AWS Expands Bedrock AgentCore as Agent Knowledge Retrieval Becomes Managed Infrastructure
AWS announced Managed Knowledge Base, Web Search on AgentCore and AgentCore harness general availability on June 17, 2026.
Key takeaways
AWS announced several Amazon Bedrock AgentCore updates at AWS Summit New York on June 17, 2026. The releases include Managed Knowledge Base, Web Search on AgentCore, AgentCore harness general availability, policy integrations and optimization capabilities, showing that production AI agents are becoming managed infrastructure around knowledge, execution and governance.
AWS announced multiple Amazon Bedrock AgentCore updates during AWS Summit New York on June 17, 2026. The main releases include Amazon Bedrock Managed Knowledge Base, Web Search on AgentCore, AgentCore harness general availability and new policy and optimization capabilities.
Managed Knowledge Base is designed to reduce the work required to build enterprise RAG pipelines. It brings together connectors, parsing, storage, retrieval, embeddings, reranking and model selection as a managed capability. Web Search on AgentCore lets agents retrieve current web information inside the AWS environment and return source URLs, snippets, titles and publication dates.
For ENHE AI readers, the practical lesson is that agent selection should include knowledge access, source traceability, permission controls, account isolation, observability, cost management and recovery options. Production AI agents are becoming infrastructure, not just model prompts.
What this means for everyday users
ENHE users should use this as an AI agent platform checklist. Cloud, local and workflow automation tools should be evaluated by source traceability, knowledge connectors, tool permissions, account security, observability, cost controls and failure recovery.
Tools you may use
Related tutorials
Related Tools And Tutorials
Use the following ENHE AI sections to continue from the news signal into tool selection, account-service guidance, or practical learning.
Related reading
Nine-Stage AI Agent Evaluation Checklist: From First Commit to Production Drift
AWS published a nine-stage production AI-agent evaluation framework built around Amazon Bedrock AgentCore on October 16, 2026. It follows an agent from defining quality and comparing experiments through merge checks, deployment gates, canary scoring, adversarial testing, drift detection, live pulse monitoring, and feedback-driven improvement. The framework evaluates five dimensions—safety, quality, performance, cost, and operational control—at tool, individual-agent, and multi-agent levels. This durable guide converts the public framework into a vendor-neutral checklist for ordinary teams, with minimum evidence, ownership, and stop conditions designed to catch soft failures where latency and uptime remain normal while answer quality quietly declines over time.
Three agents produce a track together on persistent AgentCore runtimes
On September 30, AWS published a hands-on example in which three specialized agents collaborate to render, generate, and clear a music track on Amazon Bedrock AgentCore Runtime Instances. The sample colocates agents on one GPU-backed instance, gives them persistent shared storage, and uses a shared session ID for handoffs and resumable work. AWS says Runtime Instances can host agents built with different frameworks; the walkthrough uses Strands and a file-backed session manager. It is an implementation example, not evidence of unattended production readiness. Deploying it provisions cloud resources such as runtimes, storage, and container repositories, so teams should estimate ongoing charges, narrow IAM permissions, and test cleanup and failure isolation before adapting the pattern.
OpenAI combines legal search, specialized instructions, and governance controls in Astra for Law
OpenAI introduced Astra for Law on September 17, combining GPT-6 Astra with a legal search index, instructions for legal analysis and writing, and an ecosystem of professional plugins. OpenAI says the index searches United States case law, statutes, regulations, court rules, and administrative decisions across more than 230 million URLs. On 200 questions from a private Vals AI Legal Research Bench validation set, the complete setup passed an overall correctness check on 54.0% of questions, versus 38.7% for GPT-6 Astra with web search alone at the highest reasoning effort. Initial access is limited to selected firms, with API availability planned later, and lawyers must still verify authority and jurisdiction.
