Deploy conversational agents with Vonage and Amazon Nova Sonic

In this post, we explore how developers can integrate Amazon Nova Sonic with the Vonage communications service to build responsive, natural-sounding voice experiences in real time. By combining the Vonage Voice API with the low-latency and expressive speech capabilities of Amazon Nova Sonic, businesses can deploy AI voice agents that deliver more human-like interactions than traditional voice interfaces. These agents can be used as customer support, virtual assistants, and more.

LangSmith and LangGraph Platform are now available in AWS Marketplace

LangSmith and LangGraph Platform (self-hosted deployments) are now available in AWS Marketplace.

More advanced AI capabilities are coming to Search

For Google AI Pro and AI Ultra subscribers, AI Mode in Search now features the ability to use Gemini 2.5 Pro and do deeper research for you.

Open Deep Research

TL;DR Deep research has broken out as one of the most popular agent applications. OpenAI, Anthropic, Perplexity, and Google all have deep research products that produce comprehensive reports using various sources of context. There are also many open source implementations. We've built an open deep researcher that is simple

Enabling customers to deliver production-ready AI agents at scale

Today, I’m excited to share how we’re bringing this vision to life with new capabilities that address the fundamental aspects of building and deploying agents at scale. These innovations will help you move beyond experiments to production-ready agent systems that can be trusted with your most critical business processes.

Google France hosted a hackathon to tackle healthcare's biggest challenges

Doctors, developers and researchers gathered in Paris to prototype new medical solutions using Google’s AI models.

Seq vs Seq: the Ettin Suite of Paired Encoders and Decoders

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Amazon Bedrock Knowledge Bases now supports Amazon OpenSearch Service Managed Cluster as vector store

Amazon Bedrock Knowledge Bases has extended its vector store options by enabling support for Amazon OpenSearch Service managed clusters, further strengthening its capabilities as a fully managed Retrieval Augmented Generation (RAG) solution. This enhancement builds on the core functionality of Amazon Bedrock Knowledge Bases , which is designed to seamlessly connect foundation models (FMs) with internal data sources. This post provides a comprehensive, step-by-step guide on integrating an Amazon Bedrock knowledge base with an OpenSearch Service managed cluster as its vector store.

Monitor agents built on Amazon Bedrock with Datadog LLM Observability

We’re excited to announce a new integration between Datadog LLM Observability and Amazon Bedrock Agents that helps monitor agentic applications built on Amazon Bedrock. In this post, we'll explore how Datadog's LLM Observability provides the visibility and control needed to successfully monitor, operate, and debug production-grade agentic applications built on Amazon Bedrock Agents.

How PayU built a secure enterprise AI assistant using Amazon Bedrock

PayU offers a full-stack digital financial services system that serves the financial needs of merchants, banks, and consumers through technology. In this post, we explain how we equipped the PayU team with an enterprise AI solution and democratized AI access using Amazon Bedrock, without compromising on data residency requirements.

The next wave of AI for content creation includes digital twins

AI and digital twins transform CPG marketing with scalable, cost-effective, personalized content creation. Learn more.

Supercharge generative AI workflows with NVIDIA DGX Cloud on AWS and Amazon Bedrock Custom Model Import

This post is co-written with Andrew Liu, Chelsea Isaac, Zoey Zhang, and Charlie Huang from NVIDIA. DGX Cloud on Amazon Web Services (AWS) represents a significant leap forward in democratizing access to high-performance AI infrastructure. By combining NVIDIA GPU expertise with AWS scalable cloud services, organizations can accelerate their time-to-train, reduce operational complexity, and unlock […]

Accelerate generative AI inference with NVIDIA Dynamo and Amazon EKS

This post introduces NVIDIA Dynamo and explains how to set it up on Amazon EKS for automated scaling and streamlined Kubernetes operations. We provide a hands-on walkthrough, which uses the NVIDIA Dynamo blueprint on the AI on EKS GitHub repo by AWS Labs to provision the infrastructure, configure monitoring, and install the NVIDIA Dynamo operator.

Moonshot AI's Kimi K2 model is now supported in Vercel AI Gateway

You can now access Kimi K2 from Moonshot AI using Vercel's AI Gateway, with no Moonshot AI account required.

AWS doubles investment in AWS Generative AI Innovation Center, marking two years of customer success

In this post, AWS announces a $100 million additional investment in its AWS Generative AI Innovation Center, marking two years of successful customer collaborations across industries from financial services to healthcare. The investment comes as AI evolves toward more autonomous, agentic systems, with the center already helping thousands of customers drive millions in productivity gains and transform customer experiences.

A summer of security: empowering cyber defenders with AI

Here’s what we’re announcing at cybersecurity conferences like Black Hat USA and DEF CON 33.

Intellectual freedom by design

ChatGPT is designed to be useful, trustworthy, and adaptable so you can make it your own.

Build AI-driven policy creation for vehicle data collection and automation using Amazon Bedrock

Sonatus partnered with the AWS Generative AI Innovation Center to develop a natural language interface to generate data collection and automation policies using generative AI. This innovation aims to reduce the policy generation process from days to minutes while making it accessible to both engineers and non-experts alike. In this post, we explore how we built this system using Sonatus’s Collector AI and Amazon Bedrock. We discuss the background, challenges, and high-level solution architecture.

How Rapid7 automates vulnerability risk scores with ML pipelines using Amazon SageMaker AI

In this post, we share how Rapid7 implemented end-to-end automation for the training, validation, and deployment of ML models that predict CVSS vectors. Rapid7 customers have the information they need to accurately understand their risk and prioritize remediation measures.

Build secure RAG applications with AWS serverless data lakes

In this post, we explore how to build a secure RAG application using serverless data lake architecture, an important data strategy to support generative AI development. We use Amazon Web Services (AWS) services including Amazon S3, Amazon DynamoDB, AWS Lambda, and Amazon Bedrock Knowledge Bases to create a comprehensive solution supporting unstructured data assets which can be extended to structured data. The post covers how to implement fine-grained access controls for your enterprise data and design metadata-driven retrieval systems that respect security boundaries. These approaches will help you maximize the value of your organization's data while maintaining robust security and compliance.

Advanced fine-tuning methods on Amazon SageMaker AI

When fine-tuning ML models on AWS, you can choose the right tool for your specific needs. AWS provides a comprehensive suite of tools for data scientists, ML engineers, and business users to achieve their ML goals. AWS has built solutions to support various levels of ML sophistication, from simple SageMaker training jobs for FM fine-tuning to the power of SageMaker HyperPod for cutting-edge research. We invite you to explore these options, starting with what suits your current needs, and evolve your approach as those needs change.

