts retaining final decisions and high-risk actions requiring authorization. Duco reports reconciliation deployments 10x faster; one global bank saw onboarding costs fall 70% and straight-through processing rise by over 20%.

### Source excerpt

Duco, a data automation platform for tier-one banks, rebuilt its agentic AI stack on Amazon Bedrock and Amazon Bedrock AgentCore. With strict per-tenant isolation, a multi-model strategy, and an MCP skills architecture that cut context overhead by 90%, Duco cut reconciliation deployment time 10x and onboarding costs 70%.

## How MoEngage built agentic customer engagement on Amazon Bedrock AgentCore

DevFeed: [How MoEngage built agentic customer engagement on Amazon Bedrock AgentCore](<https://devfeed.tech/articles/how-moengage-built-agentic-customer-engagement-on-amazon-bedrock-agentcore-136122.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/how-moengage-built-agentic-customer-engagement-on-amazon-bedrock-agentcore/>)

Author: Ashwin Srinivasan

Published: 2026-11-16T18:16:07Z

Content type: article

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [AI Chat](<https://devfeed.tech/topics/ai-chat.md>), [API Governance](<https://devfeed.tech/topics/api-governance.md>)

Tags: [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agentcore-runtime](<https://devfeed.tech/tags/agentcore-runtime.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-bedrock-guardrails](<https://devfeed.tech/tags/amazon-bedrock-guardrails.md>), [amazon-cloudwatch](<https://devfeed.tech/tags/amazon-cloudwatch.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [api](<https://devfeed.tech/tags/api.md>), [apis](<https://devfeed.tech/tags/apis.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [customer-engagement](<https://devfeed.tech/tags/customer-engagement.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [data](<https://devfeed.tech/tags/data.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [mcp-tools](<https://devfeed.tech/tags/mcp-tools.md>), [platform](<https://devfeed.tech/tags/platform.md>), [secure-access](<https://devfeed.tech/tags/secure-access.md>)

### AI overview

MoEngage turned its OpenAPI 3.0 platform APIs into MCP tools with FastMCP, letting Merlin AI agents and external MCP clients work with live campaign, analytics, segment, content, and flow data. The MCP server runs on Amazon Bedrock AgentCore runtime and calls existing APIs, which continue to enforce permissions and data residency. Requests use existing JWT authentication; workspace and user context travel in headers outside model-visible tool arguments, and each user session runs in an isolated environment. Merlin AI includes embedded, conversational, custom, and per-customer decisioning agents, with activity logs and options for autonomous or human-reviewed actions. MoEngage reports that Glance reached campaign go-live 50% faster and had a 38% uplift in push click-through rates; platform-wide figures include 60-70% less manual effort for channel, timing, and frequency decisions and over 50% lower AI infrastructure costs versus self-hosted models. AgentCore feature availability varies by AWS Region.

### Source excerpt

MoEngage built Merlin AI, a set of AI agents on Amazon Bedrock and Amazon Bedrock AgentCore that let marketing and product teams draft, analyze, and adjust campaigns from a single conversation. Learn how MoEngage turned its existing APIs into MCP tools and kept each tenant's data isolated while giving agents secure access to live platform data.

## Novo Nordisk modernizes manufacturing process documents with Amazon Bedrock AgentCore

DevFeed: [Novo Nordisk modernizes manufacturing process documents with Amazon Bedrock AgentCore](<https://devfeed.tech/articles/novo-nordisk-modernizes-manufacturing-process-documents-with-amazon-bedrock-agentcore-136124.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/novo-nordisk-modernizes-manufacturing-process-documents-with-amazon-bedrock-agentcore/>)

Author: Elias Bedmar

Published: 2026-11-16T17:04:11Z

Content type: article

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [hybrid-search](<https://devfeed.tech/topics/hybrid-search.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>), [knowledge-management](<https://devfeed.tech/topics/knowledge-management.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>)

