Amazon Bedrock
AI overview
Sign in and the AI will write an overview from our coverage.
Headlines · 71
- AWS Explores Prompt Caching Patterns for AI Agents on Bedrock
The AWS Machine Learning Blog explains how Amazon Bedrock prompt caching can reuse previously processed context, including instructions, tool definitions, and conversation history, instead of resending the full context on every agent step. The guide covers implicit and explicit cache breakpoints, stable prefixes, additional tools, cache eligibility, and write costs. In one six-turn workload, AWS reported about 62% lower input cost with implicit caching and about 61% with explicit rolling breakpoints on GPT-6 Astra, while cautioning that results vary by workflow.
AWS Machine Learning Blog · 🔥 0 - Build agentic retrieval on managed Amazon Bedrock with CDK
The AWS Machine Learning Blog presents a tutorial for building agentic retrieval on a Managed Amazon Bedrock Knowledge Base with the AWS Cloud Development Kit. It combines multi-knowledge-base routing, a reasoning agent hosted in Amazon Bedrock AgentCore, MCP tools, cited retrieval, seven observability layers, and evaluation, with a CDK application that provisions four dependent stacks. AWS says the reasoning agent can choose whether to retrieve, which knowledge base to consult, and whether to retrieve again before answering.
AWS Machine Learning Blog · 🔥 0 - Experiential offers an open-source gateway for agent model routing
Experiential Labs describes Experiential as an open-source gateway and router for agent workflows. Its README says the gateway provides one OpenAI-compatible API for hosted, bring-your-own-key and local models, with controls over model access and spending by user, agent and use case. The project also says users can turn production traffic into custom routers or specialized models, and offers hosted and local gateway options. These capabilities are described by the project and were not independently verified.
GitHub Trending · Python · 🔥 0 - AWS Capacity Mostly Booked Through 2027, With 2028 Commitments
Amazon CEO Andy Jassy said AWS capacity for 2026 is sold out and 2027 is largely sold out, while a good portion of 2028 capacity is already committed. The Information reports that AWS still reserves capacity for on-demand computing, inference services, Bedrock and EC2, so the statements mainly concern large capacity bookings rather than every available resource. Jassy attributed the strong bookings to continuing demand from AI laboratories and enterprise customers.
The Information · 🔥 0 - Codex CLI 0.164.0 adds presets, inline controls, and enterprise MCP authentication
According to the release notes, Codex CLI 0.164.0 adds ten numbered /presets slots for reusable prompts and slash commands, inline /model and /permissions arguments, and fullscreen image previews on terminals supporting Kitty or Sixel graphics. It also documents enterprise MCP authentication options, credential masking for supported remote Bash commands and Zsh snapshot sessions, and an Amazon Bedrock setup wizard enabled by default. Bug fixes address compaction failures, session resumption, Windows proxy authentication, configuration overrides, queued prompts, and macOS sandbox checks.
OpenAI Codex CLI Releases · 🔥 0 - Rescale built an AI test-triage agent with AWS AI-DLC in five days
Rescale used AWS's AI-Driven Development Lifecycle (AI-DLC) framework to build an intelligent triage agent that classifies automated end-to-end test failures and routes them to the right team, according to an AWS Machine Learning Blog post. The agent was built with the Strands SDK, containerized on Amazon EKS inside Rescale's existing Argo Workflows pipeline, and retrieves log evidence through MCP, after the team moved log retrieval from a third-party service to Amazon CloudWatch. AWS says Rescale went from problem definition to staging deployment in five days and to production within weeks; the post also says humans define scope, validate work and approve production changes while AI proposes and executes.
AWS Machine Learning Blog · 🔥 0 - AWS executive says physical AI scaling hinges on data, governance and cost
Amazon Web Services automotive and manufacturing global managing director Ozgur Tohumcu told TMTPost and Zhidx that scaling physical AI often depends less on model capability than on data foundations, governance, organizational readiness and deployment economics. He said many automakers’ AI projects remain at the proof-of-concept stage, while AWS supports physical AI through foundation models, simulation and synthetic data, model distillation and optimization, edge deployment, and hardware and physical platforms. Amazon also said its operations network includes more than one million robots.
