Amazon Bedrock AgentCore
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 71
- AWS adds billing for AgentCore Marketplace purchases
AWS launched AWS Billing as a payment option for Amazon Bedrock AgentCore payments on AWS Marketplace. According to AWS Machine Learning Blog, agents can discover and purchase x402-enabled software, APIs, data, and content per request in USD, with session spending limits, approved-seller policies, and transaction records in AWS CloudTrail and AWS Cost Explorer.
AWS Machine Learning Blog · 🔥 3 - Accenture and AWS Detail Six Ways to Reduce AI Token Costs
The AWS Machine Learning Blog describes a six-lever approach Accenture used to reduce token spending in four client engagements spanning telecom, insurance, mining and a large enterprise deployment. The methods cover cost attribution, workload-aware model routing, context reduction, semantic caching, model distillation and infrastructure optimization, and are available through Amazon Bedrock. Where savings were measured, Accenture reported token-spending reductions of about 40–85%, though client names were withheld and the results may vary by workload.
AWS Machine Learning Blog · 🔥 3 - Cisco Engineers Compete in AWS AI League Agentic AI Tournament
AWS reports that 1,200 Cisco engineers competed in an agentic AI tournament at Cisco Transformation Fest 4.0 in 2026. AWS account team members provided pre-event training so participants without prior agentic AI experience could enter, according to AWS. The competition included two challenges: building agents with Amazon Bedrock AgentCore and fine-tuning models in Amazon SageMaker Studio. Participants submitted to a live leaderboard and received automated feedback, while finalists competed in a live finale.
AWS Machine Learning Blog · 🔥 3 - AWS publishes an AgentCore Gateway pattern for private API inspection
AWS Machine Learning Blog published a tested architecture pattern for connecting Amazon Bedrock AgentCore Gateway to private APIs and MCP servers through a hub-and-spoke network with centralized firewall inspection. The pattern places an Amazon VPC Lattice resource gateway in the network account and includes six configuration decisions, validation checks, CloudFormation templates, test scripts, troubleshooting guidance, quotas, and an address plan. AWS built and tested it in us-east-1 using three member accounts and an AWS Organizations management account, and recommends adapting it to each organization’s account architecture.
AWS Machine Learning Blog · 🔥 0 - AWS cuts token use and latency for large-JSON agents
AWS Machine Learning Blog details three composable strategies used in Flightscape’s Training Schedule Optimization agent: offloading large artifacts to Amazon S3, paging tool results, and compacting context. The production agent handles JSON payloads larger than 20 MB and provides more than 40 tools for crew scheduling, resource allocation, and business-rule validation. On AWS’s internal benchmark with a 23 MB payload, the optimizations reduced token consumption by up to 71% and average latency by up to 80%.
AWS Machine Learning Blog · 🔥 0 - AWS FDE expands AI deployment service to 15 countries
AWS says Forward Deployed Engineering is now available to commercial and public-sector customers in 15 countries. The service uses 45-day sprints to build AI systems in customers’ own AWS accounts, with each sprint priced under the FDE Terms and billed through the account. AWS describes the offering as combining production deployment, reusable foundations, workflows and governance.
AWS Machine Learning Blog · 🔥 0 - AWS launches SMART for WhatsApp agents on AgentCore
AWS Machine Learning Blog introduced SMART (Social Messaging Agent Runtime Toolkit), an open-source Python SDK and Terraform stack for adding a WhatsApp channel layer to agents running on Amazon Bedrock AgentCore. It handles webhook authentication and normalization, media processing, persistent memory, scheduling, authenticated outbound triggers, message templates, observability and infrastructure deployment through one command. AWS says Webmotors used SMART to shorten delivery from a planned two months to six weeks, but that deployment outcome comes from the company's own account.
AWS Machine Learning Blog · 🔥 0 - LoanPro deploys multi-agent loan-servicing assistant with AWS
LoanPro built a production multi-agent loan-servicing assistant with AWS Partner AllCloud and the AWS Generative AI Innovation Center. The system uses Amazon Bedrock and Amazon Bedrock AgentCore to retrieve live borrower data, generate account summaries and recommend servicing actions. Its Data Retrieval Tool spans eight LoanPro API endpoints and synthesizes about 1,400 fields per account. AgentCore Gateway exposes the APIs as tools over the Model Context Protocol, handles authentication and manages connections, while AWS Lambda provides the integration layer. LoanPro said the deployment applies role-based access controls and compliance guardrails and records AI actions in its audit trail. AllCloud’s published case study reported customer call times reduced by up to 15%, but the supplied report provides no independent measurement methodology.