Tags: [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [agents-sdk](<https://devfeed.tech/tags/agents-sdk.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-bedrock-data-automation](<https://devfeed.tech/tags/amazon-bedrock-data-automation.md>), [amazon-neptune](<https://devfeed.tech/tags/amazon-neptune.md>), [amazon-opensearch-serverless](<https://devfeed.tech/tags/amazon-opensearch-serverless.md>), [anthropic-claude](<https://devfeed.tech/tags/anthropic-claude.md>), [aws-cdk](<https://devfeed.tech/tags/aws-cdk.md>), [aws-identity-and-access-management-iam](<https://devfeed.tech/tags/aws-identity-and-access-management-iam.md>), [aws-lambda](<https://devfeed.tech/tags/aws-lambda.md>), [aws-step-functions](<https://devfeed.tech/tags/aws-step-functions.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [graphrag](<https://devfeed.tech/tags/graphrag.md>), [grounded](<https://devfeed.tech/tags/grounded.md>), [hybrid-search](<https://devfeed.tech/tags/hybrid-search.md>), [knowledge-graph](<https://devfeed.tech/tags/knowledge-graph.md>), [manufacturing](<https://devfeed.tech/tags/manufacturing.md>), [manufacturing-technology](<https://devfeed.tech/tags/manufacturing-technology.md>), [novo-nordisk](<https://devfeed.tech/tags/novo-nordisk.md>), [process-intelligence](<https://devfeed.tech/tags/process-intelligence.md>)

### AI overview

Novo Nordisk's Manufacturing Technology team built a process-intelligence assistant on Amazon Bedrock AgentCore to answer manufacturing questions with cited information from controlled documents. It pairs a curated knowledge graph in Amazon Neptune, which captures process hierarchy and relationships, with hybrid semantic and BM25 search in Amazon OpenSearch Serverless, followed by reranking. In guided mode, the agent resolves scope--such as site, product generation, or equipment--from graph data before searching; it uses approved, effective documents by default and states when content is unavailable or ambiguous. The article reports that SME tasks that once took hours or days can take minutes. It describes a vault of about four million documents, while noting that document metadata may be mapped in the graph before full text is indexed; the assistant distinguishes these states.

### Source excerpt

Novo Nordisk's Manufacturing Technology team within the Tablet area team built a process-intelligence assistant on Amazon Bedrock AgentCore, using a GraphRAG architecture that pairs a knowledge graph in Amazon Neptune with hybrid search in Amazon OpenSearch Serverless to turn millions of controlled manufacturing documents into grounded, cited answers.

## Automate Bedrock AgentCore Security with Harness

DevFeed: [Automate Bedrock AgentCore Security with Harness](<https://devfeed.tech/articles/automate-bedrock-agentcore-security-with-harness-136342.md>)

Original publisher: [Read original article](<https://www.harness.io/blog/control-access-to-ai-agents-deployed-on-aws-bedrock-agentcore>)

Author: Akshit Madan

Published: 2026-11-16T08:09:00Z

Content type: article

Language: en

Sources: [Harness](<https://devfeed.tech/sources/harness-blog.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>), [CI/CD](<https://devfeed.tech/topics/cicd.md>), [canary release](<https://devfeed.tech/topics/canary-release.md>), [Security](<https://devfeed.tech/topics/security.md>), [AWS IAM](<https://devfeed.tech/topics/aws-iam.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-behavior](<https://devfeed.tech/tags/agent-behavior.md>), [agent-service](<https://devfeed.tech/tags/agent-service.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [automate](<https://devfeed.tech/tags/automate.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-iam](<https://devfeed.tech/tags/aws-iam.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bedrock-agentcore](<https://devfeed.tech/tags/bedrock-agentcore.md>), [canary](<https://devfeed.tech/tags/canary.md>), [custom](<https://devfeed.tech/tags/custom.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [harness](<https://devfeed.tech/tags/harness.md>), [iam](<https://devfeed.tech/tags/iam.md>), [jwt](<https://devfeed.tech/tags/jwt.md>), [rollback](<https://devfeed.tech/tags/rollback.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

