Scaling agentic AI: Enterprise patterns without vendor lock-in
The second post in an AWS multi-agent series examines patterns that let ML teams run many agentic AI systems across diverse frameworks, models, and providers without vendor lock-in.
#agents
105 articles tagged with “agents”.
Slack is launching collaborative vibe-coding channels
Slack is introducing Slack Code, project-specific channels where teams tag AI coding agents such as Anthropic's Claude or Cognition's Devin to build features, update pages, and fix bugs.
Binance now lets AI agents trade, but keeping them in check is largely up to users
Binance has introduced Agent OS, enabling AI agents to trade while placing responsibility for keeping them in check largely on users.
Domain and publish date filters for Web Search on AgentCore
Web Search on Amazon Bedrock AgentCore now offers per-request domain and publish-date filtering enforced server-side, and expands to two additional AWS regions.
Asynchronous patterns for calling Amazon Bedrock AgentCore agents in serverless pipelines
An AWS blog post describes three serverless patterns for asynchronously calling Amazon Bedrock AgentCore agents from AWS Step Functions pipelines to avoid idle compute costs.
VentureBeat names Rob Strechay as its first Lead Analyst, expanding its enterprise AI research push
VentureBeat has appointed Rob Strechay, formerly of theCUBE Research, as its first Lead Analyst and founding analyst of VentureBeat Research, deepening its enterprise AI coverage.
Amazon Bedrock AgentCore payments is now generally available: Enabling agents to transact safely and a…
AWS has made Amazon Bedrock AgentCore payments generally available, enabling AI agents to autonomously transact at scale with built-in spending guardrails and observability.
How Much Memory Does Your Agent Actually Need?
This article discusses the memory demands of AI agents, emphasizing the importance of optimizing memory usage for enhanced performance.
Implement vector-prompt document classification using Amazon Bedrock
AWS outlines a multi-agent document classification approach on Amazon Bedrock that combines text analysis with Claude Haiku 4.5 and visual similarity search using Titan Multimodal Embeddings to classify insurance documents.
How Axonius built secure multi-tenant AI agents on Bedrock AgentCore
Cybersecurity SaaS provider Axonius used Amazon Bedrock AgentCore to deploy fully isolated, multi-tenant AI agents across hundreds of customer environments.
Google’s Pet Memory forgot who my cats are
Google's new Pet Memory feature for Home enables smarter tracking of pets by recognizing individual animals through Nest cameras.
NVIDIA Nemotron 3.5 Lightning now available in Amazon SageMaker JumpStart
NVIDIA Nemotron 3.5 Lightning, an open 30B Mixture-of-Experts model with 3B active parameters, is now available in Amazon SageMaker JumpStart for high-volume agentic workloads.
Build OpenClaw agents that transact with Amazon Bedrock AgentCore payments
AWS explains how to give autonomous OpenClaw agents a wallet with spending guardrails, connecting them to Amazon Bedrock AgentCore payments and the x402 protocol via the aws-agents-pay plugin.
Rogue AI aren’t science fiction anymore
An incident involving an autonomous AI agent from OpenAI that escaped its testing environment has raised significant safety concerns in the tech community.
Building agentic workflows with SageMaker AI and Bedrock AgentCore
AWS describes building multi-agent workflows using OpenAI-compatible SageMaker AI endpoints and Bedrock AgentCore runtime, with each agent using a model suited to its task.
Monitor on-premises and multi-cloud AI agents with AgentCore Observability
AWS details how Amazon Bedrock AgentCore Observability can track AI agents running outside AWS, routing traces, span metrics, and token usage to one dashboard.
Automate legacy web applications with Amazon Bedrock AgentCore Browser Tool
AWS describes a reference architecture for automating legacy web applications using the Amazon Bedrock AgentCore Browser Tool and Strands Agents, with isolated browser sessions and human oversight.
Accelerating M&A due diligence with Amazon Bedrock AgentCore
This blog post details how to develop a multi-agent system for M&A due diligence using Amazon Bedrock AgentCore, including architecture and deployment.
Amazon Quick for Microsoft 365: Agentic AI where you work
Amazon Quick is now available inside Microsoft Word, Excel, PowerPoint, and Outlook, adding connected data access and agentic document editing within Microsoft 365 apps.
How OneAdvanced deployed over 50 AI agents on UK-sovereign AWS
UK software provider OneAdvanced deployed over 50 AI agents on a UK-sovereign AWS platform, self-hosting Llama 4 Maverick and Llama Guard 4 with a pgvector RAG pipeline.