Streamline machine learning workflows with SkyPilot on Amazon SageMaker HyperPod

This post is co-written with Zhanghao Wu, co-creator of SkyPilot. The rapid advancement of generative AI and foundation models (FMs) has significantly increased computational resource requirements for machine learning (ML) workloads. Modern ML pipelines require efficient systems for distributing workloads across accelerated compute resources, while making sure developer productivity remains high. Organizations need infrastructure solutions […]

Intelligent document processing at scale with generative AI and Amazon Bedrock Data Automation

This post presents an end-to-end IDP application powered by Amazon Bedrock Data Automation and other AWS services. It provides a reusable AWS infrastructure as code (IaC) that deploys an IDP pipeline and provides an intuitive UI for transforming documents into structured tables at scale. The application only requires the user to provide the input documents (such as contracts or emails) and a list of attributes to be extracted. It then performs IDP with generative AI.

Build a conversational data assistant, Part 2 – Embedding generative business intelligence with Amazon Q in QuickSight

In this post, we dive into how we integrated Amazon Q in QuickSight to transform natural language requests like “Show me how many items were returned in the US over the past 6 months” into meaningful data visualizations. We demonstrate how combining Amazon Bedrock Agents with Amazon Q in QuickSight creates a comprehensive data assistant that delivers both SQL code and visual insights through a single, intuitive conversational interface—democratizing data access across the enterprise.

Build a conversational data assistant, Part 1: Text-to-SQL with Amazon Bedrock Agents

In this post, we focus on building a Text-to-SQL solution with Amazon Bedrock, a managed service for building generative AI applications. Specifically, we demonstrate the capabilities of Amazon Bedrock Agents. Part 2 explains how we extended the solution to provide business insights using Amazon Q in QuickSight, a business intelligence assistant that answers questions with auto-generated visualizations.

Implement user-level access control for multi-tenant ML platforms on Amazon SageMaker AI

In this post, we discuss permission management strategies, focusing on attribute-based access control (ABAC) patterns that enable granular user access control while minimizing the proliferation of AWS Identity and Access Management (IAM) roles. We also share proven best practices that help organizations maintain security and compliance without sacrificing operational efficiency in their ML workflows.

Long-running execution flows now supported in Amazon Bedrock Flows in public preview

We announce the public preview of long-running execution (asynchronous) flow support within Amazon Bedrock Flows. With Amazon Bedrock Flows, you can link foundation models (FMs), Amazon Bedrock Prompt Management, Amazon Bedrock Agents, Amazon Bedrock Knowledge Bases, Amazon Bedrock Guardrails, and other AWS services together to build and scale predefined generative AI workflows.

Fraud detection empowered by federated learning with the Flower framework on Amazon SageMaker AI

In this post, we explore how SageMaker and federated learning help financial institutions build scalable, privacy-first fraud detection systems.

Building intelligent AI voice agents with Pipecat and Amazon Bedrock – Part 2

In Part 1 of this series, you learned how you can use the combination of Amazon Bedrock and Pipecat, an open source framework for voice and multimodal conversational AI agents to build applications with human-like conversational AI. You learned about common use cases of voice agents and the cascaded models approach, where you orchestrate several components to build your voice AI agent. In this post (Part 2), you explore how to use speech-to-speech foundation model, Amazon Nova Sonic, and the benefits of using a unified model.

Uphold ethical standards in fashion using multimodal toxicity detection with Amazon Bedrock Guardrails

In the fashion industry, teams are frequently innovating quickly, often utilizing AI. Sharing content, whether it be through videos, designs, or otherwise, can lead to content moderation challenges. There remains a risk (through intentional or unintentional actions) of inappropriate, offensive, or toxic content being produced and shared. In this post, we cover the use of the multimodal toxicity detection feature of Amazon Bedrock Guardrails to guard against toxic content. Whether you’re an enterprise giant in the fashion industry or an up-and-coming brand, you can use this solution to screen potentially harmful content before it impacts your brand’s reputation and ethical standards. For the purposes of this post, ethical standards refer to toxic, disrespectful, or harmful content and images that could be created by fashion designers.

The EU Code of Practice and future of AI in Europe

OpenAI joins the EU Code of Practice, advancing responsible AI while partnering with European governments to drive innovation, infrastructure, and economic growth.

New capabilities in Amazon SageMaker AI continue to transform how organizations develop AI models

In this post, we share some of the new innovations in SageMaker AI that can accelerate how you build and train AI models. These innovations include new observability capabilities in SageMaker HyperPod, the ability to deploy JumpStart models on HyperPod, remote connections to SageMaker AI from local development environments, and fully managed MLflow 3.0.

Accelerate foundation model development with one-click observability in Amazon SageMaker HyperPod

With a one-click installation of the Amazon Elastic Kubernetes Service (Amazon EKS) add-on for SageMaker HyperPod observability, you can consolidate health and performance data from NVIDIA DCGM, instance-level Kubernetes node exporters, Elastic Fabric Adapter (EFA), integrated file systems, Kubernetes APIs, Kueue, and SageMaker HyperPod task operators. In this post, we walk you through installing and using the unified dashboards of the out-of-the-box observability feature in SageMaker HyperPod. We cover the one-click installation from the Amazon SageMaker AI console, navigating the dashboard and metrics it consolidates, and advanced topics such as setting up custom alerts.

Accelerating generative AI development with fully managed MLflow 3.0 on Amazon SageMaker AI

In this post, we explore how Amazon SageMaker now offers fully managed support for MLflow 3.0, streamlining AI experimentation and accelerating your generative AI journey from idea to production. This release transforms managed MLflow from experiment tracking to providing end-to-end observability, reducing time-to-market for generative AI development.

Amazon SageMaker HyperPod launches model deployments to accelerate the generative AI model development lifecycle

In this post, we announce Amazon SageMaker HyperPod support for deploying foundation models from SageMaker JumpStart, as well as custom or fine-tuned models from Amazon S3 or Amazon FSx. This new capability allows customers to train, fine-tune, and deploy models on the same HyperPod compute resources, maximizing resource utilization across the entire model lifecycle.

Supercharge your AI workflows by connecting to SageMaker Studio from Visual Studio Code

AI developers and machine learning (ML) engineers can now use the capabilities of Amazon SageMaker Studio directly from their local Visual Studio Code (VS Code). With this capability, you can use your customized local VS Code setup, including AI-assisted development tools, custom extensions, and debugging tools while accessing compute resources and your data in SageMaker Studio. In this post, we show you how to remotely connect your local VS Code to SageMaker Studio development environments to use your customized development environment while accessing Amazon SageMaker AI compute resources.