Harness CD treats a Bedrock AgentCore agent as a deployable service and applies its authorizer configuration on each deployment. AWS_IAM accepts callers using AWS SigV4 credentials; CUSTOM_JWT validates OIDC/OAuth tokens against a discovery URL and configured audiences, clients, scopes, or claims. Either can be restricted to calls through the AgentCore Gateway. The authorizer governs inbound callers, while the execution role governs the agent's outbound AWS access. For canary traffic shifting, provision a Gateway and target rule pointing to the initial endpoint; without one, deployments cut over directly and skip traffic shifting. A pipeline can deploy revisions, shift traffic in stages with validations or approvals between shifts, and roll back to the previous revision on failure. Agent deployments require the CDS_AGENT_RUNTIME_DEPLOYMENT feature flag.

### Source excerpt

Set the agent authorizer (AWS_IAM or CUSTOM_JWT) in Harness. Then every Bedrock AgentCore deployment ships with access control, canary rollout, and rollback. | Blog

## Architecture patterns for fast session startup on Amazon Bedrock AgentCore runtime

DevFeed: [Architecture patterns for fast session startup on Amazon Bedrock AgentCore runtime](<https://devfeed.tech/articles/architecture-patterns-for-fast-session-startup-on-amazon-bedrock-agentcore-runtime-133423.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/architecture-patterns-for-fast-session-startup-on-amazon-bedrock-agentcore-runtime/>)

Author: Evandro Franco

Published: 2026-11-13T22:02:39Z

Content type: article

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [app startup](<https://devfeed.tech/topics/app-startup.md>), [Amazon CloudWatch](<https://devfeed.tech/topics/amazon-cloudwatch.md>)

Tags: [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agentcore-runtime](<https://devfeed.tech/tags/agentcore-runtime.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bedrock-agentcore](<https://devfeed.tech/tags/bedrock-agentcore.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [environment](<https://devfeed.tech/tags/environment.md>), [expert-400](<https://devfeed.tech/tags/expert-400.md>), [fast](<https://devfeed.tech/tags/fast.md>), [first](<https://devfeed.tech/tags/first.md>), [how-to](<https://devfeed.tech/tags/how-to.md>), [image](<https://devfeed.tech/tags/image.md>), [keep](<https://devfeed.tech/tags/keep.md>), [patterns](<https://devfeed.tech/tags/patterns.md>), [post](<https://devfeed.tech/tags/post.md>), [request](<https://devfeed.tech/tags/request.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [session](<https://devfeed.tech/tags/session.md>), [startup](<https://devfeed.tech/tags/startup.md>)

### AI overview

AgentCore runtime V2 builds an initialized environment once, snapshots its memory and disk, then restores it in a fresh microVM for each session. Memory-held objects return ready, while image files are fetched on first read; init work therefore moves to deploy time, though create or update takes a few minutes and larger snapshots can increase restore time and memory cost. The post recommends measuring `Latency` and `OverheadLatency`, moving static setup into init, keeping dynamic and per-session values in the handler, and using build hooks for files or tools init cannot prepare. For sub-second interactive starts, pre-warm a session when the user opens the app; this can hide startup delay but uses a session even if the user never sends a prompt.

### Source excerpt

Amazon Bedrock AgentCore runtime V2 snapshots your initialized environment and restores it for each new session, so session start no longer grows with image size. This post explains how V2 starts a session, how to measure session start time, and four patterns to keep work off the first request.

## How IGNYTE runs candidate search with Amazon S3 Vectors

DevFeed: [How IGNYTE runs candidate search with Amazon S3 Vectors](<https://devfeed.tech/articles/how-ignyte-runs-candidate-search-with-amazon-s3-vectors-133435.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/storage/how-ignyte-runs-candidate-search-with-amazon-s3-vectors/>)

Author: Saurabh Gupta

Published: 2026-11-13T19:52:38Z

Content type: article

Language: en

Sources: [AWS Storage Blog](<https://devfeed.tech/sources/aws-storage-blog.md>)