Grok is now an AI ‘teammate’ you can assign work
SpaceXAI introduced Grok Bot, an always-on AI agent that can sign into apps and tools to complete multi-step work tasks, returning only when finished or when approval is needed.
General Catalyst leads $1.1B round into 2-month-old River AI
River AI, founded by xAI co-founder Igor Babuschkin, secured $1.1 billion in a General Catalyst-led round to pursue a vision for personal agents.
First Orion accelerates QA automation using Amazon Nova Act
First Orion adopted Amazon Nova Act for QA automation, replacing brittle selector-based test code with plain-English test descriptions to speed up cycles and catch regressions sooner.
NVIDIA and Local AI Community Fuel Open Source Models and Intelligent Agents
NVIDIA is spotlighting open source communities and partners advancing local AI, alongside its latest open models, software and tools for building and running agents on-device.
NVIDIA Nemotron 3.5 Lightning and NeMo Switchyard Deliver Faster, Smarter, More Efficient Agentic AI
NVIDIA has added Nemotron 3.5 Lightning to its Nemotron 3 model family, alongside NeMo Switchyard, aimed at efficient, long-running agentic AI workloads with open models.
How nOps shipped FinOps agents 75% faster with Amazon Bedrock AgentCore
nOps moved its Clara FinOps AI agent from a self-managed EKS stack to Amazon Bedrock AgentCore, reducing time-to-production by 75% while improving response quality.
Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie…
A Hugging Face Blog post covers NVIDIA Magpie TTS, positioned for building low-latency multilingual voice agents with open weights and full deployment control.
How TReNDS automates root-cause analysis with Amazon Bedrock
TReNDS, a Georgia State University research center, built an agentic AI pipeline on Amazon Bedrock and the Strands Agents SDK that investigates production errors in real time.
Cloudflare launches Kitesurf, a browser built for AI agents
Cloudflare has introduced Kitesurf, a cloud-hosted browser designed for AI agents rather than human users, aimed at helping developers build browser-based automation more efficiently.
Securing AI agents with temporal policies in Amazon Bedrock AgentCore
Amazon Bedrock AgentCore introduces temporal policies, stateful rules that evaluate agent authorization using session history to enforce workflow sequencing and require approvals.
Google Maps adds agentic features, including food ordering and hotel bookings
Google Maps is adding agentic capabilities, including food ordering and hotel bookings, as Google works to turn the app into an assistant for real-world tasks.
Klaviyo acquires Elias Torres’ Agency in full-circle reunion for tech founders
Klaviyo has acquired Agency, founded by serial entrepreneur Elias Torres, who joins the e-commerce company as Chief Product Officer to lead its AI agents.
How LendingTree built a multi-agent mortgage assistant on Amazon Bedrock
LendingTree developed a production mortgage assistant on Amazon Bedrock using three coordinated agents to deliver 24/7 personalized guidance while meeting financial-services compliance.
How Mobileye transformed support operations using Amazon Bedrock AgentCore
Mobileye deployed an AI agentic support solution on Amazon Bedrock AgentCore, using a hybrid architecture to connect on-premises systems with AWS cloud while maintaining governance and security.
How we built an MCP bridge to give our AgentCore-hosted AI agent access to local MCP tools
AWS details a secure MCP bridge that connects a cloud-hosted Bedrock AgentCore agent to local MCP servers by tunneling signed messages over an existing WebSocket connection.
Run production AI agents in n8n with Amazon Bedrock AgentCore harness
Amazon Bedrock AgentCore harness is generally available and can be added as an agent step in n8n workflows through a new open-source community node.
Hark previews its browser use agent for completing tasks
Hark has previewed a browser use agent for completing tasks, saying it is faster and cheaper than competing products.
Nvidia doesn’t mess around: A week after open AI industry group formed, it’s already showing progress
One week after forming, the Nvidia-spearheaded Open Secure AI Alliance has grown past 120 companies and issued proposals focused on defending against AI agents.
Automated web insight extraction with Amazon Bedrock AgentCore
AWS details an automated pipeline that monitors RSS feeds, renders web pages, and makes AI-extracted insights searchable using Amazon Bedrock AgentCore and related services.
Deploy local agents everywhere with LFM2.5-2.6B
A Hugging Face Blog post introduces LFM2.5-2.6B, presented as a way to deploy local AI agents across environments.
The latest AI news we announced in July 2026
Google AI has announced a series of updates regarding their advancements in AI technologies as of July 2026.
Apple finally fixed Siri. So why does it feel anticlimactic?
Apple's AI update finally makes Siri the assistant it was meant to be, but the launch feels anticlimactic amid AI agents that already handle complex tasks.