智东西 · 🔥 0 - AWS details Deep Insight, an open-source multi-agent data analysis system
The AWS Solutions Architecture team published the first post in a three-part series describing Deep Insight, a production multi-agent system that takes a CSV file and a natural-language prompt and produces a professional .docx report with citations. The system runs a hierarchy of specialized agents — Coordinator, Planner, Supervisor, Coder, Validator, Reporter and Tracker — built on the Strands Agents SDK, Amazon Bedrock, Amazon Bedrock AgentCore, an Application Load Balancer and AWS Fargate, with Claude models assigned by role (Haiku, Opus and Sonnet). The authors say Deep Insight is open source and that a human-in-the-loop Plan Reviewer, which auto-approves after a 300-second countdown in the web version, addresses the problem that agents make context-based judgments rather than following fixed instructions. All performance and adoption claims come from the vendor authors and were not independently measured.
AWS Machine Learning Blog · 🔥 0 - AWS details AAIF, an agent framework routing routine tasks to local small models
An AWS Machine Learning Blog post walks through the Adaptive Agentic Intelligence Framework (AAIF), built with Strands Agents, which uses a 1B-parameter llama3.2 orchestrator running locally through Ollama to classify incoming requests. Routine tasks such as device telemetry retrieval and camera-feed analysis stay on local small models, while complex analysis is sent to cloud frontier models through Amazon Bedrock. The post says the pattern builds on a research position from Belcak et al. at NVIDIA arguing small language models are sufficiently powerful and more economical for many agentic invocations, and uses an IoT monitoring scenario as its reference implementation.
AWS Machine Learning Blog · 🔥 0 - Claude Code v2.1.305 fixes provider, sandbox, and workflow issues
Claude Code v2.1.305 adds configurable Linux nested user namespaces and a retry-watchdog usage-limit recheck interval. It also retries requests without tool search when Vertex, Bedrock, or another gateway rejects it, alongside fixes for model overrides, worktrees, MCP servers, workflow resumes, cloud sessions, self-hosted runners, and Code Review.
Claude Code Releases · 🔥 0 - Octave builds multi-tenant AI foundation for Reliance on Amazon Bedrock
An AWS Machine Learning Blog post describes how Octave (formerly Hexagon SIG) built a secure multi-tenant AI foundation for its Reliance quality management platform on Amazon Bedrock, using Cohere Embed v4 for multilingual and multimodal search and Amazon Bedrock AgentCore to run each user session in a dedicated, sanitized microVM. Octave says the foundation embedded 2 billion documents and that its first feature, a Complaint Triage Assistant, has run in production for three months. By Octave's own accounting, the shared layers cut deployment time per use case by 50 percent, while a Cohere social post repeats claims of premium accuracy and lower vector storage costs without independent measurement.
AWS Machine Learning Blog · 🔥 0 - Amazon Bedrock brings OpenAI GPT models to Canada
AWS says Amazon Bedrock cross-Region inference now makes GPT-5.6 Sol, Terra and Luna, GPT-6 Astra, Sol and Luna, and GPT-6.1 Sol available from Canada Central and Canada West (Calgary). Applications call the local Bedrock Runtime endpoint, while requests are routed to supported destination regions for inference; the models are accessible through the OpenAI Responses, Chat Completions and Bedrock Converse APIs. AWS says North American inference and data-residency controls are applied, while flagged content may be retained in the destination region for up to 30 days.
AWS Machine Learning Blog · 🔥 0 - AWS and Keyfactor Detail an X.509 PKI Architecture for AI Agent Identity
AWS Machine Learning Blog presents a reference architecture that combines Keyfactor EJBCA with AWS services to authenticate AI agents, verify user delegation and enforce revocation across MCP tool calls. Its example uses Amazon Bedrock, the AWS Strands Agents SDK and FastMCP, with signed request envelopes, RFC 8693 audience-scoped tokens, OCSP checks and identity cross-validation. The post says it also provides complete example source code.