Topics: [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [Amazon OpenSearch Service](<https://devfeed.tech/topics/amazon-opensearch-service.md>), [Embeddings](<https://devfeed.tech/topics/embeddings.md>), [vector embeddings in AI](<https://devfeed.tech/topics/vector-embeddings-in-ai.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Amazon SageMaker](<https://devfeed.tech/topics/amazon-sagemaker.md>), [Parquet files in Amazon S3](<https://devfeed.tech/topics/parquet-files-in-amazon-s3.md>)

Tags: [agentcore](<https://devfeed.tech/tags/agentcore.md>), [amazon-opensearch-service](<https://devfeed.tech/tags/amazon-opensearch-service.md>), [amazon-sagemaker-ai](<https://devfeed.tech/tags/amazon-sagemaker-ai.md>), [amazon-simple-storage-service-s3](<https://devfeed.tech/tags/amazon-simple-storage-service-s3.md>), [approximate-nearest-neighbor-search](<https://devfeed.tech/tags/approximate-nearest-neighbor-search.md>), [aws-glue](<https://devfeed.tech/tags/aws-glue.md>), [aws-lambda](<https://devfeed.tech/tags/aws-lambda.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [embeddings](<https://devfeed.tech/tags/embeddings.md>), [intermediate-200](<https://devfeed.tech/tags/intermediate-200.md>), [layout](<https://devfeed.tech/tags/layout.md>), [metadata](<https://devfeed.tech/tags/metadata.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [semantic](<https://devfeed.tech/tags/semantic.md>)

### AI overview

IGNYTE moved embeddings for more than 1 billion contacts from OpenSearch Service to Amazon S3 Vectors; more than 800 million contacts are currently embedded. OpenSearch Service retains full profiles and handles structured filters. A scheduled batch pipeline loads company records first, then enriches contact records, generates embeddings, and writes profiles and vectors to their respective stores. Vectors are partitioned by continent, with minimal metadata for query filters. Searches embed the recruiter's query, retrieve the 100 closest contacts from the matching S3 Vectors index, then apply skills, experience, and other structured filters in OpenSearch Service. The article reports that the full agent matching workflow averages under 30 seconds after migration, compared with 3-4 minutes before; this is an end-to-end result, not a single vector query.

### Source excerpt

Ignyte moved the embeddings for more than 1 billion contacts from Amazon OpenSearch Service to Amazon S3 Vectors, keeping OpenSearch Service for structured filtering. See the per-continent index layout, the minimal-metadata design, and the batch pipeline behind its two-hop semantic candidate search.

## Build a self-healing ETL pipeline with Amazon Bedrock AgentCore

DevFeed: [Build a self-healing ETL pipeline with Amazon Bedrock AgentCore](<https://devfeed.tech/articles/build-a-self-healing-etl-pipeline-with-amazon-bedrock-agentcore-133386.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/big-data/build-a-self-healing-etl-pipeline-with-amazon-bedrock-agentcore/>)

Author: Kevin Tinn

Published: 2026-11-13T19:08:10Z

Content type: tutorial

Language: en

Sources: [AWS Big Data Blog](<https://devfeed.tech/sources/aws-big-data-blog.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [etl](<https://devfeed.tech/topics/etl.md>), [AWS Glue](<https://devfeed.tech/topics/aws-glue.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [data lake](<https://devfeed.tech/topics/data-lake.md>), [knowledge-engineering](<https://devfeed.tech/topics/knowledge-engineering.md>), [aws-sns](<https://devfeed.tech/topics/aws-sns.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-glue](<https://devfeed.tech/tags/aws-glue.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bedrock-agentcore](<https://devfeed.tech/tags/bedrock-agentcore.md>), [build](<https://devfeed.tech/tags/build.md>), [can](<https://devfeed.tech/tags/can.md>), [data](<https://devfeed.tech/tags/data.md>), [data-lake](<https://devfeed.tech/tags/data-lake.md>), [domain](<https://devfeed.tech/tags/domain.md>), [errors](<https://devfeed.tech/tags/errors.md>), [etl](<https://devfeed.tech/tags/etl.md>), [etl-pipeline](<https://devfeed.tech/tags/etl-pipeline.md>), [pipeline](<https://devfeed.tech/tags/pipeline.md>), [self-healing](<https://devfeed.tech/tags/self-healing.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The described AWS Glue pipeline routes records that fail schema validation to a four-agent system on Amazon Bedrock AgentCore. A correction agent queries a Bedrock Knowledge Base for domain guidance and looks up precomputed strategies in S3 Vectors in parallel, selecting the higher-confidence result. At the default 0.7 threshold, it applies qualifying corrections; otherwise, the orchestrator sends an SNS alert for human review. A persistence agent writes corrected records to both corrected and transformed data lake zones. The sample annotates records with the chosen strategy rather than changing field values; direct transformations require extending its correction function. With repository credentials configured, a remediation agent can analyze the source error and open a GitHub pull request; without them, that step is skipped. The post outlines AWS CDK deployment and sample-data workflow, and notes required AWS services, model access, Python 3.10+, and a container runtime for local testing.