Use K8sGPT and Amazon Bedrock for simplified Kubernetes cluster maintenance

This post demonstrates the best practices to run K8sGPT in AWS with Amazon Bedrock in two modes: K8sGPT CLI and K8sGPT Operator. It showcases how the solution can help SREs simplify Kubernetes cluster management through continuous monitoring and operational intelligence.

How Rocket streamlines the home buying experience with Amazon Bedrock Agents

Rocket AI Agent is more than a digital assistant. It’s a reimagined approach to client engagement, powered by agentic AI. By combining Amazon Bedrock Agents with Rocket’s proprietary data and backend systems, Rocket has created a smarter, more scalable, and more human experience available 24/7, without the wait. This post explores how Rocket brought that vision to life using Amazon Bedrock Agents, powering a new era of AI-driven support that is consistently available, deeply personalized, and built to take action.

Build an MCP application with Mistral models on AWS

This post demonstrates building an intelligent AI assistant using Mistral AI models on AWS and MCP, integrating real-time location services, time data, and contextual memory to handle complex multimodal queries. This use case, restaurant recommendations, serves as an example, but this extensible framework can be adapted for enterprise use cases by modifying MCP server configurations to connect with your specific data sources and business systems.

Build real-time conversational AI experiences using Amazon Nova Sonic and LiveKit

mazon Nova Sonic is now integrated with LiveKit’s WebRTC framework, a widely used platform that enables developers to build real-time audio, video, and data communication applications. This integration makes it possible for developers to build conversational voice interfaces without needing to manage complex audio pipelines or signaling protocols. In this post, we explain how this integration works, how it addresses the historical challenges of voice-first applications, and some initial steps to start using this solution.

The AI Cloud: A unified platform for AI workloads

We made it simple to build, preview, and ship any frontend, from marketing pages to dynamic apps, without managing infrastructure. Now we’re introducing the next layer: the Vercel AI Cloud.

What Is AI Sentiment Analysis and How to Build It with n8n?

Learn how to use AI sentiment analysis in n8n to intelligently automate workflows. Explore sentiment types, real-world use cases, and step-by-step guidance to build an agent-based system that classifies and explains email intent.

How to Build an Agent

Learn how to build an agent -- from choosing realistic task examples, to building the MVP to testing quality and safety, to deploying in production.

Building the Hugging Face MCP Server

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

AWS AI infrastructure with NVIDIA Blackwell: Two powerful compute solutions for the next frontier of AI

In this post, we announce general availability of Amazon EC2 P6e-GB200 UltraServers and P6-B200 instances, powered by NVIDIA Blackwell GPUs, designed for training and deploying the largest, most sophisticated AI models.

Unlock retail intelligence by transforming data into actionable insights using generative AI with Amazon Q Business

Amazon Q Business for Retail Intelligence is an AI-powered assistant designed to help retail businesses streamline operations, improve customer service, and enhance decision-making processes. This solution is specifically engineered to be scalable and adaptable to businesses of various sizes, helping them compete more effectively. In this post, we show how you can use Amazon Q Business for Retail Intelligence to transform your data into actionable insights.

MedGemma: Our most capable open models for health AI development

June 2025 (version 1.102)

Learn what is new in the Visual Studio Code June 2025 Release (1.102)

Democratize data for timely decisions with text-to-SQL at Parcel Perform

The business team in Parcel Perform often needs access to data to answer questions related to merchants’ parcel deliveries, such as “Did we see a spike in delivery delays last week? If so, in which transit facilities were this observed, and what was the primary cause of the issue?” Previously, the data team had to manually form the query and run it to fetch the data. With the new generative AI-powered text-to-SQL capability in Parcel Perform, the business team can self-serve their data needs by using an AI assistant interface. In this post, we discuss how Parcel Perform incorporated generative AI, data storage, and data access through AWS services to make timely decisions.

Query Amazon Aurora PostgreSQL using Amazon Bedrock Knowledge Bases structured data

In this post, we discuss how to make your Amazon Aurora PostgreSQL-Compatible Edition data available for natural language querying through Amazon Bedrock Knowledge Bases while maintaining data freshness.

Configure fine-grained access to Amazon Bedrock models using Amazon SageMaker Unified Studio

In this post, we demonstrate how to use SageMaker Unified Studio and AWS Identity and Access Management (IAM) to establish a robust permission framework for Amazon Bedrock models. We show how administrators can precisely manage which users and teams have access to specific models within a secure, collaborative environment. We guide you through creating granular permissions to control model access, with code examples for common enterprise governance scenarios.

Improve conversational AI response times for enterprise applications with the Amazon Bedrock streaming API and AWS AppSync

This post demonstrates how integrating an Amazon Bedrock streaming API with AWS AppSync subscriptions significantly enhances AI assistant responsiveness and user satisfaction. By implementing this streaming approach, the global financial services organization reduced initial response times for complex queries by approximately 75%—from 10 seconds to just 2–3 seconds—empowering users to view responses as they’re generated rather than waiting for complete answers.

Scale generative AI use cases, Part 1: Multi-tenant hub and spoke architecture using AWS Transit Gateway

n this two-part series, we discuss a hub and spoke architecture pattern for building a multi-tenant and multi-account architecture. This pattern supports abstractions for shared services across use cases and teams, helping create secure, scalable, and reliable generative AI systems. In Part 1, we present a centralized hub for generative AI service abstractions and tenant-specific spokes, using AWS Transit Gateway for cross-account interoperability.

Reasoning reimagined: Introducing Phi-4-mini-flash-reasoning

Unlock faster, efficient reasoning with Phi-4-mini-flash-reasoning—optimized for edge, mobile, and real-time applications.

Dive deeper with AI Mode and get gaming help in Circle to Search

We’re bringing new AI capabilities to Circle to Search, so you can dive deeper and ask follow-ups in AI Mode, and get gaming tips.

Inngest joins the Vercel Marketplace

Build background jobs and AI workflows with Inngest, now on the Vercel Marketplace. Native support for Next.js, preview environments, and branching.

How Lush and Google Cloud AI are reinventing retail checkout

Cosmetics company Lush is embracing Google Cloud AI to improve how they work.

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Upskill your LLMs with Gradio MCP Servers

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Creating custom kernels for the AMD MI300

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Mastra Changelog 2025-07-09

Mastra is now Apache-2.0 licensed, Playground goes multi-modal, new memory and RAG features, and more.

