Amazon Quick now integrates with Snowflake Cortex AI through the Model Context Protocol (MCP), enabling teams to query their Snowflake data and documents using natural language, and automate multi-step workflows directly within their Quick workspace. After setting up the connection using Snowflake’s managed MCP server with OAuth authentication, you can ask questions across structured data through Cortex Analyst and retrieve insights from unstructured documents through Cortex Search.
With this integration, you can build Flows in Quick that orchestrate Snowflake Cortex Agents to execute repeatable, governed workflows with consistent structured output. This is ideal for any multi-step process that spans structured data and unstructured documents. The same MCP connection is also accessible from Quick Chat and other Quick features. For example, users can ask ad-hoc follow-up questions or explore their Snowflake data conversationally alongside their automated flows. Quick intelligently routes relevant prompts to Snowflake Cortex AI and returns contextualized answers alongside enterprise knowledge stored in Quick Spaces, giving teams both the rigor of a structured process and the flexibility of a conversational interface.
The Snowflake Cortex AI integration with Amazon Quick is available in all AWS Regions where Amazon Quick is available.
Visit the Amazon Quick website to learn more and start your Quick free trial. To learn more about the Snowflake Cortex AI integration, read the blog. To learn more about Quick integrations, visit the integrations page.
Amazon Quick now integrates with Snowflake Cortex AI through the Model Context Protocol (MCP), enabling teams to query their Snowflake data and documents using natural language, and automate multi-step workflows directly within their Quick workspace. After setting up the connection using Snowflake’s managed MCP server with OAuth authentication, you can ask questions across structured data through Cortex Analyst and retrieve insights from unstructured documents through Cortex Search.
With this integration, you can build Flows in Quick that orchestrate Snowflake Cortex Agents to execute repeatable, governed workflows with consistent structured output. This is ideal for any multi-step process that spans structured data and unstructured documents. The same MCP connection is also accessible from Quick Chat and other Quick features. For example, users can ask ad-hoc follow-up questions or explore their Snowflake data conversationally alongside their automated flows. Quick intelligently routes relevant prompts to Snowflake Cortex AI and returns contextualized answers alongside enterprise knowledge stored in Quick Spaces, giving teams both the rigor of a structured process and the flexibility of a conversational interface.
The Snowflake Cortex AI integration with Amazon Quick is available in all AWS Regions where Amazon Quick is available.
Visit the Amazon Quick website to learn more and start your Quick free trial. To learn more about the Snowflake Cortex AI integration, read the blog. To learn more about Quick integrations, visit the integrations page.
Amazon CloudWatch Application Signals introduces service health ranking on the application map and new infrastructure, logs, and traces tabs on the service overview page. These capabilities let operators triage unhealthy services and inspect the underlying compute environment, log snippets, and trace details in one place, making it easier to find root causes without switching tools. Customers use Application Signals to monitor the health of distributed applications, but identifying why a service was unhealthy often required leaving CloudWatch to correlate infrastructure data across separate tools. The application map now ranks services by health and shows runtime indicators on service nodes for Amazon EKS, Amazon ECS, AWS Lambda, and Amazon EC2, along with a new infrastructure tab that surfaces the compute and runtime environment, its components, and curated default metrics with deep links to the relevant monitoring tools. In addition, the service overview page provides the infrastructure, logs, and traces tab, helping operators spot issues in context of their application. With health-ranked services on the application map and new infrastructure, logs, and traces tabs, operators can instantly identify their most degraded services and drill into the compute environment, error-producing log snippets, and slow or failing transactions — all without leaving Application Signals. These capabilities span workloads running on Amazon EKS, Amazon ECS, AWS Lambda, and Amazon EC2, giving teams a single pane to move from symptom to root cause in minutes instead of hours.
Amazon CloudWatch Application Signals introduces service health ranking on the application map and new infrastructure, logs, and traces tabs on the service overview page. These capabilities let operators triage unhealthy services and inspect the underlying compute environment, log snippets, and trace details in one place, making it easier to find root causes without switching tools. Customers use Application Signals to monitor the health of distributed applications, but identifying why a service was unhealthy often required leaving CloudWatch to correlate infrastructure data across separate tools. The application map now ranks services by health and shows runtime indicators on service nodes for Amazon EKS, Amazon ECS, AWS Lambda, and Amazon EC2, along with a new infrastructure tab that surfaces the compute and runtime environment, its components, and curated default metrics with deep links to the relevant monitoring tools. In addition, the service overview page provides the infrastructure, logs, and traces tab, helping operators spot issues in context of their application. With health-ranked services on the application map and new infrastructure, logs, and traces tabs, operators can instantly identify their most degraded services and drill into the compute environment, error-producing log snippets, and slow or failing transactions — all without leaving Application Signals. These capabilities span workloads running on Amazon EKS, Amazon ECS, AWS Lambda, and Amazon EC2, giving teams a single pane to move from symptom to root cause in minutes instead of hours. These capabilities are available in all AWS Regions where Amazon CloudWatch Application Signals is supported. To learn more about this feature, see the Amazon CloudWatch Application Signals documentation . For pricing details, see the Amazon CloudWatch pricing page
Amazon Aurora PostgreSQL-Compatible Edition now supports PostgreSQL major version 18, starting with version 18.3. This release brings community improvements to query performance and database management, and introduces support for pg_roaringbitmap, a new extension that performs fast, memory-efficient set operations on large collections of integers. This enables use cases such as audience segmentation, tag-based filtering, and permission checks directly in the database without application-layer processing.