### Source excerpt

Build a self-healing ETL pipeline on AWS Glue and Amazon Bedrock AgentCore that automatically corrects bad records using domain knowledge, writes the fixes back to the data lake, and can open pull requests to prevent the same errors from recurring.

## How Natera designed an agentic AI system for lab ops with Amazon Bedrock AgentCore

DevFeed: [How Natera designed an agentic AI system for lab ops with Amazon Bedrock AgentCore](<https://devfeed.tech/articles/how-natera-designed-an-agentic-ai-system-for-lab-ops-with-amazon-bedrock-agentcore-130935.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/how-natera-designed-an-agentic-ai-system-for-lab-ops-with-amazon-bedrock-agentcore/>)

Author: Ariel Jirau

Published: 2026-11-12T21:47:07Z

Content type: tutorial

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-ai](<https://devfeed.tech/tags/agentic-ai.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [automated](<https://devfeed.tech/tags/automated.md>), [base](<https://devfeed.tech/tags/base.md>), [construction](<https://devfeed.tech/tags/construction.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [customer-solutions](<https://devfeed.tech/tags/customer-solutions.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [faster](<https://devfeed.tech/tags/faster.md>), [first](<https://devfeed.tech/tags/first.md>), [full](<https://devfeed.tech/tags/full.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-base](<https://devfeed.tech/tags/knowledge-base.md>), [lab](<https://devfeed.tech/tags/lab.md>), [ops](<https://devfeed.tech/tags/ops.md>)

### AI overview

Natera's SWARM system uses Amazon Bedrock AgentCore to turn lab operations knowledge into ticket diagnostics, cutting average first response from 17.4 hours to about 8 minutes and generating reports for 96.2% of incoming tickets before engineer review. It separates autonomous ticket analysis from interactive engineer sessions, with both runtimes sharing a versioned library of 33 independently testable skills. Jira tickets flow through EventBridge, SQS, and Lambda; diagnostics retrieve from a knowledge base built from vendor manuals, historical tickets, and operational data. Natera emphasizes data quality, reporting that adding missing manuals raised one instrument family's accuracy from 71% to 75% without model changes. Its controls include short-lived OIDC/STS deployment credentials, least-privilege IAM, private networking, audit logging, and excluding patient-identifiable information from the index and model. A continuous engineer-verified evaluation loop grades responses by instrument family. The reported results are based on a 90-day production evaluation; only 269 of 524 evaluated tickets had confidence labels and verified resolutions for accuracy comparisons.

### Source excerpt

Natera built SWARM, an agentic AI system on Amazon Bedrock AgentCore that captures institutional lab-operations knowledge and deploys it at scale. This post walks through the full architecture, from knowledge base construction to deployment and evaluation, delivering about 130x faster first response and 96.2% automated coverage across support tickets.