Accelerate AI development with Amazon Bedrock API keys

Today, we’re excited to announce a significant improvement to the developer experience of Amazon Bedrock: API keys. API keys provide quick access to the Amazon Bedrock APIs, streamlining the authentication process so that developers can focus on building rather than configuration.

Accelerating data science innovation: How Bayer Crop Science used AWS AI/ML services to build their next-generation MLOps service

In this post, we show how Bayer Crop Science manages large-scale data science operations by training models for their data analytics needs and maintaining high-quality code documentation to support developers. Through these solutions, Bayer Crop Science projects up to a 70% reduction in developer onboarding time and up to a 30% improvement in developer productivity.

Combat financial fraud with GraphRAG on Amazon Bedrock Knowledge Bases

In this post, we show how to use Amazon Bedrock Knowledge Bases GraphRAG with Amazon Neptune Analytics to build a financial fraud detection solution.

Classify call center conversations with Amazon Bedrock batch inference

In this post, we demonstrate how to build an end-to-end solution for text classification using the Amazon Bedrock batch inference capability with the Anthropic’s Claude Haiku model. We walk through classifying travel agency call center conversations into categories, showcasing how to generate synthetic training data, process large volumes of text data, and automate the entire workflow using AWS services.

Effective cross-lingual LLM evaluation with Amazon Bedrock

In this post, we demonstrate how to use the evaluation features of Amazon Bedrock to deliver reliable results across language barriers without the need for localized prompts or custom infrastructure. Through comprehensive testing and analysis, we share practical strategies to help reduce the cost and complexity of multilingual evaluation while maintaining high standards across global large language model (LLM) deployments.

Cohere Embed 4 multimodal embeddings model is now available on Amazon SageMaker JumpStart

The Cohere Embed 4 multimodal embeddings model is now generally available on Amazon SageMaker JumpStart. The Embed 4 model is built for multimodal business documents, has leading multilingual capabilities, and offers notable improvement over Embed 3 across key benchmarks. In this post, we discuss the benefits and capabilities of this new model. We also walk you through how to deploy and use the Embed 4 model using SageMaker JumpStart.

Meet the Builders: Highlights from the MCP Server Builder Meetup

Unlock microservices potential with Apollo GraphQL. Seamlessly integrate APIs, manage data, and enhance performance. Explore Apollo's innovative solutions.

Working with 400,000 teachers to shape the future of AI in schools

OpenAI joins the American Federation of Teachers to launch the National Academy for AI Instruction.

SmolLM3: smol, multilingual, long-context reasoner

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

How INRIX accelerates transportation planning with Amazon Bedrock

INRIX pioneered the use of GPS data from connected vehicles for transportation intelligence. In this post, we partnered with Amazon Web Services (AWS) customer INRIX to demonstrate how Amazon Bedrock can be used to determine the best countermeasures for specific city locations using rich transportation data and how such countermeasures can be automatically visualized in street view images. This approach allows for significant planning acceleration compared to traditional approaches using conceptual drawings.

Qwen3 family of reasoning models now available in Amazon Bedrock Marketplace and Amazon SageMaker JumpStart

Today, we are excited to announce that Qwen3, the latest generation of large language models (LLMs) in the Qwen family, is available through Amazon Bedrock Marketplace and Amazon SageMaker JumpStart. With this launch, you can deploy the Qwen3 models—available in 0.6B, 4B, 8B, and 32B parameter sizes—to build, experiment, and responsibly scale your generative AI applications on AWS. In this post, we demonstrate how to get started with Qwen3 on Amazon Bedrock Marketplace and SageMaker JumpStart.

Agents as escalators: Real-time AI video monitoring with Amazon Bedrock Agents and video streams

In this post, we show how to build a fully deployable solution that processes video streams using OpenCV, Amazon Bedrock for contextual scene understanding and automated responses through Amazon Bedrock Agents. This solution extends the capabilities demonstrated in Automate chatbot for document and data retrieval using Amazon Bedrock Agents and Knowledge Bases, which discussed using Amazon Bedrock Agents for document and data retrieval. In this post, we apply Amazon Bedrock Agents to real-time video analysis and event monitoring.

New AI tools for mental health research and treatment

This field guide and investment support AI’s potential in evidence-based mental health interventions and research.

Enabling Fully Sharded Data Parallel (FSDP2) in Opacus

Introducing Deep Research in Azure AI Foundry Agent Service

Announcing the public preview of Deep Research in Azure AI Foundry—an API and SDK-based offering of OpenAI’s advanced agentic research capability. Learn more.

Transforming network operations with AI: How Swisscom built a network assistant using Amazon Bedrock

In this post, we explore how Swisscom developed their Network Assistant. We discuss the initial challenges and how they implemented a solution that delivers measurable benefits. We examine the technical architecture, discuss key learnings, and look at future enhancements that can further transform network operations.

End-to-End model training and deployment with Amazon SageMaker Unified Studio

In this post, we guide you through the stages of customizing large language models (LLMs) with SageMaker Unified Studio and SageMaker AI, covering the end-to-end process starting from data discovery to fine-tuning FMs with SageMaker AI distributed training, tracking metrics using MLflow, and then deploying models using SageMaker AI inference for real-time inference. We also discuss best practices to choose the right instance size and share some debugging best practices while working with JupyterLab notebooks in SageMaker Unified Studio.

Mastra Changelog 2025-07-03

Agent Network (vNext), workflow cancellation, and custom memory model support highlight this week's Mastra updates.

Beyond Workflows: Introducing Agent Network (vNext)

Agent Network (vNext) introduces intelligent AI orchestration that automatically routes and executes complex multi-agent tasks without predetermined workflows.

Optimize RAG in production environments using Amazon SageMaker JumpStart and Amazon OpenSearch Service

In this post, we show how to use Amazon OpenSearch Service as a vector store to build an efficient RAG application.

Advancing AI agent governance with Boomi and AWS: A unified approach to observability and compliance

In this post, we share how Boomi partnered with AWS to help enterprises accelerate and scale AI adoption with confidence using Agent Control Tower.

Reducing Storage Footprint and Bandwidth Usage for Distributed Checkpoints with PyTorch DCP

The latest AI news we announced in June

Here are Google’s latest AI updates from June 2025

Context Engineering

TL;DR Agents need context to perform tasks. Context engineering is the art and science of filling the context window with just the right information at each step of an agent’s trajectory. In this post, we break down some common strategies — write, select, compress, and isolate — for context engineering

Use Amazon SageMaker Unified Studio to build complex AI workflows using Amazon Bedrock Flows

In this post, we demonstrate how you can use SageMaker Unified Studio to create complex AI workflows using Amazon Bedrock Flows.