AWS Machine Learning Blog · 🔥 0 - Amazon Bedrock adds structured outputs for Claude models
Amazon Bedrock now supports structured outputs for all available Anthropic Claude models through its bedrock-runtime and bedrock-mantle endpoints. The feature uses constrained decoding to enforce JSON schemas during generation and adds strict schema validation for tool parameters, reducing custom parsing and retry logic for production workflows.
AWS Machine Learning Blog · 🔥 0 - TwelveLabs Pegasus 1.5 available on Amazon Bedrock
An AWS Machine Learning Blog post says TwelveLabs' Pegasus 1.5 is available on Amazon Bedrock in the US West (Oregon) Region, and that availability was announced on Oct 9, 2026. According to AWS, the video language model turns long-form video into structured, timestamped metadata: users describe the segments they care about and the model returns every match as JSON. AWS says it adds video segmentation, multimodal prompting with reference images and on-the-fly processing with no pre-indexing. A single request can analyze up to two hours of video, up from one hour in Pegasus 1.2, and the model is billed through AWS Marketplace under TwelveLabs rather than Amazon Bedrock. The supplied text does not include independent benchmarks.
AWS Machine Learning Blog · 🔥 0 - Anthropic opens Claude Opus 5.5 Fast Mode to all developers, claiming 2.5x output speed
Anthropic has ended the research preview of Claude Opus 5.5's Fast Mode and removed the waitlist, opening it to all developers, according to 36Kr and AIbase. The reports say Fast Mode keeps the same model weights and reasoning capability as the standard version and instead optimizes API and inference configuration to raise output speed up to 2.5x — a vendor-stated figure with no independent measurement supplied. Developers enable it with a speed: "fast" API parameter or the /fast toggle in Claude Code; it currently covers Opus 5.5, Opus 5 and Opus 4.8 but not Sonnet or Haiku, and is available on the API and Microsoft Azure Foundry, with Google Cloud coming and AWS Bedrock unsupported for now. 36Kr also reports lower pricing — $8 input / $40 output per million tokens for Opus 5.5 Fast Mode versus $10/$50 for Opus 5 and Opus 4.8 Fast Mode — plus separate rate limits, no prompt-cache sharing with standard mode, automatic fallback to standard speed at the cap, and billing against a separate usage allowance for subscribers.
36氪 人工智能 · 🔥 0 - AWS launches Agent Toolkit with MCP servers and plugins for coding agents
AWS published the Agent Toolkit for AWS on GitHub, an officially supported set of MCP servers, skills and plugins meant to help AI coding agents build, deploy and manage applications on AWS. The toolkit can be configured from the terminal through the AWS CLI, and has separate install paths for Claude Code, Codex, Cursor, Kiro and fx; the Claude Code plugins are listed on Anthropic's official plugin marketplace. Its AWS MCP Server is described as covering 300-plus AWS services through one authenticated endpoint, with sandboxed script execution, real-time documentation search, and enterprise controls including CloudWatch metrics, IAM condition keys and CloudTrail audit logging. Those capability descriptions come from the project README and are AWS's own account.
GitHub Trending · Python · 🔥 0 - Tamnoon's Tami agent automates cloud security fixes on Amazon Bedrock
In an AWS Machine Learning Blog post, cloud security remediation vendor Tamnoon described Tami, an agentic remediation orchestrator built on Amazon Bedrock that ingests findings from CNAPP, CSPM and other security tools, normalizes and prioritizes them with asset and exposure context, then assesses whether a fix is safe before generating and orchestrating it. The post says Tami uses defense-in-depth safeguards: no remediation is drafted until a deliberately cautious, scope-focused independent safety assessment clears it, investigation steps are validated as read-only, only the remediation path can change environments, every change carries backup, verification and rollback, and each generation step is paired with a reflection check. Tamnoon claims the approach delivered over 90 percent reduction in critical cloud exposure within 90 days with zero production issues and 13,000-plus engineer hours saved per week, figures the article attributes to Tamnoon's own research rather than independent measurement, alongside roles for Amazon Bedrock AgentCore and Bedrock Guardrails.
