Amazon Bedrock AgentCore
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 71
- AWS recaps September Bedrock, AgentCore and Strands updates
An AWS Machine Learning Blog recap says Amazon Bedrock added several capabilities for AI builders in September: Amazon Bedrock Managed Agents powered by OpenAI is now in public preview, and the AgentCore runtime has lower cold-start latency and scales sessions to zero when idle. Strands introduced an open source agent harness that AWS says matches popular harnesses on accuracy while using 28 percent fewer tokens, plus Strands Decider 2B, an open source 2B-parameter decision model that returns answers locally in about 115ms. Bedrock also lists OpenAI's GPT-6 Astra, Sol and Luna, along with Claude Fable 5.1, Claude Opus 5.5, Claude Sonnet 5.5, Moonshot AI's Kimi K3 and xAI's Grok 4.6 and 4.7, and added native ServiceNow, Salesforce and Zendesk connectors to its managed knowledge base.
AWS Machine Learning Blog · 🔥 0 - SailPoint Navigate 2026: enterprises race to secure AI agents at machine speed
At its Navigate 2026 conference in Austin, SailPoint framed identity security for AI agents as a board-level priority: one Fortune 500 company that insisted it had no agents discovered 10,000 of them, many holding standing admin privileges. SailPoint pitched its Autonomous Identity approach along with just-in-time authorization and a Lineage Map tracing the chain from human to agent to tool to data, arguing that policy enforcement must sit outside the agent; its CEO said machine identities now number 109 for every human. AWS said tasks on Amazon Bedrock AgentCore grew 15-fold in the first six months of the year, with a new agent created every 4.5 seconds.
SiliconANGLE AI · 🔥 0 - Xianyu becomes a grey market for AI: H20 servers, cheap tokens, Gemini subs
A 略大参考 article republished by TMTPost argues that Alibaba's second-hand marketplace Xianyu has become a clearing house for AI "offcuts" in China: retired NVIDIA H20 chips and complete servers (an 8-GPU 141GB H20 machine listed near 2.8 million yuan), cut-rate API tokens, and Gemini Pro subscriptions at about 5 yuan a month versus the official $19.99. Sellers also offer custom agent building, cloud deployment and one-stop website services. The article cautions that most listings serve as display and lead generation, with larger enterprises sticking to established channels.
钛媒体 · 🔥 0 - From demo to production: what an agent harness actually adds
The piece frames an agent as "model + harness" and splits the harness into a development half (memory, tools and MCP, retrieval, prompt orchestration) and an operations half (observability, evals, guardrails, routing, cost control, deployment and scaling) — capabilities the model itself does not provide. It then builds the same finance agent, FinBot, two ways: a managed Amazon Bedrock AgentCore Harness configured via CreateHarness/InvokeHarness calls, with per-session Firecracker microVMs, managed memory and automatic tracing; and a self-managed LangChain agent on the reader's own Kubernetes cluster behind the open-source Agent Router (formerly Envoy AI Gateway). The trade-offs come down to where provider credentials live, who carries the operational burden, and whether you pay a vendor bill or infrastructure plus engineering time.
InfoQ 中文 AI&大模型 · 🔥 0 - One prompt hijacked every AgentCore agent in an AWS account, Zenity says
Security firm Zenity Labs published research on a vulnerability chain it calls "AgentCorruption": chat access to a single public Amazon Bedrock AgentCore agent was enough to trick it, in plain language, into querying the instance metadata service at 169.254.169.254 and sending its own temporary AWS credentials to an external server. Using AgentCore's overly broad default execution role, the researchers then listed and invoked every agent in the same account and region, downloaded their source code and container images, read private user-agent conversations and secrets from AWS Secrets Manager, and poisoned long-term memory to make the hijack persistent. Zenity says it reported the findings to AWS on 25 December 2025; AWS has since made IMDSv2 the default for new AgentCore deployments and narrowed the default role.
The Decoder · 🔥 0 - AWS playbook: six-week program turns non-engineers into AI agent builders
In an AWS Machine Learning Blog post, Amazon Web Services describes a six-week program that pairs non-engineering business staff with mentors and production-grade tools—Kiro, Amazon Bedrock, Strands Agents SDK and AWS Lambda agents—for about four hours a week, ending in a working prototype. A team of four customer-facing employees with no engineering background built WealthWise, a multi-agent financial advisory prototype with five agents (portfolio analysis, risk assessment, financial planning and more), a dual-server Node.js and Python Flask architecture, four DynamoDB tables and, the team says, sub-5-second responses for complex reasoning; it took first place in the demo judging. AWS reports that self-rated “strong or expert” understanding of agentic AI rose from 27% to 82% among participants, and readiness to identify AI opportunities from 41% to 85%.