Accelerating AI innovation: Scale MCP servers for enterprise workloads with Amazon Bedrock

In this post, we present a centralized Model Context Protocol (MCP) server implementation using Amazon Bedrock that provides shared access to tools and resources for enterprise AI workloads. The solution enables organizations to accelerate AI innovation by standardizing access to resources and tools through MCP, while maintaining security and governance through a centralized approach.

Choosing the right approach for generative AI-powered structured data retrieval

In this post, we explore five different patterns for implementing LLM-powered structured data query capabilities in AWS, including direct conversational interfaces, BI tool enhancements, and custom text-to-SQL solutions.

Revolutionizing drug data analysis using Amazon Bedrock multimodal RAG capabilities

In this post, we explore how Amazon Bedrock's multimodal RAG capabilities revolutionize drug data analysis by efficiently processing complex medical documentation containing text, images, graphs, and tables.

Building secure, scalable AI in the cloud with Microsoft Azure

Forrester Research shows how Azure helps enterprises scale generative AI securely, unlocking real business value. Learn more.

Changelist: June 2025

Windsurf updates from June 2025!

We used Veo to animate archive photography from the Harley-Davidson Museum

In Moving Archives, we’re bringing the iconic Harley-Davidson Museum archives to life with the help of Veo and Gemini.

No-code personal agents, powered by GPT-4.1 and Realtime API

And hit $36M ARR in just 45 days with a 20-person team.

How Exa built a Web Research Multi-Agent System with LangGraph and LangSmith

See how Exa used LangGraph and LangSmith to build a multi-agent web research system to process research queries

Training and Finetuning Sparse Embedding Models with Sentence Transformers v5

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Build and deploy AI inference workflows with new enhancements to the Amazon SageMaker Python SDK

In this post, we provide an overview of the user experience, detailing how to set up and deploy these workflows with multiple models using the SageMaker Python SDK. We walk through examples of building complex inference workflows, deploying them to SageMaker endpoints, and invoking them for real-time inference.

5 ways AI is supercharging research in financial services

Learn how Microsoft is enhancing research and analytics with AI for investment banks, asset management firms, and financial data and analytics providers.

Context extraction from image files in Amazon Q Business using LLMs

In this post, we look at a step-by-step implementation for using the custom document enrichment (CDE) feature within an Amazon Q Business application to process standalone image files. We walk you through an AWS Lambda function configured within CDE to process various image file types, and showcase an example scenario of how this integration enhances Amazon Q Business's ability to provide comprehensive insights.

Expanded access to Google Vids and no-cost AI tools in Classroom

Learn more about expanded access to Google Vids for all education users, and Gemini in Classroom, a new suite of no-cost AI tools available for educators.

AI in Australia—OpenAI’s Economic Blueprint

Today, OpenAI, in partnership with Mandala Partners, is sharing the OpenAI AI Economic Blueprint for Australia. At a time when boosting productivity has emerged as a national priority for Australia, the Blueprint provides a clear, actionable plan for how Australia can unlock the full economic and social potential of artificial intelligence.

Excited to announce that Mastra, the Typescript agent framework, is moving into beta

We officially switched over to vNext on May 6th, 2025

What a week at Mastra

5 Recommended MCP Servers for Cline

An LLM's power isn't just in the model itself, but in the tools it can access. While base models are powerful, they often hit limitations when faced with tasks requiring up-to-the-minute information, interaction with live websites, or deep, structured reasoning. MCP servers are dedicated tools that extend Cline’s capabilities, allowing it to overcome the inherent limitations of large language models. By connecting Cline to specialized servers for search, documentation, browser control, and more

Open Source AI Editor: First Milestone

We are open sourcing the GitHub Copilot Chat extension. It’s the first milestone in making VS Code an open source AI editor.

We're opening up Mastra Cloud

REGEN: Empowering personalized recommendations with natural language

AWS costs estimation using Amazon Q CLI and AWS Cost Analysis MCP

In this post, we explore how to use Amazon Q CLI with the AWS Cost Analysis MCP server to perform sophisticated cost analysis that follows AWS best practices. We discuss basic setup and advanced techniques, with detailed examples and step-by-step instructions.

Coding Agents 101: The Art of Actually Getting Things Done

The year is 2025. Coding agents aren't magic, but they're about the closest thing we have. We've noticed some engineers, in particular at the senior-to-staff level, finding success faster than others. Here we share some top lessons sourced from the experience of our customers and ourselves.

Mastra Changelog 2025-06-27

Mastra Cloud public beta, agent network chat, memory improvements, workflow updates, and a new Mastra 101 lesson.

Tailor responsible AI with new safeguard tiers in Amazon Bedrock Guardrails

In this post, we introduce the new safeguard tiers available in Amazon Bedrock Guardrails, explain their benefits and use cases, and provide guidance on how to implement and evaluate them in your AI applications.

How Microsoft 365 Copilot and agents help tackle the infinite workday

A new Work Trend Index special report reveals a new state of work: a seemingly infinite workday. Learn how to conquer the infinite workday.

We’re improving Ask Photos and bringing it to more Google Photos users.

We love seeing how you’re using Ask Photos in early access, like asking "suggest photos that'd make great phone backgrounds" or "what did I eat on my trip to Barcelona?"…

Structured data response with Amazon Bedrock: Prompt Engineering and Tool Use

We demonstrate two methods for generating structured responses with Amazon Bedrock: Prompt Engineering and Tool Use with the Converse API. Prompt Engineering is flexible, works with Bedrock models (including those without Tool Use support), and handles various schema types (e.g., Open API schemas), making it a great starting point. Tool Use offers greater reliability, consistent results, seamless API integration, and runtime validation of JSON schema for enhanced control.

Using Amazon SageMaker AI Random Cut Forest for NASA’s Blue Origin spacecraft sensor data

In this post, we demonstrate how to use SageMaker AI to apply the Random Cut Forest (RCF) algorithm to detect anomalies in spacecraft position, velocity, and quaternion orientation data from NASA and Blue Origin’s demonstration of lunar Deorbit, Descent, and Landing Sensors (BODDL-TP).

Vercel Ship 2025 recap

Vercel Ship 2025 added new building blocks for an AI era: Fast, flexible, and secure by default. Lower costs with Fluid's Active CPU pricing, Rolling Releases for safer deployments, invisible CAPTCHA with BotID. See these and more in our recap.