AWS Machine Learning Blog · 🔥 0 - Orca Security builds Discovery AI natural language security queries on Amazon Bedrock
An AWS Machine Learning Blog post describes Discovery AI, a natural-language query agent that Orca Security built with AWS on Amazon Bedrock to turn plain-language questions into filters for its Sonar query system. Sonar spans more than 900 cloud infrastructure and application models, 18 operators and nested parent-child relationships, which previously required users to hand-write JSON queries. Orca reports that compared with its initial prototype, which loaded the full schema into one prompt, input tokens per workload fell 93 percent from roughly 2 million to 140,000, cost fell 90 percent and end-to-end latency fell 75 percent from about 60 seconds to 15 seconds. The pipeline pairs retrieval-augmented example retrieval with schema-aware generation and splits models by stage: Anthropic Claude Haiku 4.5 for model selection and query generation, Amazon Nova 2 Lite for guardrails and validation, Amazon Titan for embeddings and Cohere Rerank 3.5 for reranking. Orca says Discovery AI has handled thousands of queries per day in production since March 2026.
AWS Machine Learning Blog · 🔥 0 - Grok 4.7 arrives on Amazon Bedrock, with AWS agent tests across reasoning levels
SpaceXAI's Grok 4.7 is now available on Amazon Bedrock with configurable reasoning effort, tool calling and structured output, according to the AWS Machine Learning Blog. SpaceXAI says the model uses a larger base model than Grok 4.6 and a longer reinforcement-learning run on a task mix weighted toward multi-hour problems, citing gains such as Terminal-Bench 4.0 rising from 20.3% to 37.6%, plus a 500K-token context window. AWS built a tool-calling agent on three search-requiring tasks with one verifiable answer each and ran it six times per effort level for 72 runs: 67 were correct, with all 18 xhigh runs correct and 15 of 18 at low effort, while mean output tokens were about 1,184 at low versus 9,147 at xhigh.
AWS Machine Learning Blog · 🔥 0 - Moonshot AI reported at $50B valuation as it moves toward a 2027 Hong Kong IPO
Citing people familiar with the matter, Bloomberg reported on October 6 that Moonshot AI has closed a final funding round at a valuation of about $50 billion and plans to list in Hong Kong in the first quarter of 2027, according to articles republished by 36Kr and TMTPost from Bohu Finance. That is about a month after Moonshot was reported to have filed a confidential A1 listing application with the Hong Kong Stock Exchange. The articles say K3, released in July, topped the Hugging Face trending list within 30 minutes, and that annualized recurring revenue rose from $100 million in March to $1 billion in August, with Bloomberg's sources pointing to $2 billion by year-end. They also list September commercialization moves, including the "Moon Landing" partner program, the full rollout of K2.8 Preview, K3 on Amazon Bedrock, and the release of Kimi Code Desktop and a financial-industry solution. The funding and IPO details rest on unnamed sources, have not been confirmed by the company, and contrast with founder Yang Zhilin's late-2025 internal letter saying a listing was not an immediate priority.
36氪 人工智能 · 🔥 0 - Amazon Bedrock adds global cross-Region inference for GPT-6 in Asia Pacific
AWS Machine Learning Blog published a tutorial on calling OpenAI's GPT-6 Sol and GPT-6 Luna through Amazon Bedrock global cross-Region inference from five Asia Pacific source Regions, plus GPT-6 Astra from Singapore. It says all three accept text and image input, client-side tool use and prompt caching, while differing in available reasoning-effort levels. The post also covers the Converse API, OpenAI-compatible APIs and coding clients, along with IAM and SCP permissions, quota management and CloudWatch/CloudTrail monitoring.