PostgreSQL 18 introduces B-tree skip scans, which improve query performance, and reduce index storage and maintenance overhead. Major version upgrades now retain optimizer statistics, ensuring consistent query performance immediately after upgrading without waiting for statistics to be regenerated. Logical replication can now stream large transactions in parallel, reducing replication lag and keeping downstream systems more current. Please refer to the Amazon Aurora PostgreSQL release notes for details.
You can upgrade your database using several options including RDS Blue/Green deployments, upgrade in-place, or restoring a snapshot. Learn more about upgrading your database instances in the Amazon Aurora User Guide. Aurora PostgreSQL 18.3 is available in all commercial AWS Regions and AWS GovCloud (US) Regions.
Amazon Aurora is designed for unparalleled high performance and availability at global scale with full PostgreSQL and MySQL compatibility. It provides built-in security, continuous backups, serverless compute, up to 15 read replicas, automated multi-Region replication, and integrations with other AWS services. To get started with Amazon Aurora, take a look at our getting started page.
Amazon Aurora PostgreSQL-Compatible Edition now supports PostgreSQL major version 18, starting with version 18.3. This release brings community improvements to query performance and database management, and introduces support for pg_roaringbitmap, a new extension that performs fast, memory-efficient set operations on large collections of integers. This enables use cases such as audience segmentation, tag-based filtering, and permission checks directly in the database without application-layer processing. PostgreSQL 18 introduces B-tree skip scans, which improve query performance, and reduce index storage and maintenance overhead. Major version upgrades now retain optimizer statistics, ensuring consistent query performance immediately after upgrading without waiting for statistics to be regenerated. Logical replication can now stream large transactions in parallel, reducing replication lag and keeping downstream systems more current. Please refer to the Amazon Aurora PostgreSQL release notes for details. You can upgrade your database using several options including RDS Blue/Green deployments, upgrade in-place, or restoring a snapshot. Learn more about upgrading your database instances in the Amazon Aurora User Guide. Aurora PostgreSQL 18.3 is available in all commercial AWS Regions and AWS GovCloud (US) Regions. Amazon Aurora is designed for unparalleled high performance and availability at global scale with full PostgreSQL and MySQL compatibility. It provides built-in security, continuous backups, serverless compute, up to 15 read replicas, automated multi-Region replication, and integrations with other AWS services. To get started with Amazon Aurora, take a look at our getting started page.
Amazon Managed Workflows for Apache Airflow (MWAA) Serverless now supports workflow and task state change events to Amazon EventBridge, enabling data engineering and platform teams to build event-driven automation for their Apache Airflow workflows.
Previously, monitoring workflow execution required custom polling logic or manual observation. With this launch, MWAA Serverless can emit events when workflows transition between states, including started, running, succeeded, or failed, and when individual tasks change state, such as scheduled, succeeded, failed, or up for retry. With this feature, you can further automate your existing workflows – for example, using EventBridge notifications to trigger alerts when a production workflow fails, automatically restart dependent pipelines when an upstream workflow succeeds, or log state transitions to Amazon S3 for compliance and auditing.
This feature is available in all AWS Regions where Amazon MWAA Serverless is available. For the complete list of supported Regions, see Regions in the Amazon MWAA Serverless User Guide. For pricing details, see Amazon EventBridge pricing.
Amazon Managed Workflows for Apache Airflow (MWAA) Serverless now supports workflow and task state change events to Amazon EventBridge, enabling data engineering and platform teams to build event-driven automation for their Apache Airflow workflows.
Previously, monitoring workflow execution required custom polling logic or manual observation. With this launch, MWAA Serverless can emit events when workflows transition between states, including started, running, succeeded, or failed, and when individual tasks change state, such as scheduled, succeeded, failed, or up for retry. With this feature, you can further automate your existing workflows – for example, using EventBridge notifications to trigger alerts when a production workflow fails, automatically restart dependent pipelines when an upstream workflow succeeds, or log state transitions to Amazon S3 for compliance and auditing.
This feature is available in all AWS Regions where Amazon MWAA Serverless is available. For the complete list of supported Regions, see Regions in the Amazon MWAA Serverless User Guide. For pricing details, see Amazon EventBridge pricing.
To learn more, see Monitoring Amazon MWAA Serverless in the Amazon MWAA Serverless User Guide and Amazon MWAA Serverless events in the Amazon EventBridge Events Reference.