The Google for Startups Gemini kit is here

Learn more about how startups can use Gemini models and other AI resources from Google.

Customizable, no-code voice agent automation with GPT-4o

Windsurf and AHEAD Form Strategic AI DevOps Partnership

AHEAD is now offering a full suite of services around Windsurf

Cline v3.18: Gemini CLI Provider, Optimized Claude 4

Hello Cline community 🫡 Cline v3.18 is a focused release that introduces the Gemini CLI as a provider, delivers significant performance and reliability upgrades for the Claude 4 family, and ships several important core improvements. Gemini CLI Provider If you have the Gemini CLI tool installed and authenticated with your personal Google account, you can now leverage it directly within Cline. This gives you access to 1,000 free requests per day for the Gemini 2.5 Pro and Flash models, making

Gemma 3n fully available in the open-source ecosystem!

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Mastra Cloud Public Beta

Mastra Cloud is now in public beta — deploy, manage, and scale your AI agents and workflows.

Introducing AI Agent Monitoring

Sentry's agent monitoring brings tracing, tool visibility, model performance, and deep context into one unified experience — so you can quickly understand what broke, where, & why.

5 tips for getting started with Flow

Here are five tips for making videos with Flow, Google’s new AI filmmaking tool.

PyTorch + vLLM = ♥️

Build an intelligent multi-agent business expert using Amazon Bedrock

In this post, we demonstrate how to build a multi-agent system using multi-agent collaboration in Amazon Bedrock Agents to solve complex business questions in the biopharmaceutical industry. We show how specialized agents in research and development (R&D), legal, and finance domains can work together to provide comprehensive business insights by analyzing data from multiple sources.

FlagGems Joins the PyTorch Ecosystem: Triton-Powered Operator Library for Universal AI Acceleration

Driving cost-efficiency and speed in claims data processing with Amazon Nova Micro and Amazon Nova Lite

In this post, we shared how an internal technology team at Amazon evaluated Amazon Nova models, resulting in notable improvements in inference speed and cost-efficiency.

Presenting Flux Fast: Making Flux go brrr on H100s

From potholes to personalization: What Abu Dhabi is teaching us about AI-powered smart cities

Discover how city governments are transforming public service delivery with AI—enhancing personalization, empowering workers, and streamlining operations.

AlphaGenome: AI for better understanding the genome

Introducing a new, unifying DNA sequence model that advances regulatory variant-effect prediction and promises to shed new light on genome function — now available via API.

MUVERA: Making multi-vector retrieval as fast as single-vector search

Gemini CLI: your open-source AI agent

Free and open source, Gemini CLI brings Gemini directly into developers’ terminals — with unmatched access for individuals.

Empowering educators with AI innovation and insights

Learn about AI features for educators coming to Microsoft 365 Copilot and insights from the 2025 AI in Education Report from Microsoft.

AI Gateway is now in beta

AI Gateway is now in Beta, giving you a single endpoint to access a wide range of AI models across providers, with better uptime, faster responses, no lock-in.

Lower pricing with Active CPU pricing for Fluid compute

Pricing for Vercel Functions on Fluid compute has been reduced. All Fluid-based compute now uses an Active CPU pricing model, offering up to 90% savings in addition to the cost efficiency already delivered by Fluid's concurrency model.

Power Your LLM Training and Evaluation with the New SageMaker AI Generative AI Tools

Today we are excited to introduce the Text Ranking and Question and Answer UI templates to SageMaker AI customers. In this blog post, we’ll walk you through how to set up these templates in SageMaker to create high-quality datasets for training your large language models.

Amazon Bedrock Agents observability using Arize AI

Today, we’re excited to announce a new integration between Arize AI and Amazon Bedrock Agents that addresses one of the most significant challenges in AI development: observability. In this post, we demonstrate the Arize Phoenix system for tracing and evaluation.

How Captide agents running on LangGraph Platform compress investment research from days to seconds

See how Captide is using LangGraph Platform and LangSmith for their investment research and equity modeling agents.

Wichita Public Schools’ AI adoption: How it started, how it’s going

Wichita Public Schools' early use of AI in education shows how tools like Copilot can enhance learning and improve school efficiency.

How SkillShow automates youth sports video processing using Amazon Transcribe

SkillShow, a leader in youth sports video production, films over 300 events yearly in the youth sports industry, creating content for over 20,000 young athletes annually. This post describes how SkillShow used Amazon Transcribe and other Amazon Web Services (AWS) machine learning (ML) services to automate their video processing workflow, reducing editing time and costs while scaling their operations.

NewDay builds A Generative AI based Customer service Agent Assist with over 90% accuracy

This post is co-written with Sergio Zavota and Amy Perring from NewDay. NewDay has a clear and defining purpose: to help people move forward with credit. NewDay provides around 4 million customers access to credit responsibly and delivers exceptional customer experiences, powered by their in-house technology system. NewDay’s contact center handles 2.5 million calls annually, […]

From research to climate resilience

Gemini Robotics On-Device brings AI to local robotic devices

We’re introducing an efficient, on-device robotics model with general-purpose dexterity and fast task adaptation.

What’s New in GraphOS: Apollo Summer ’25 Release – AI-Ready API Orchestration with Enhanced MCP Server, Pricing Plans, and Performance Upgrades

Unlock microservices potential with Apollo GraphQL. Seamlessly integrate APIs, manage data, and enhance performance. Explore Apollo's innovative solutions.

Every Token Counts: Building Efficient AI Agents with GraphQL and Apollo MCP Server

Unlock microservices potential with Apollo GraphQL. Seamlessly integrate APIs, manage data, and enhance performance. Explore Apollo's innovative solutions.

How to Use Your Claude Max Subscription in Cline

If you're a Cline user with a Claude Max subscription, you can connect your account to save on token costs. Instead of paying per token via an API key, the Claude Code provider lets you leverage your existing subscription for all your development tasks in Cline. 0:00 /0:17 1× Setup 1. Install Claude Code: First, install the Claude Code CLI: npm install -g @anthropic-ai/claude-code (Anthropic's instructions) 2. Configure in Cline: * Navigate to 

Driving scalable growth with OpenAI o3, GPT-4.1, and CUA

By matching every OpenAI model to its best-fit task, Unify scales targeted outreach and generates 30% more pipeline.

AI Test Generation and PR Review in Sentry (Now in Open Beta)

Sentry’s new AI PR review and test generator help you ship code that breaks less. Try it - for free - today.