## AI-driven database investigation using MCP, Agent Skills, and AWS DevOps Agent

DevFeed: [AI-driven database investigation using MCP, Agent Skills, and AWS DevOps Agent](<https://devfeed.tech/articles/ai-driven-database-investigation-using-mcp-agent-skills-and-aws-devops-agent-131174.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/database/integrate-mcp-tools-agent-skills-and-aws-devops-agent-for-ai-driven-database-investigation/>)

Author: Sudhir Amin

Published: 2026-11-12T18:34:07Z

Content type: article

Language: en

Sources: [AWS Database Blog](<https://devfeed.tech/sources/aws-database-blog.md>)

Topics: [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [sql-server](<https://devfeed.tech/topics/sql-server.md>), [RDS for SQL Server](<https://devfeed.tech/topics/rds-for-sql-server.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Monitoring](<https://devfeed.tech/topics/monitoring.md>), [AWS IAM](<https://devfeed.tech/topics/aws-iam.md>), [Amazon Bedrock](<https://devfeed.tech/topics/amazon-bedrock.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [DevOps](<https://devfeed.tech/topics/devops.md>), [MSP MCP](<https://devfeed.tech/topics/msp-mcp.md>)

Tags: [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agent-skills](<https://devfeed.tech/tags/agent-skills.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-rds](<https://devfeed.tech/tags/amazon-rds.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [aws](<https://devfeed.tech/tags/aws.md>), [aws-lambda](<https://devfeed.tech/tags/aws-lambda.md>), [connect](<https://devfeed.tech/tags/connect.md>), [database](<https://devfeed.tech/tags/database.md>), [dba](<https://devfeed.tech/tags/dba.md>), [devops](<https://devfeed.tech/tags/devops.md>), [devops-agent](<https://devfeed.tech/tags/devops-agent.md>), [diagnostic](<https://devfeed.tech/tags/diagnostic.md>), [investigation](<https://devfeed.tech/tags/investigation.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [rds-for-sql-server](<https://devfeed.tech/tags/rds-for-sql-server.md>), [skills](<https://devfeed.tech/tags/skills.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>)

### AI overview

AWS DevOps Agent can investigate RDS for SQL Server incidents by combining CloudWatch and Database Insights telemetry with SQL-specific MCP tools hosted in Lambda and exposed through Amazon Bedrock AgentCore Gateway. A Markdown skill defines triage thresholds, diagnostic steps, and report format; built-in telemetry identifies the problem type, while Gateway tools retrieve session, query, plan, and index details. In the example, an alarm led the agent to identify a head blocker holding a lock on dbo.Orders, with about 14 sessions waiting. It linked recurring spikes to a five-minute transaction pattern, noted it could not identify the client process, and recommended removing the delay, bounding client timeouts, and raising the alarm threshold. Access is constrained through SigV4, an allowlist, Secrets Manager credential retrieval by Lambda, and a read-only SQL login. The sample requires Database Insights, suitable database permissions, private VPC access, and supported AWS services and region.

### Source excerpt

Learn how to connect Amazon RDS for SQL Server diagnostic tools to AWS DevOps Agent through Amazon Bedrock AgentCore Gateway. MCP tools run in AWS Lambda behind a governed Gateway endpoint, and an investigation skill encodes your DBA team's method so the agent can triage alarms and run autonomous, auditable database investigations.

## Run agents securely and efficiently with the next generation AgentCore runtime

DevFeed: [Run agents securely and efficiently with the next generation AgentCore runtime](<https://devfeed.tech/articles/run-agents-securely-and-efficiently-with-the-next-generation-agentcore-runtime-130772.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/run-agents-securely-and-efficiently-with-the-next-generation-agentcore-runtime/>)

Author: Madhu Parthasarathy

Published: 2026-11-12T17:59:59Z

Content type: release

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [AI Infrastructure](<https://devfeed.tech/topics/ai-infrastructure.md>), [virtual machines](<https://devfeed.tech/topics/virtual-machines.md>), [agentic workflows](<https://devfeed.tech/topics/agentic-workflows.md>)