AWS shows how AgentCore can deliver the same MCP tools and interactive widgets across compatible AI hosts
AWS published a technical walkthrough for running MCP Apps on Amazon Bedrock AgentCore on September 11. In the reference architecture, an AI host discovers MCP tools and resources, invokes a tool through WAF and AgentCore Gateway, and receives structured content from business logic implemented with Lambda and DynamoDB. When a tool points to a resource URI, the host reads self-contained widget HTML and renders it in a sandboxed iframe with the structured result injected through the MCP Apps lifecycle. AWS presents MCP Apps as a host-agnostic standard, so one server can provide the same tools and widgets to compatible AI hosts. The production guidance still requires strict argument validation, trust-boundary controls, caller restrictions, monitoring, and cost review.
OpenAI launches the Agents API public beta with the Codex harness and hosted sandboxes
OpenAI introduced the Agents API in public beta on September 10, exposing the harness and infrastructure behind Codex to developers. A single API call can define an agent task, model, tools, and environment. Teams may run it in an OpenAI-hosted sandbox, on their own infrastructure, or with listed ecosystem-provider integrations. OpenAI says the API supports MCP, custom functions, built-in tools such as web search, automatic context compaction for long sessions, and optional parallel subagents. The hosted sandbox can be configured with files, packages, skills, and plugins. The API is available to all developers in public beta with no separate API fee beyond token and tool charges. Teams should validate permissions, tool behavior, observability, and recovery paths before treating beta workflows as production-ready.
AWS connects AgentCore evaluations to GitHub Actions for pre-merge agent regression gates
AWS published a reference workflow on September 8 for integrating Amazon Bedrock AgentCore Evaluations with GitHub Actions. The pipeline deploys a development agent and an OAuth-protected MCP server, invokes representative prompts, collects OpenTelemetry traces, and scores behavior before allowing a pull request to proceed. AWS describes built-in dimensions such as helpfulness, correctness, goal success, tool selection, tool parameters, and trajectory order, with custom and code-based evaluators available. The post compares three authentication patterns: evaluating stored traces, using a pre-authorized test user, or issuing machine-to-machine credentials for CI. Its implementation uses the third pattern. Teams should validate that CI credentials cannot escape their intended environment, that evaluation samples cover important failures, and that score variance, latency, evaluator cost, and rollback behavior are visible before treating the threshold as a release gate.
Summary
Amazon Bedrock AgentCore's new capabilities show that production AI agents need managed knowledge, execution, governance and optimization infrastructure, not only stronger models.
Sources
AWS News Blog：Introducing Amazon Bedrock Managed Knowledge Base，2026年6月17日
AWS News Blog：Announcing Web Search on Amazon Bedrock AgentCore，2026年6月17日
AWS Machine Learning Blog：Amazon Bedrock AgentCore harness is now generally available，2026年6月18日
AWS Machine Learning Blog：New in Amazon Bedrock AgentCore，2026年6月17日
About Amazon：AWS Summit New York 2026 AI agent innovations，2026年6月18日
FAQ
What is this ENHE AI article about?
AWS announced several Amazon Bedrock AgentCore updates at AWS Summit New York on June 17, 2026. The releases include Managed Knowledge Base, Web Search on AgentCore, AgentCore harness general availability, policy integrations and optimization capabilities, showing that production AI agents are becoming managed infrastructure around knowledge, execution and governance.
Why is this AI update worth watching?
AWS announced new Amazon Bedrock AgentCore capabilities on June 17, 2026. Managed Knowledge Base packages enterprise RAG infrastructure into a managed capability. Web Search on AgentCore gives agents current web grounding while keeping queries inside the AWS environment. AgentCore harness is generally available and wraps runtime, memory, identity, observability and tool access. The update shows production AI agents shifting toward governed knowledge and execution infrastructure.
What does it mean for everyday AI users?
ENHE users should use this as an AI agent platform checklist. Cloud, local and workflow automation tools should be evaluated by source traceability, knowledge connectors, tool permissions, account security, observability, cost controls and failure recovery.
Where can readers continue learning on ENHE AI?
Readers can continue with ENHE AI software apps, AI skill tutorials, and AI account service guidance to turn the news signal into practical action.
Table of contents
AWS Expands Bedrock AgentCore as Agent Knowledge Retrieval Becomes Managed Infrastructure