Unlocking rich genetic insights through multimodal AI with M-REGLE

No-code data preparation for time series forecasting using Amazon SageMaker Canvas

Amazon SageMaker Canvas offers no-code solutions that simplify data wrangling, making time series forecasting accessible to all users regardless of their technical background. In this post, we explore how SageMaker Canvas and SageMaker Data Wrangler provide no-code data preparation techniques that empower users of all backgrounds to prepare data and build time series forecasting models in a single interface with confidence.

Build an agentic multimodal AI assistant with Amazon Nova and Amazon Bedrock Data Automation

In this post, we demonstrate how agentic workflow patterns such as Retrieval Augmented Generation (RAG), multi-tool orchestration, and conditional routing with LangGraph enable end-to-end solutions that artificial intelligence and machine learning (AI/ML) developers and enterprise architects can adopt and extend. We walk through an example of a financial management AI assistant that can provide quantitative research and grounded financial advice by analyzing both the earnings call (audio) and the presentation slides (images), along with relevant financial data feeds.

Ask a techspert: What is inference?

Learn more about AI and inference from Google experts.

The rise of "context engineering"

Header image from Dex Horthy on Twitter. Context engineering is building dynamic systems to provide the right information and tools in the right format such that the LLM can plausibly accomplish the task. Most of the time when an agent is not performing reliably the underlying cause is that the

FYAI: How to leverage AI to reimagine cross-functional collaboration with Yina Arenas

Hear from Microsoft's Yina Arenas on the shifting AI landscape, why businesses get stuck on “proof of concept," and how Azure AI Foundry can help. Learn more.

Keith Messick joins Vercel as CMO

We’re welcoming Keith Messick as Chief Marketing Officer to support our growth, engage on more channels, and (as always) amplify the voice of the developer. Keith is a longtime enterprise CMO and comes to Vercel from database leader, Redis.

A colorful quantum future

Transformers backend integration in SGLang

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

AWS & Cline: 35 New MCP Servers to Manage Your Cloud with AI

We're excited to announce that Amazon Web Services has officially contributed 35 new Model Context Protocol (MCP) servers to the Cline ecosystem. This is a major milestone that extends the power of AI to nearly every corner of the AWS platform, allowing developers to manage their entire cloud infrastructure using natural language. For a long time, managing a complex cloud environment meant juggling dozens of consoles, dashboards, and configuration files. With these new MCP servers, that complex

Fault Tolerant Llama: training with 2000 synthetic failures every ~15 seconds and no checkpoints on Crusoe L40S

Build a scalable AI video generator using Amazon SageMaker AI and CogVideoX

In recent years, the rapid advancement of artificial intelligence and machine learning (AI/ML) technologies has revolutionized various aspects of digital content creation. One particularly exciting development is the emergence of video generation capabilities, which offer unprecedented opportunities for companies across diverse industries. This technology allows for the creation of short video clips that can be […]

Building trust in AI: The AWS approach to the EU AI Act

The EU AI Act establishes comprehensive regulations for AI development and deployment within the EU. AWS is committed to building trust in AI through various initiatives including being among the first signatories of the EU's AI Pact, providing AI Service Cards and guardrails, and offering educational resources while helping customers understand their responsibilities under the new regulatory framework.

Update on the AWS DeepRacer Student Portal

Starting July 14, 2025, the AWS DeepRacer Student Portal will enter a maintenance phase where new registrations will be disabled. Until September 15, 2025, existing users will retain full access to their content and training materials, with updates limited to critical security fixes, after which the portal will no longer be available.

Accelerate foundation model training and inference with Amazon SageMaker HyperPod and Amazon SageMaker Studio

In this post, we discuss how SageMaker HyperPod and SageMaker Studio can improve and speed up the development experience of data scientists by using IDEs and tooling of SageMaker Studio and the scalability and resiliency of SageMaker HyperPod with Amazon EKS. The solution simplifies the setup for the system administrator of the centralized system by using the governance and security capabilities offered by the AWS services.

6 inspiring, real-world AI activities for educators

Explore AI activities for educators using the Microsoft Education AI Toolkit. Access resources to get started with AI in education.

Introducing Microsoft 365 Copilot Tuning, multi-agent orchestration, and more from Microsoft Build 2025

Tune the latest AI models for your specific business needs and enable agents to work as a team in Microsoft Copilot Studio.

7 Best AI Agent Builders: An Expert Market Breakdown

Explore 7 top AI agent builders: workflow-native, AI-native & hybrid. Compare AI agent builder platforms by use case, integration & flexibility!

(LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardware

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

PyTorch Docathon 2025: Wrap Up

Meeting summarization and action item extraction with Amazon Nova

In this post, we present a benchmark of different understanding models from the Amazon Nova family available on Amazon Bedrock, to provide insights on how you can choose the best model for a meeting summarization task.

Building a custom text-to-SQL agent using Amazon Bedrock and Converse API

Developing robust text-to-SQL capabilities is a critical challenge in the field of natural language processing (NLP) and database management. The complexity of NLP and database management increases in this field, particularly while dealing with complex queries and database structures. In this post, we introduce a straightforward but powerful solution with accompanying code to text-to-SQL using a custom agent implementation along with Amazon Bedrock and Converse API.

Accelerate threat modeling with generative AI

In this post, we explore how generative AI can revolutionize threat modeling practices by automating vulnerability identification, generating comprehensive attack scenarios, and providing contextual mitigation strategies.

Search Live: Talk, listen and explore in real time with AI Mode

Search Live with voice facilitates back-and-forth conversations in AI Mode.

AI strategies from the frontlines of higher education

Explore the latest strategies from higher education institutions and how they’re creating AI-ready campuses with Microsoft AI solutions.

Hear a podcast discussion about Gemini’s coding capabilities.

The latest episode of the Google AI: Release Notes podcast focuses on how the Gemini team built one of the world’s leading AI coding models.Host Logan Kilpatrick chats w…

Toward understanding and preventing misalignment generalization

We study how training on incorrect responses can cause broader misalignment in language models and identify an internal feature driving this behavior—one that can be reversed with minimal fine-tuning.

Preparing for future AI risks in biology

As our models grow more capable in biology, we’re layering in safeguards and partnering with global experts, including hosting a biodefense summit this July.