Tags: [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agentcore-runtime](<https://devfeed.tech/tags/agentcore-runtime.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [amazon-simple-storage-service-amazon-s3](<https://devfeed.tech/tags/amazon-simple-storage-service-amazon-s3.md>), [announcements](<https://devfeed.tech/tags/announcements.md>), [billing](<https://devfeed.tech/tags/billing.md>), [compute](<https://devfeed.tech/tags/compute.md>), [data](<https://devfeed.tech/tags/data.md>), [faster](<https://devfeed.tech/tags/faster.md>), [foundational-100](<https://devfeed.tech/tags/foundational-100.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [isolation](<https://devfeed.tech/tags/isolation.md>), [sessions](<https://devfeed.tech/tags/sessions.md>), [usage-based-billing](<https://devfeed.tech/tags/usage-based-billing.md>)

### AI overview

Amazon Bedrock AgentCore runtime's next generation keeps each agent session in a hardware-isolated Firecracker MicroVM with its own identity, policy, and audit trail, while adding larger sessions, faster startup, usage-based memory reclamation, and storage mounts. Sessions scale up to 8 vCPUs and 32 GB, support container images up to 10 GB, and are reported to start in under two seconds independent of image size and concurrency. Released memory is reclaimed within minutes, and idle agents scale to zero; always-on agents can instead use committed baseline pricing with bursts up to four times baseline. Sessions can mount and save filesystems such as Amazon S3 through FUSE, bringing data into the stated trust boundary. The article says per-session storage-folder scoping through session-labeled credentials is planned by re:Invent. Availability is reported across AWS Regions in North and South America, Europe, and Asia Pacific.

### Source excerpt

AI agents now run multi-step workloads for hours and act on behalf of users, raising the bar for secure, scalable agent compute. Learn how the next generation of Amazon Bedrock AgentCore runtime delivers hardware-isolated sessions with faster starts, more compute, usage-based billing, and isolation that now extends to your data.

## Build composable, interoperable multi-agent systems with A2A on AWS

DevFeed: [Build composable, interoperable multi-agent systems with A2A on AWS](<https://devfeed.tech/articles/build-composable-interoperable-multi-agent-systems-with-a2a-on-aws-130561.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/build-composable-interoperable-multi-agent-systems-with-a2a-on-aws/>)

Author: Amit Chaudhary

Published: 2026-11-12T15:42:21Z

Content type: article

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [A2A protocol](<https://devfeed.tech/topics/a2a-protocol.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Amazon Web Services](<https://devfeed.tech/topics/aws.md>), [supervisor agent pattern](<https://devfeed.tech/topics/supervisor-agent-pattern.md>), [Cloud Networking](<https://devfeed.tech/topics/cloud-networking.md>), [Amazon GuardDuty](<https://devfeed.tech/topics/amazon-guardduty.md>)

Tags: [a2a](<https://devfeed.tech/tags/a2a.md>), [a2a-protocol](<https://devfeed.tech/tags/a2a-protocol.md>), [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [aws](<https://devfeed.tech/tags/aws.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bedrock-agentcore](<https://devfeed.tech/tags/bedrock-agentcore.md>), [build](<https://devfeed.tech/tags/build.md>), [ecs](<https://devfeed.tech/tags/ecs.md>), [framework](<https://devfeed.tech/tags/framework.md>), [langchain](<https://devfeed.tech/tags/langchain.md>), [multi-agent](<https://devfeed.tech/tags/multi-agent.md>), [multi-agent-system](<https://devfeed.tech/tags/multi-agent-system.md>), [multi-agent-systems](<https://devfeed.tech/tags/multi-agent-systems.md>), [oauth](<https://devfeed.tech/tags/oauth.md>), [systems](<https://devfeed.tech/tags/systems.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [with](<https://devfeed.tech/tags/with.md>)

### AI overview

The reference architecture shows cross-organization agents collaborating through A2A without sharing secrets or depending on each other's framework: a LangChain orchestrator on ECS calls a Strands compliance agent on Bedrock AgentCore, which calls back to an enterprise context agent for account metadata. Agent Cards expose curated skills for discovery and routing; OAuth JWTs from separate Cognito user pools authenticate calls in both directions. The deployment uses three Jupyter notebooks across two AWS accounts, with synthetic compliance findings, an end-to-end test, and token rejection checks. The sample requires specified AWS accounts, model access and Jupyter setup, incurs resource charges, and is intended for sandbox use; production adaptations are outlined, including stronger client authentication and private connectivity.