AWS Machine Learning Blog · 🔥 0 - AWS adds AgentCore memory to Bedrock Agentic Retrieve
AWS says Amazon Bedrock Managed Knowledge Base can now use Amazon Bedrock AgentCore memory within the same AgenticRetrieveStream request. The integration stores and restores conversations, extracts durable facts, and adds relevant memories to knowledge-base retrieval while retaining per-user isolation and ACL-based document filtering. Developers enable it with memoryConfiguration, while the service manages conversation persistence and fact extraction.
AWS Machine Learning Blog · 🔥 0 - Duco rebuilds financial-data agent stack on Amazon Bedrock AgentCore
AWS reports that Duco rebuilt its agentic AI stack for financial-data automation using Amazon Bedrock and Amazon Bedrock AgentCore. The architecture combines strict per-tenant isolation, a multi-model strategy and on-demand MCP skills loading to reduce context overhead. AWS says reconciliation deployments are 10 times faster; for one global bank, onboarding costs fell by 70% and straight-through processing increased by more than 20%. The report attributes these results to Duco's client deployments.
AWS Machine Learning Blog · 🔥 0 - Multi-agent coordination patterns for manufacturing
A tutorial organizes multi-agent coordination into two tiers: Tier 1 uses predefined flows, including sequential pipelines, conditional workflows and routers, while Tier 2 lets a model choose the path at runtime. It recommends beginning with deterministic Tier 1 workflows and reserving Tier 2 for tasks whose subtasks emerge during execution. The tutorial also identifies anti-patterns such as unbounded iteration, unstructured natural-language handoffs, premature adoption of multiple agents and unapproved real-world actions. Suggested safeguards include hard iteration and token limits, typed handoffs, observability, business rules and human approval before execution.
AWS Machine Learning Blog · 🔥 0 - MoEngage Deploys Merlin AI on Amazon Bedrock AgentCore
AWS Machine Learning Blog described how MoEngage built Merlin AI, a set of AI agents that operate on live platform data, using Amazon Bedrock, Amazon Bedrock AgentCore, and the Model Context Protocol. Its MCP Connector exposes existing OpenAPI-compatible campaign, analytics, segmentation, content, and flow capabilities as tools, with JWT validation, isolated sessions, and tenant-scoped access. MoEngage reports customer improvements including faster campaign launches and higher push click-through rates, but the figures are vendor-reported.
AWS Machine Learning Blog · 🔥 0 - Novo Nordisk deploys GraphRAG assistant for manufacturing docs on Amazon Bedrock AgentCore
The AWS Machine Learning Blog describes how Novo Nordisk's Manufacturing Technology team built an agentic process-intelligence assistant on Amazon Bedrock AgentCore to answer questions about regulated manufacturing documentation. The system pairs a curated knowledge graph with hybrid dense-vector and BM25 search across Amazon OpenSearch and Amazon Neptune, adds a Bedrock Rerank stage, and clarifies ambiguous questions before retrieving. AWS says the solution helped subject-matter experts finish work that previously took hours or days in minutes.
AWS Machine Learning Blog · 🔥 0 - Natera’s SWARM automates lab instrument support
AWS reports that Natera built SWARM, an agentic AI system on Amazon Bedrock AgentCore, to capture institutional knowledge and support diagnostics for laboratory instruments. During a 90-day production evaluation, average first response time fell from 17.4 hours to roughly eight minutes, and 96.2% of incoming tickets received an automated diagnostic report before engineer review, according to Natera and AWS. The evaluation covered 524 tickets, but only 269 had confidence labels and engineer-verified resolutions available for comparison; the 37 low-confidence cases were too few for statistically meaningful conclusions.
AWS Machine Learning Blog · 🔥 0 - AWS launches AgentCore Runtime V2 for heavier AI agent workloads
AWS announced the next generation of Amazon Bedrock AgentCore Runtime, with each session supporting up to 8 virtual CPUs, 32 GB of memory and a 10 GB container image. Runtime V2 uses snapshot-based startup, isolated Firecracker microVMs and memory reclamation for workloads that include compiling large projects, operating browsers and loading local models. AWS says it is the default for new AgentCore environments across 19 regions, while existing environments can select V2 or remain on V1.