What AI Companies Actually Need Right Now

At Cline, we've scaled to 500k+ users and raised significant funding from top-tier VCs. As Head of AI, I recently interviewed a strong ML engineer candidate. Despite their solid background, I voted "no hire." Let me explain why - it reveals a broader pattern about what AI companies actually need right now, and getting this wrong can be a $200k+ mistake. The $200k Mistake: Why Hiring MLEs Too Early Kills AI Startups Here's a pattern I see repeatedly in well-funded AI startups: 1. Raise a sub

The Local LLM Reality Check: What Actually Happens When You Try to Run AI Models on Your Computer

If you've used DeepSeek's R1 (or V3 for that matter), you've probably been impressed at its performance for the price. And if you've run into issues with its API recently, your next thought was probably, “Hey, I’ve got a decent computer—maybe I can run this locally and run this myself!” Then reality hits: the full DeepSeek R1 model needs about 1,342 GB of VRAM—no, that’s not a typo. It’s designed to run on a cluster of 16 NVIDIA A100 GPUs, each with 80GB of memory (source). Let’s break down wha

DeepSeek's Wild Week: A View from the Developer Trenches

Last week, Chinese AI startup, DeepSeek, caused the biggest single-day drop in NVIDIA's history, wiping nearly $600 billion from the chip giant's market value. But while Wall Street panicked about DeepSeek's cost claims, Cline users in our community were discovering a more nuanced reality. The Promise vs The Reality "R1 is so hesitant to open and read files while Claude just bulldozes through them," observed one of our users. This perfectly captures the gap between DeepSeek's impressive bench

Best AI Coding Assistant 2025: Complete Guide to Cline and Cursor

Updated March 4, 2025 article to reflect recent developments Remember when GitHub Copilot first launched and we thought AI-assisted coding couldn't get more revolutionary? Two years later, we're seeing a fascinating divergence in how AI coding assistants approach development. With recent releases from both Cline (now 3.5) and Cursor (0.46), we're witnessing not just a battle of features, but a philosophical split in how AI should partner with developers. I've watched both tools mature. Let's c

The Developer's Guide to MCP: From Basics to Advanced Workflows

Picture this: You're deep into development with your AI assistant, trying to juggle multiple tools – GitHub issues need updating, tests need running, and documentation needs reviewing. But instead of the seamless workflow you imagined, you're stuck with manual context switching and disconnected tools. Your AI assistant, brilliant as it is, feels trapped in its chat window. This is where the Model Context Protocol (MCP) changes everything. It's not just another developer tool – it's a fundamenta

Everyone's Talking About R1 vs o1 Benchmarks. But Here's What Really Matters.

In an interesting coincidence, DeepSeek released R1 on the same day we launched Plan & Act modes in Cline. And something fascinating started happening immediately: developers began naturally using R1 for planning phases and 3.5-Sonnet for implementation. Not because anyone suggested it – it just made sense. 0:00 /0:54 1× What's Actually Happening Here's what developers discovered works best: 1. Start new tasks in Plan mode using R1 ($0.55/M tokens)

Why AI Engineers Need Planning More Than Perfect Prompts

The best AI engineers I know follow a specific pattern. They don't obsess over prompt crafting – they obsess over planning. There's a reason for this, and it's not what most people think. The Reality Check Here's what typically happens when someone starts working with AI: 1. They throw requirements at the model 2. They get mediocre outputs 3. They blame their prompting skills 4. They spend hours "optimizing" prompts 5. They still get mediocre results Sound familiar? But here's what eli

DeepNVMe: Affordable I/O scaling for Deep Learning Applications

Gemini 2.5: Updates to our family of thinking models

Explore the latest Gemini 2.5 model updates with enhanced performance and accuracy: Gemini 2.5 Pro and Flash generally available and stable, and the new Flash-Lite in preview.

We’re expanding our Gemini 2.5 family of models

Gemini 2.5 Flash and Pro are now generally available, and we’re introducing 2.5 Flash-Lite, our most cost-efficient and fastest 2.5 model yet.

We’re expanding our Gemini 2.5 family of models

Gemini 2.5 Flash and Pro are now generally available, and we’re introducing 2.5 Flash-Lite, our most cost-efficient and fastest 2.5 model yet.

How Anomalo solves unstructured data quality issues to deliver trusted assets for AI with AWS

In this post, we explore how you can use Anomalo with Amazon Web Services (AWS) AI and machine learning (AI/ML) to profile, validate, and cleanse unstructured data collections to transform your data lake into a trusted source for production ready AI initiatives.

An innovative financial services leader finds the right AI solution: Robinhood and Amazon Nova

In this post, we share how Robinhood delivers democratized finance and real-time market insights using generative AI and Amazon Nova.

Build conversational interfaces for structured data using Amazon Bedrock Knowledge Bases

This post provides instructions to configure a structured data retrieval solution, with practical code examples and templates. It covers implementation samples and additional considerations, empowering you to quickly build and scale your conversational data interfaces.

Advancing healthcare AI innovation for global impact at HLTH Europe 2025

At HLTH Europe 2025, Microsoft will showcase our commitment to move forward the next frontier of health AI innovation. Learn more.

MCP will be the death of low-code automation, and other spooky stories

Explore the state and future of MCP in AI agents—from vendor security and model risks to cost and orchestration. MCP shows promise but faces adoption hurdles due to immaturity, security flaws, and backward compatibility challenges.

AI in sales: Applying historical lessons to modern challenges

See the latest AI sales transformation offering from Microsoft and agents to help sales teams nurture and close deals.

4 ways Microsoft Copilot empowers financial services employees

In the rapidly evolving landscape of financial services, staying ahead of the curve with technological innovation is not simply an advantage—it's a necessity.

How and when to build multi-agent systems

Late last week two great blog posts were released with seemingly opposite titles. “Don’t Build Multi-Agents” by the Cognition team, and “How we built our multi-agent research system” by the Anthropic team. Despite their opposing titles, I would argue they actually have a lot in common and contain some

Groq on Hugging Face Inference Providers 🔥

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Why PLAID Japan builds agents on their Google Cloud infrastructure with Mastra

How PLAID Japan migrated from GUI-based AI tools to Mastra for better collaboration and productivity for their engineering team building on Google Cloud.

The Last AI Coding Agent

It feels like every month there's a new "must-have" AI coding tool. The FOMO is real; but so is the fatigue of constantly switching, learning new workflows, and migrating settings. It’s exhausting, but that's the price for developers who want to be armed with the greatest leverage powered by AI. The magic of AI coding isn't just in the tool itself; it's in the power of the underlying model. And the "best" model is a moving target. One year ago, GPT-4o led the way. Then Anthropic's Claude 3.5 So

ParetoQ: Scaling Laws in Extremely Low-bit LLM Quantization