### Source excerpt

Build a composable, interoperable multi-agent system on AWS with the Agent-to-Agent (A2A) protocol. A LangChain orchestrator on Amazon ECS communicates with a Strands agent on Amazon Bedrock AgentCore across organizational boundaries, using bidirectional, OAuth-authenticated calls, with neither side depending on the other's framework or SDK.

## Fine-grained access control for Amazon Bedrock Managed Knowledge Base tools

DevFeed: [Fine-grained access control for Amazon Bedrock Managed Knowledge Base tools](<https://devfeed.tech/articles/fine-grained-access-control-for-amazon-bedrock-managed-knowledge-base-tools-130562.md>)

Original publisher: [Read original article](<https://aws.amazon.com/blogs/machine-learning/fine-grained-access-control-for-amazon-bedrock-managed-knowledge-base-tools/>)

Author: Renya Kujirada

Published: 2026-11-12T15:40:24Z

Content type: article

Language: en

Sources: [Artificial Intelligence](<https://devfeed.tech/sources/artificial-intelligence.md>)

Topics: [Access Control](<https://devfeed.tech/topics/access-control.md>), [Amazon Bedrock Knowledge Bases](<https://devfeed.tech/topics/amazon-bedrock-knowledge-bases.md>), [Amazon Bedrock AgentCore](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md>), [Amazon Cognito](<https://devfeed.tech/topics/amazon-cognito.md>), [AWS IAM](<https://devfeed.tech/topics/aws-iam.md>), [Zero Trust](<https://devfeed.tech/topics/zero-trust.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [advanced-300](<https://devfeed.tech/tags/advanced-300.md>), [agentcore](<https://devfeed.tech/tags/agentcore.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [amazon-bedrock-agentcore](<https://devfeed.tech/tags/amazon-bedrock-agentcore.md>), [amazon-bedrock-knowledge-bases](<https://devfeed.tech/tags/amazon-bedrock-knowledge-bases.md>), [base](<https://devfeed.tech/tags/base.md>), [based](<https://devfeed.tech/tags/based.md>), [bedrock](<https://devfeed.tech/tags/bedrock.md>), [bedrock-agentcore](<https://devfeed.tech/tags/bedrock-agentcore.md>), [control](<https://devfeed.tech/tags/control.md>), [fine](<https://devfeed.tech/tags/fine.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [identity](<https://devfeed.tech/tags/identity.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-base](<https://devfeed.tech/tags/knowledge-base.md>), [managed](<https://devfeed.tech/tags/managed.md>), [technical-how-to](<https://devfeed.tech/tags/technical-how-to.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

The design keeps a shared agent from choosing whose documents it searches: a gateway interceptor overwrites the MCP tool's `userContext` with the email from a JWT validated by the gateway, and Managed Knowledge Base ACL awareness filters results to that user's permitted documents. ACL awareness trusts the supplied identity, so it is not authorization by itself. Policy in AgentCore can independently deny calls when the injected user ID does not match the JWT email; a knowledge base resource policy can also restrict `Retrieve` and `GetDocumentContent` to the gateway execution role, blocking direct calls and other principals. These defenses have limits: the resource policy cannot distinguish another gateway using the same role, and explicit denial can affect other consumers. The sample requires a verified email claim; Cognito token customization needs the Essentials or Plus plan. S3 ACL updates apply after sync, and ACL mistakes silently omit documents.

### Source excerpt

Learn how to expose an Amazon Bedrock Managed Knowledge Base to AI agents as MCP tools through Amazon Bedrock AgentCore Gateway while keeping per-user access control. A request interceptor injects verified identity, Policy in AgentCore validates it independently, and a resource-based policy restricts direct access to the knowledge base.

[Next page](<https://devfeed.tech/topics/amazon-bedrock-agentcore.md?cursor=WyIyMDI2LTExLTEyVDE1OjQwOjI0KzAwOjAwIiwgIjQ4N2Q5MzY3LTA5Y2MtNGQ1OS04N2UxLWQwOGNiOTE4YWM0NCJd>)