AWS Machine Learning Blog · 🔥 0 - AWS details cross-organizational A2A multi-agent reference architecture
An AWS post walks through a deployed reference architecture in which a LangChain-based enterprise orchestrator communicates with a Strands Agents-based SaaS agent across separate AWS accounts using the Agent-to-Agent (A2A) protocol. Three agents run in the two accounts with OAuth authentication in both directions. Each account has its own Amazon Cognito user pool, allowing each side to authenticate through its own identity provider without sharing secrets. The system is deployed through three Jupyter notebooks and tested end to end.
AWS Machine Learning Blog · 🔥 0 - AWS details granular access control for Bedrock knowledge tools
AWS Machine Learning Blog published a guide to securing Amazon Bedrock Managed Knowledge Base tools for multi-tenant AI agents. Its architecture uses Amazon Bedrock AgentCore Gateway and Model Context Protocol tools, with trusted code injecting verified user attributes and overriding model-generated search context. Additional AgentCore policies and resource-based controls provide independent safeguards.
AWS Machine Learning Blog · 🔥 0 - AWS Introduces Agent DLC for Production AI Agent Evaluation
The AWS Machine Learning Blog introduced the Agent Development Lifecycle (Agent DLC), a framework for evaluating non-deterministic AI agents with two feedback loops and an explicit acceptance standard. It recommends repeatedly running examples, versioning prompt and configuration changes, and scheduling evaluations to detect drift caused by external dependencies. The article also presents a measured example in which high aggregate retrieval precision concealed a coverage problem, though the supplied excerpt omits the underlying measurements.
AWS Machine Learning Blog · 🔥 0 - Amazon Bedrock AgentCore Launches in AWS China Regions
Amazon Web Services said Amazon Bedrock AgentCore is now generally available in the AWS China Beijing and Ningxia regions, operated by Guanghuan Xinwang and West Cloud Data respectively. The company also described upgrades spanning its Agentic AI stack, security and governance, AI-ready data foundation, and local technical support; most capability claims were not independently verified. AWS said 277 new services and features had launched in the China regions this year, bringing the cumulative total above 2,800.
智东西 · 🔥 0 - Build autonomous Java agents with Spring AI and Bedrock AgentCore
AWS Machine Learning Blog provides a technical walkthrough for building autonomous AI agents in Java with Spring AI 2.0, spring-ai-agentcore 2.0, and Amazon Bedrock AgentCore. It demonstrates planning, tool and API calls, conversation memory, identity isolation, managed runtime, and both a single-agent travel assistant and a multi-agent document-processing architecture. The platform capabilities are presented as AWS vendor claims and have not been independently validated in the report.
AWS Machine Learning Blog · 🔥 0 - Codex on Amazon Bedrock: AWS details enterprise access paths
AWS Machine Learning Blog says OpenAI Codex can use Amazon Bedrock for inference with supported OpenAI models while the client continues to run on the developer workstation. It recommends beginning with a small, least-privilege Native AWS Access pilot, then considering AgentCore Gateway or an existing LLM Gateway for routing, guardrails, and request-path controls. The open-source Guidance for Codex on AWS repository provides quick starts and configurations for these access paths.
AWS Machine Learning Blog · 🔥 0 - AWS Publishes Guide to 140-Plus AI/ML Sessions at re:Invent 2026
Amazon Web Services has published an attendee guide for its re:Invent 2026 AI/ML track, which AWS says includes more than 140 sessions within a broader program of more than 2,000 learning sessions. The event runs from November 30 through December 4. Session formats include breakouts, chalk talks, builder sessions, workshops, code talks and lightning talks, with interactive AI experiences at the AWS Village. AWS says attendees unable to travel to Las Vegas can watch keynotes live and see recorded breakout sessions on its Events YouTube channel a few days after the event.
AWS Machine Learning Blog · 🔥 0 - AWS proposes push-based sync for Agent Registry records
AWS outlined an event-driven architecture for synchronizing AWS Agent Registry records with MCP server tools and schemas. AWS CloudTrail captures UpdateAgentRuntime API calls, Amazon EventBridge routes matching events, and AWS Lambda queries the MCP server, compares its tools with the registry, and updates the matching record. The design supports single-account deployments and cross-account event forwarding. Updated records return to DRAFT status and must pass the approval workflow before becoming discoverable again. The sample requires an existing matching registry record, does not automatically register previously unknown servers, has no manual force-sync path, and does not retry when a cold MCP server returns zero tools.