AWS Machine Learning Blog · 🔥 0 - Cornerstone cuts database diagnosis time 78% with Bedrock-based Orion AI
Cornerstone OnDemand's Enterprise DataOps team built Orion AI, a multi-agent system on Amazon Bedrock and AWS's open-source Strands Agents framework, using a hub-and-spoke topology in which a meta-orchestrator routes work to 13 domain-specific agents, including three SQL Server diagnostics agents. According to the AWS blog post, database diagnosis time fell from about 45 minutes to 10 minutes per incident (a 78% reduction), manual lifecycle steps dropped roughly 70%, SRE-to-data-team reporting lag went from 15 minutes to real time, and redundant alerts fell by a median of 65%. A three-person team delivered the system in six months on Amazon ECS, with Amazon Bedrock AgentCore providing cross-session memory.
AWS Machine Learning Blog · 🔥 0 - Building a context-aware AI assistant with OpenClaw on AWS AgentCore
An AWS Machine Learning Blog tutorial shows how to run the open-source agentic system OpenClaw on Amazon Bedrock AgentCore runtime and give it continuity with AgentCore memory, using a gardening assistant called Sprout as the example; the whole system ships in a single CloudFormation template that deploys with one command. On each message the agent retrieves long-term memory records from a per-user namespace, ranks explicit preferences ahead of inferred facts, and injects them into the system prompt, degrading gracefully to a memory-free answer if retrieval times out within a 3-second budget or errors. Tasks are routed to different models — Claude Haiku 4.5 for text and Claude Sonnet 4.5 for image diagnosis — with Telegram as the front door. The author estimates roughly $1–2 per month for light personal use versus about $35 per month for an always-on EC2 instance.
AWS Machine Learning Blog · 🔥 0 - AWS tutorial: building a voice travel concierge with AgentCore and Nova Sonic
An AWS Machine Learning Blog tutorial walks through deploying a voice travel concierge on Amazon Bedrock AgentCore: Amazon Nova 2.5 Sonic handles real-time speech-to-speech, Strands Agents defines the agent, and AgentCore Gateway exposes airline backend endpoints as MCP tools, with Amazon Bedrock Knowledge Bases answering policy questions via RAG. The post says Nova 2.5 Sonic improves tool calling and multi-step agentic task completion and supports bidirectional streaming, asynchronous tool calls, latency masking and barge-in. The solution deploys with AWS CDK and a React front end on Amplify.
AWS Machine Learning Blog · 🔥 0 - AWS ships MCP server to promote Amazon Quick resources across accounts
An AWS blog post details the Amazon Quick Resource Migrator, a sample Model Context Protocol server hosted on Amazon Bedrock AgentCore runtime that promotes Amazon Quick agents, action connectors, knowledge bases, flows and spaces from a development AWS account to production. It reads and recreates resources through the Amazon Quick (Quick Sight) API, replays source permissions in the target account, offers a read-only preview, is idempotent across re-runs, and writes versioned S3 backups with a restore tool. S3 documents behind knowledge bases are not copied, and connector credentials are created as placeholders and must be re-authenticated in the target account; full source is in an aws-samples repository.
AWS Machine Learning Blog · 🔥 0 - AWS shows layered evaluation for multi-agent systems with AgentCore Evaluations
An AWS blog post explains how to assess multi-agent systems with Amazon Bedrock AgentCore Evaluations, combining built-in evaluators (helpfulness, task success, instruction following, tool selection) with custom evaluators for domain rules such as constraint satisfaction, route feasibility and SQL correctness. The walkthrough uses a fictional retailer, AnyCompany Retail, building a supply-chain decisioning system with the Strands Agents SDK: one orchestrator agent plus optimization, distribution, routing and analytics sub-agents running on AgentCore runtime with memory and observability. A separate explainability layer of six cross-cutting evaluators checks decision rationale, evidence attribution, constraint reasoning, trade-off explanation, tool-use explainability and assumption disclosure; AgentCore Evaluations runs in on-demand mode for benchmarks and CI/CD gates, and online mode to sample production traces into CloudWatch dashboards and alarms.
AWS Machine Learning Blog · 🔥 0
Experience and discussion from the community
Share my Amazon Bedrock AgentCore experienceAsk about Amazon Bedrock AgentCore
Nobody has shared their experience with Amazon Bedrock AgentCore yet.