AWS Machine Learning Blog · 🔥 0 - GLM-5.3 joins Amazon Bedrock, showing two Chinese model go-to-market paths
An analysis published via 36Kr's Muhe Business Finance says Zhipu's GLM-5.3 went live on Amazon Bedrock during China's October National Day holiday under a usage-based revenue-share deal; Zhipu's Hong Kong shares reportedly rose more than 7% that day, and Goldman Sachs upgraded the stock to buy with a HK$1,560 target, raising its end-2026 ARR estimate for Zhipu from $2.7bn to $3.2bn. The piece contrasts this with DeepSeek, which has been available on Bedrock since March 11, 2025 via Bedrock and Custom Model Import but is described as prioritising distribution and open weights over direct monetisation, a difference it ties to Zhipu's post-IPO revenue pressure versus DeepSeek's High-Flyer backing and its reported RMB 51bn first external round in June 2026.
36氪 人工智能 · 🔥 0 - Synopsys, Amazon sign multi-year custom chip IP deal worth over $1B
Synopsys said it has entered a multi-year strategic agreement with Amazon worth more than $1 billion, using Synopsys silicon IP and AI-driven engineering software to speed development of Amazon's custom chips and AWS infrastructure. The two will also optimize Synopsys software for Trainium and Graviton, while Synopsys engineering teams adopt Amazon EC2 and Amazon Bedrock to accelerate their own product development.
36氪快讯 · 🔥 0 - 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 - Postman details Agent Mode architecture on Amazon Bedrock
In an Amazon Machine Learning Blog post, Postman and AWS describe the production architecture behind Agent Mode, Postman's AI-native way to work across API testing, documentation, discovery and implementation. The post says the team expected model quality and prompt design to be the hardest problems, but deeper challenges came from integrating an agent into an 11-year-old product built around interface-driven assumptions. The described patterns include dynamically scoping tools per task, favoring schema-based reads over tool proliferation, building purpose-made context handlers per entity, and treating the context window as a scarce budget. Inference runs on Amazon Bedrock with cross-Region inference, multi-tier prompt caching and model-dependent data-retention settings. Agent Mode requires user approval before actions that change application state and uses Amazon Bedrock Guardrails to redact personally identifiable information. Postman says its production implementation is proprietary and not available as a public sample repository.
AWS Machine Learning Blog · 🔥 0 - AWS brings Amazon Bedrock AgentCore to China regions
Amazon Web Services said Amazon Bedrock AgentCore, its fully managed platform for deploying and operating AI agents, is now generally available in the China (Beijing) region operated by Sinnet and the China (Ningxia) region operated by NWCD. It ships with six capabilities: a serverless microVM-based Runtime with up to eight hours of runtime support, Gateway, Identity, Browser Tools, Code Interpreter and Observability. The report cites customers including Ericsson, Sony and Cox Automotive, which it says moved 17 enterprise agent solutions into production in under a year.
智东西 · 🔥 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 - Amazon cut 30,000 jobs in a year while betting $200B on AI infrastructure
A report republished with authorization by TMTPost says Amazon eliminated more than 30,000 corporate roles between October 2025 and October 2026 — roughly 10% of its 350,000 white-collar staff and the largest layoff in its 30-year history — with over 70% of the cuts at L5–L7 middle-management levels. In the same period, the article says, Amazon announced 2026 capital expenditure of about $200 billion, mostly for AI infrastructure, roughly 1.5x the prior year's $131 billion and nearly 37% above Wall Street expectations. It also cites an estimated $3 billion in annual savings from the first 14,000-person round (per Cybernews) and says Amazon raised its total Anthropic investment from $8 billion to $33 billion in April 2026, with future plans up to $65 billion, in exchange for Anthropic's commitment to spend more than $100 billion on AWS over the next decade.
钛媒体 · 🔥 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
Experience and discussion from the community
Share my Amazon Bedrock experienceAsk about Amazon Bedrock
Nobody has shared their experience with Amazon Bedrock yet.