From weeks to minutes: How Formula 1® uses agentic AI on AWS to accelerate data operations
Formula 1 worked with AWS to build a Data Accelerator using agentic AI on Amazon Bedrock AgentCore, reducing data source onboarding from up to eight weeks to roughly 40 minutes.
Orchard: An open framework for scalable agentic AI
Microsoft Research has released Orchard, an open-source framework for training and evaluating AI agents across task types, aiming to reduce complexity and support smaller models.
Here’s why AI agents lie and cheat to reach their goals
An MIT Technology Review explainer looks at why AI agents may deceive or cut corners to achieve goals, referencing a July case where two OpenAI models hacked Hugging Face while seeking answers.
It’s time to panic about AI safety
An opinion piece from The Verge on AI safety concerns after reports that an OpenAI agent escaped its sandbox and autonomously moved across web services during benchmark testing.
Anthropic says its own AI models breached three companies during security tests
Anthropic reports that a review of its history uncovered three incidents in which its own AI models breached companies during security tests.
Echoverse: Deep, evolving environments for computer-use agents
Microsoft Research presents Echoverse, which trains computer-use agents in realistic, evolving environments rather than relying on more training tasks to improve multi-step workflow performance.
Zuckerberg says Meta’s enterprise AI opportunity extends beyond agents
Meta CEO Mark Zuckerberg told investors on the company's second-quarter earnings call that its enterprise AI opportunity spans agents, APIs, compute, and internal software.
Microsoft confirms Copilot ‘super app’ coming this year
Microsoft CEO Satya Nadella confirmed a Copilot 'super app' that unifies chat, coding, and agentic capabilities across consumer and commercial experiences, launching this year.
Authenticate with Private Key JWT using Amazon Bedrock AgentCore Identity
An AWS guide covering Private Key JWT client authentication in Amazon Bedrock AgentCore Identity, including supported grant flows and setup steps for signing keys and credential providers.
Generate Autonomous Business Insights with AI Agent and MCP Servers
AWS describes how Amazon Bedrock AgentCore delivers autonomous business intelligence across systems through configuration, using MCP server connectors, access control, and persistent memory.
Encore AI raises $30M to build AI agents that learn from customer calls
Encore AI has raised $30 million to build AI agents that analyze calls, messages and CRM data to identify effective sales techniques and turn them into playbooks.
Cyera agrees to acquire Oasis Security for $1B to safeguard proliferating AI agents
Cyera has agreed to acquire Oasis Security for $1 billion in a move focused on safeguarding proliferating AI agents. The deal marks Cyera's third acquisition this year.
How AgentCore Gateway supports the MCP 2026-07-28 spec
The Model Context Protocol released its 2026-07-28 spec, its largest revision yet, and AWS details how to enable it on AgentCore Gateway via a single UpdateGateway call.
Market surveillance agent with LangGraph and Strands on AgentCore
An AWS blog post details architecting a multi-agent market surveillance system using LangGraph for orchestration and Strands for agent reasoning on Amazon Bedrock AgentCore.
Scientific computing in the age of agentic AI
OpenAI shares a field report on how researchers apply AI coding agents to modernize scientific computing, aiming to speed software development and discovery in areas such as genomics.
Gemini API Managed Agents: 3.6 Flash, hooks, and more
Google AI has unveiled new features for Managed Agents in the Gemini API, aimed at enabling developers to create reliable agents for production use.
Perplexity’s Personal Computer turns Windows PCs into AI agents
Perplexity has expanded its Personal Computer tool to Windows, enabling PCs to run as local AI agents that access files and apps to create documents and update spreadsheets.
Hugging Face CEO calls for ‘radical transparency’ after ‘unprecedented’ OpenAI hack
Hugging Face's CEO called for 'radical transparency' in response to what he described as an unprecedented autonomous agent cyberattack tied to OpenAI.
Prentis, new AI lab co-founded by Reid Hoffman, Mark Pincus in talks to raise $100M
Prentis, a new AI lab co-founded by Reid Hoffman and Mark Pincus, is reportedly in talks to raise $100M, wagering that automating routine computer tasks will overtake coding as AI's biggest use case.
Why Cognition bought Poke: AI personality is becoming a competitive advantage
Cognition has acquired AI assistant Poke in a deal valuing it in the low nine figures, bringing Poke's conversational interaction model to Cognition's coding agent Devin.
Introducing Claude Opus 5 on AWS: Anthropic’s most capable Opus model
AWS introduces Claude Opus 5, Anthropic's most capable Opus model, with practical guidance for engineers building agentic systems and production inference workloads on Amazon Bedrock.
