AWS published a technical walkthrough for building MCP Apps—interactive HTML widgets rendered inside AI hosts like ChatGPT and Claude—using Amazon Bedrock AgentCore's runtime and Gateway components. The reference implementation, a unicorn rental app, demonstrates host-agnostic rich UI delivered through a single MCP server.
AWS has launched model caching for Amazon SageMaker Inference on HyperPod, pre-loading model weights and container images onto cluster nodes to cut inference pod startup times from tens of minutes to seconds. The feature targets large models like DeepSeek-R1, which previously took 30+ minutes to become servable during scale-out events.
Amazon Bedrock Knowledge Bases now offers TwelveLabs Marengo Embed 3.0 as a managed embedding model, letting teams run natural language queries like 'show me the penalty kick' directly against video, audio, and image archives. The service is generally available in two AWS Regions, with pricing tied to standard Bedrock model invocation rates.
AWS published a reference architecture showing how to deploy a WhatsApp ordering assistant on Amazon Bedrock AgentCore, using Nova 2 Lite for text and Nova 2 Sonic for voice, with shared cross-channel memory and MCP-based tool access to backend systems.
t54's x402-secure trust layer, running on Amazon Bedrock AgentCore payments, has processed over 20 million agent-initiated micropayments without human approval. The system uses a deterministic risk-scoring gate to block payments to unsafe endpoints before funds settle.
AWS has published a reference architecture showing how to build multi-tenant agentic document chat applications using Amazon Bedrock Managed Knowledge Base. The design handles per-user document isolation, asynchronous ingestion up to 50 MB, and agentic multi-hop retrieval with citations, offloading infrastructure work from development teams.
Amazon Bedrock AgentCore Evaluations now scores AI agents regardless of the framework they're built on, by reading OpenTelemetry and OpenInference instrumentation instead of requiring a specific SDK. The service automatically decodes traces from six named frameworks and extends coverage to any library following the same telemetry conventions.
Amazon Bedrock AgentCore now lets teams write agent governance rules in plain English and automatically convert them into Dogwood, an open-source policy language, including support for time-based and cumulative constraints. The update extends Policy Authoring beyond simple parameter restrictions to rate limiting, sequential tool-call ordering, and Amazon Bedrock Guardrails integration.
Amazon Bedrock AgentCore's Web Search connector now supports per-request domain filtering and published-date windows, enforced server-side. The update, shipped as connector version 1.2.0, also expands availability to AWS regions in Dublin and Tokyo.
Amazon Bedrock AgentCore Payments, built with Coinbase and Stripe, is now generally available after a May preview. The service lets AI agents autonomously pay for paywalled content, APIs, and per-inference compute using stablecoin wallets with spending caps and audit logging.
AWS published a technical guide on designing custom composite reward functions for multi-turn reinforcement fine-tuning (RFT) of Amazon Nova models via Nova Forge's Bring Your Own Orchestration (BYOO) capability. The post covers GRPO-based reward scoring, combining outcome rewards, behavioral rewards, and penalties, plus a serverless multi-turn RL option now generally available.
Amazon has released Microsoft 365 extensions for its Quick AI assistant, embedding agentic capabilities directly into Word, Excel, PowerPoint, and Outlook. The extensions run entirely in the cloud, require no client-side installation, and connect to existing Quick data sources like Salesforce, Jira, Slack, and SharePoint.
Branded communications company First Orion adopted Amazon Nova Act as a pre-release partner in March 2025 to replace fragile Selenium and Playwright test scripts with natural-language QA automation. The shift let QA analysts author tests directly without waiting on automation engineers to translate test cases into code.
Amazon, Cursor, Microsoft, OpenAI, and Vercel have released Agent Plugins, an open standard defining a single package format for AI agent extensions. Version 1.0.0 covers Agent Skills and MCP servers, but leaves marketplaces, permissions, and runtime out of scope.
Amazon Bedrock AgentCore now supports temporal policies—stateful authorization rules that evaluate an AI agent's entire session history, not just individual tool calls. The feature runs at the AgentCore Gateway, outside agent code, so it cannot be bypassed by prompt manipulation or agent bugs.
Amazon Bedrock AgentCore now supports temporal policies that evaluate sequences of agent actions, not just single calls, powered by a new open-source policy language called Dogwood. AWS also added rate limiting at the gateway layer to cap token, request, and connection consumption per user.
AWS published a suite of six Agent Skills that automate the full lifecycle of Amazon Bedrock Automated Reasoning policies—from rule extraction to deployment—directly from coding agents like Claude Code, Cursor, Kiro, and Codex. The skills wrap Bedrock's formal-logic verification APIs in structured workflows built on Anthropic's open Agent Skills format.
AWS published a technical breakdown of an MCP bridge that connects cloud-hosted AI agents on Amazon Bedrock AgentCore to MCP servers running on a user's local machine. The architecture, used internally in a finance assistant with over 41,000 conversations in its first year, tunnels MCP JSON-RPC messages through WebSocket and browser native messaging.
Amazon has launched Web Search on Amazon Bedrock, a built-in server-side tool that grounds foundation model responses in current web knowledge with zero data egress by default. The feature is enabled via a single parameter in the OpenAI Responses API and launches with OpenAI models on Bedrock's next-generation inference engine.
Amazon has added automated policy refinement to Automated Reasoning checks in Bedrock Guardrails, replacing manual hand-editing of formal logic with two new refinement modes. Every proposed change still requires human approval before it takes effect.