AWS Machine Learning Blog · 🔥 0 - AWS offers 23 reusable generative AI assets
The AWS Generative AI Innovation Center, now part of AWS Frontier AI Engineering & Services, has published a curated catalog of 23 production-ready, open-source generative AI assets. Available since 2023, they include RAG pipeline components, document-ingestion modules, agent-scaffolding templates, evaluation frameworks and deployment guidance. Examples include FAST and the Agentic Chatbot Accelerator. AWS says customer solutions built with these assets have achieved 50-fold increases in testing capacity, 90% reductions in engineering hours and deployment timelines reduced from months to weeks, citing companies including DoorDash, Lyft and Ricoh.
AWS Machine Learning Blog · 🔥 0 - AWS open-sources UAEF for framework-agnostic AI agent evaluation
Amazon Web Services has open-sourced the Universal Agent Evaluation Framework (UAEF), a system that evaluates AI agents built on different frameworks through adapters that normalize each framework's traces into a common format. UAEF scores those traces with 36 built-in metrics across seven quality dimensions, stores results in Amazon DynamoDB and Amazon S3, and produces statistical reports plus optional LLM-generated insights on Amazon Bedrock. According to The Next Web, a score drop of more than 5% is flagged as a regression, and AWS says 12 organizations in telecom, healthcare and financial services have used the tool to compare agent versions before release.
AWS Machine Learning Blog · 🔥 0 - AWS Launches Bedrock AgentCore Web Search API
AWS announced that the Web Search API for Amazon Bedrock AgentCore is now available, letting applications and agents retrieve current web results through a single call signed with existing AWS credentials. Results can include titles, URLs, publication dates, and relevant extracts, with request-level domain and date filters, while AgentCore Gateway can apply shared source policies. AWS also detailed IAM controls, SDK support, six launch regions, and pricing of $7 per 1,000 queries.
AWS Machine Learning Blog · 🔥 0 - AWS introduces Amazon Bedrock AgentCore Evaluations
AWS Machine Learning Blog introduced Amazon Bedrock AgentCore Evaluations, combining AWS-built-in evaluators with DeepEval and AutoEval metrics for measuring AI-agent behavior. The service supports on-demand evaluation for direct session testing, online evaluation of sampled production traffic, and batch evaluation against fixed session datasets, while also offering custom LLM-as-a-judge evaluators. AWS states that its built-in evaluators are quality-tested and benchmarked for reliability, though the evidence comes from the vendor's own tutorial.
AWS Machine Learning Blog · 🔥 0 - Trovata launches autonomous agents for corporate treasury
Trovata has introduced autonomous treasury agents that run on schedules, triggers, or rules to monitor activity, explain variance, detect anomalies, and deliver updates. AWS Machine Learning Blog says the agents were built with Amazon Bedrock and Amazon Bedrock AgentCore, access treasury data through Trovata’s verified API layer, and support role-based access control.
AWS Machine Learning Blog · 🔥 0 - TCS details its agentic test orchestrator built on Amazon Bedrock AgentCore
Tata Consultancy Services built an Agentic Test Orchestrator that converts business requirements into executable, governed API and browser-based UI tests using specialized agents, project-context retrieval, and tenant-isolated AWS infrastructure. TCS and AWS say the system connects requirement ingestion, generation, execution, correction, and reporting in one traceable workflow while leaving quality engineers responsible for review, risk analysis, and release decisions. In a controlled internal benchmark covering roughly 100 scenarios, TCS reported reducing average effort from about 200 hours to 24 hours, an 88% decrease.
AWS Machine Learning Blog · 🔥 0 - AWS Presents Seven-Layer Pluggable Agentic AI Framework
AWS Machine Learning Blog presented the Pluggable Agentic AI Framework as a seven-layer reference architecture for building production-scale multi-agent applications on Amazon Bedrock AgentCore. The layers separate data and knowledge, model inference, orchestration, security and guardrails, application, observability, and business value and cost tracking, with stable contracts that allow underlying technologies to be replaced. AWS also said the architecture is not a substitute for production security hardening, testing, and review.
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.