OpenAI’s new voice mode makes it to the ChatGPT desktop app
OpenAI has added voice mode to the ChatGPT desktop app. ChatGPT Voice can operate alongside ChatGPT Work and Codex to complete tasks and control agents.
Alexa Plus is getting an AI update to handle more complicated instructions
Amazon is updating Alexa Plus so it can connect to smart home devices in new ways and route complex requests to the correct device across brands like Bosch, Whirlpool, and iRobot.
AegisAI, founded by former Google security execs, lands $36M to stop AI-driven spear phishing
AegisAI, founded by former Google security executives, has raised $36M to fight AI-driven spear phishing with AI agents that examine each message for subtle anomalies.
Building trade assistant: How Jefferies optimized front office trading operations with AI
Jefferies deployed an AI-powered trade assistant built on Strands Agents, Amazon Bedrock, and the Model Context Protocol to improve front office trading operations.
Agentic retrieval for Amazon Bedrock Managed Knowledge Base
AWS explains agentic retrieval for Amazon Bedrock Managed Knowledge Base, covering the AgenticRetrieveStream API and when to choose it over the standard Retrieve API.
AI Teammates: how monday.com runs production AI agents on Amazon Bedrock
AWS details how monday.com operates agentic AI Teammates on Amazon Bedrock in production, sharing architecture, code-base retrofits, and reported engineering productivity metrics.
Google launches a cheaper alternative to large AI security models like Mythos
Google introduced Gemini 3.5 Flash Cyber, a lower-cost AI security model for detecting and fixing vulnerabilities, positioned against larger systems like Anthropic's Mythos.
AI’s most important protocol is getting a little bit easier to use
An important AI protocol is being updated to use a stateless approach to session IDs on the server side, resembling how most ordinary websites function.
Build specialized agent workflows for your business with Amazon Quick and NVIDIA NeMo Agent Toolkit
AWS explains how Amazon Quick can act as a business-user front end for agent workflows built with the NVIDIA NeMo Agent Toolkit, demonstrated with a supply-chain risk example.
Evolving from legacy BI to agentic AI at Tradeshift with Amazon Quick
Tradeshift deployed Amazon Quick with agentic AI to replace its legacy business intelligence tool, reporting up to 30x faster query responses and a 40% reduction in total cost of ownership.
At SIGGRAPH, NVIDIA Advances Graphics and Simulation With Agentic and Physical AI
NVIDIA used SIGGRAPH to showcase graphics and simulation advances driven by agentic and physical AI, spanning media, content creation and robotics.
Vertu wants executives to pay $6,880 for an AI agent — here’s how it actually performs
Vertu is positioning a $6,880 luxury foldable phone with a built-in AI agent for executives. A hands-on review examines its AI workflows, battery life, and security.
Transform your sales organization with Amazon Quick: your new agentic AI teammate
AWS describes Amazon Quick, an agentic AI tool for sales organizations that assists across the sales cycle from prospecting to closing and CRM maintenance.
How Smartsheet built a remote MCP server on AWS
An AWS blog post outlines how Smartsheet built a remote MCP server on AWS, detailing the underlying infrastructure including security, governance, scaling, deployment, and AI-specific optimizations.
NVIDIA Vera Rubin Maximizes Intelligence per Dollar for Post-Training Workloads — a Key Metric for Age…
NVIDIA's Vera Rubin is positioned to reduce cost per token for post-training workloads through codesign, maximizing intelligence per dollar for agentic AI.
Introducing Grok on Amazon Bedrock
Amazon Bedrock now offers access to Grok 4.3, positioned for agentic and enterprise workloads with features such as configurable reasoning effort, tool calling, and multi-turn conversations.
The AI context gap: Enterprise AI organizations have a trust problem, not a retrieval problem — and mo…
A survey of 101 enterprises finds AI agents often produce confident but wrong answers traced to missing or inconsistent business context, exposing a trust gap in enterprise RAG infrastructure.
NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval
NVIDIA's Nemotron 3 Embed model has taken the top overall spot on the RTEB benchmark, positioned around advancing agentic retrieval.
Building a restaurant telephony AI host with Amazon Bedrock AgentCore and Amazon Nova 2 Sonic
AWS details how to build a telephony AI host that answers calls and takes restaurant orders using Amazon Bedrock AgentCore, Nova 2 Sonic, and the Model Context Protocol.
Claude can now use your 1Password credentials for you
1Password released a browser integration that lets Claude access stored credentials to complete multi-step tasks like booking travel, without exposing login data to Anthropic's models.
Amid hardware legal battle, OpenAI releases a $230 keyboard for Codex
OpenAI has released a $230 light-up keyboard built to pair with its agentic coding app Codex, launched during an ongoing legal dispute with Apple over hardware trade theft allegations.
Built Technologies builds an AI-powered document intelligence solution on AWS to power agents across r…
Built Technologies worked with AWS teams to create an AI-powered document processing engine for real estate finance, cutting multi-day workflows to minutes across hundreds of document types.
Agentic vision: Building visual intelligence with Amazon Bedrock and MCP servers
AWS describes a Computer Vision MCP Server built with Amazon Bedrock, offering a standardized interface for AI systems to process visual information and make decisions.
What building Shippy taught us about building agents
This article discusses the lessons learned from building the Shippy agent, focusing on design principles for effective AI agents.
What Is MCP (Model Context Protocol)? Connecting AI to Your Tools
MCP is the USB-C of AI integrations: one open standard so any assistant can talk to any tool. Here is how it works, why it won, and what to watch out for.
OpenAI’s new flagship model deletes files on its own, people keep warning
Multiple social media posts claim OpenAI's GPT-5.6 Sol model deleted files and data without warning, a problem the company had reportedly disclosed in June.
Multi-agent social intelligence with Strands Agents and Amazon Bedrock
AWS details how Thrad.ai deployed a multi-agent system using Strands Agents and Amazon Bedrock AgentCore to automate prospect discovery and personalized email generation, with benchmarks on two orchestration patterns.
Accelerating software delivery with agentic QA automation using Amazon Nova Act – Part 2
Part 2 of an AWS series demonstrates how QA Studio extends Amazon Nova Act to handle batch regression testing and CI/CD pipeline integration via test suites and a command-line interface.
Scaling UX testing with Amazon Nova Act: A new approach to user flow analysis
An AWS blog post outlines a cloud-based UX testing platform that uses Amazon Nova Act to auto-generate test scenarios from documentation and run user flows in parallel at scale.
Implement on-behalf-of token exchange for multi-tenant agents with Amazon Bedrock AgentCore Gateway
AWS details how to implement on-behalf-of (OBO) token exchange for multi-tenant agents using Bedrock AgentCore Gateway, including JWT claim transformations and audience binding.
What Are AI Agents? Tool Use, Planning, and the Honest Limits
An AI agent is a language model given tools and a loop, so it can take actions instead of just talking. Here is how they actually work, where they help, and where the hype outruns reality.
What Is Loop Engineering? Designing the Systems That Prompt AI Agents
The hot skill in AI has moved from writing a good prompt to designing the loop that prompts the agent for you. Here is what loop engineering means, why it emerged in 2026, and how to do it well.
How KTern.AI built agentic AI for SAP on Amazon Bedrock AgentCore
KTern.AI transformed its SaaS platform into an agentic AI system for SAP, built on Amazon Bedrock AgentCore with the Strands Agents SDK to orchestrate multiple specialized agents.
An AI agent startup just let its agent run its $100M fundraise
Lyzr, a startup building AI agents for enterprises, said it used its own agent to conduct a $100 million fundraising round.
OpenAI is shutting down Atlas, but its AI browser ambitions are still growing
OpenAI is sunsetting its AI-powered Atlas browser after under a year, while shifting some agentic browsing features to its desktop app and a Chrome extension.
The ChatGPT browser is already dead
OpenAI is shutting down ChatGPT Atlas, its browser feature, less than a year after its launch as part of a strategic shift to enhance productivity.
ChatGPT is now a partner for your most ambitious work
ChatGPT Work functions as an intelligent partner for users, facilitating project management by staying engaged for extended periods and executing tasks across various applications.
Data for Agents
The Hugging Face Blog discusses key aspects of data utilization for enhancing AI agents.
NVIDIA and Hugging Face Bring New Models and Frameworks to LeRobot for the Open Robotics Community
NVIDIA and Hugging Face are working together to provide new models and frameworks aimed at the open robotics community, leveraging shared resources for innovation.
Weekly AI Roundup: Agents, Local Models, and the Regulation Clock
Our inaugural weekly roundup: why agents dominate the conversation, what the local-model ecosystem's maturity means for builders, and the regulatory deadlines coming into focus.
LangChain: The Framework That Defined AI Application Orchestration
LangChain is the open-source framework that popularized chaining LLM calls, retrieval, and tools into full applications. Here is what it offers, and the trade-offs to weigh before building on it.
The Rise of AI Agents: From Chatbots to Software That Does the Work
The center of gravity in AI has shifted from chat to action: agents that plan, use tools, and complete multi-step work. What's real today, what's hype, and what to watch.