Amazon Managed Service for Prometheus now supports out-of-order sample ingestion and a workspace-level rule query offset. All workspaces have a default out-of-order time window of 1 minute, allowing the workspace to accept metric samples arriving outside strict chronological order. You can adjust this window to match your ingestion patterns or set it to 0 to disable the feature and discard out-of-order samples. You can also configure a global rule query offset that introduces a delay before rule evaluation queries run, giving late-arriving samples time to be ingested before rules execute.
Together, these features reduce data loss and improve alerting accuracy for workloads with distributed collectors, batched exports, or variable network latency. Out-of-order sample support ensures late-arriving data points are ingested rather than discarded, preserving metric completeness. The rule query offset compensates for the expected ingestion delay. Without it, rules evaluate instantly and may miss samples that haven’t landed yet, producing results that differ from the same expression evaluated after all metrics arrive. Two new CloudWatch vended metrics, OutOfOrderIngestionRate and OutOfOrderSampleAge give you visibility into ingestion patterns, helping you tune both settings for your workload.
Out-of-order sample ingestion and rule query offset are available in all AWS regions where Amazon Managed Service for Prometheus is generally available. To get started, configure the out-of-order time window and ruler query offset in your workspace settings via AWS console, API or CLI. For more information, see Amazon Managed Service for Prometheus user documentation.
Amazon Managed Service for Prometheus now supports out-of-order sample ingestion and a workspace-level rule query offset. All workspaces have a default out-of-order time window of 1 minute, allowing the workspace to accept metric samples arriving outside strict chronological order. You can adjust this window to match your ingestion patterns or set it to 0 to disable the feature and discard out-of-order samples. You can also configure a global rule query offset that introduces a delay before rule evaluation queries run, giving late-arriving samples time to be ingested before rules execute.
Together, these features reduce data loss and improve alerting accuracy for workloads with distributed collectors, batched exports, or variable network latency. Out-of-order sample support ensures late-arriving data points are ingested rather than discarded, preserving metric completeness. The rule query offset compensates for the expected ingestion delay. Without it, rules evaluate instantly and may miss samples that haven’t landed yet, producing results that differ from the same expression evaluated after all metrics arrive. Two new CloudWatch vended metrics, OutOfOrderIngestionRate and OutOfOrderSampleAge give you visibility into ingestion patterns, helping you tune both settings for your workload.
Out-of-order sample ingestion and rule query offset are available in all AWS regions where Amazon Managed Service for Prometheus is generally available. To get started, configure the out-of-order time window and ruler query offset in your workspace settings via AWS console, API or CLI. For more information, see Amazon Managed Service for Prometheus user documentation.
AWS announces AWS Workload Credentials Provider, a lightweight client-side provider that automates deployment of exported certificates from AWS Certificate Manager (ACM) and local caching of secrets from AWS Secrets Manager across AWS and non-AWS workloads.
Previously, customers exporting public or private certificates from ACM had to build custom automation using Amazon EventBridge to detect renewals and deploy the updated certificates. With public certificate lifetimes decreasing per the the Certification Authority Browser Forum (CA/B) mandate, this custom automation can become difficult to maintain at scale. AWS Workload Credentials Provider eliminates this complexity by providing a single provider that helps distribute and automate both secrets and certificates to your workloads. You configure it with your certificate ARN and specify options such as file paths and server reload behavior — the provider then handles certificate export and deployment automatically to prevent expiry related failures. It runs on Windows and Linux and supports Apache and NGINX web servers.
For secrets caching, the provider maintains full backwards compatibility with the AWS Secrets Manager Agent, enabling you to securely cache application secrets locally across AWS and non-AWS workloads through the same unified provider.
AWS announces AWS Workload Credentials Provider, a lightweight client-side provider that automates deployment of exported certificates from AWS Certificate Manager (ACM) and local caching of secrets from AWS Secrets Manager across AWS and non-AWS workloads. Previously, customers exporting public or private certificates from ACM had to build custom automation using Amazon EventBridge to detect renewals and deploy the updated certificates. With public certificate lifetimes decreasing per the the Certification Authority Browser Forum (CA/B) mandate, this custom automation can become difficult to maintain at scale. AWS Workload Credentials Provider eliminates this complexity by providing a single provider that helps distribute and automate both secrets and certificates to your workloads. You configure it with your certificate ARN and specify options such as file paths and server reload behavior — the provider then handles certificate export and deployment automatically to prevent expiry related failures. It runs on Windows and Linux and supports Apache and NGINX web servers. For secrets caching, the provider maintains full backwards compatibility with the AWS Secrets Manager Agent, enabling you to securely cache application secrets locally across AWS and non-AWS workloads through the same unified provider. AWS Workload Credentials Provider is open source and available on GitHub. You can use it with exportable ACM certificates and Secrets Manager in all AWS Regions. To learn more, visit the AWS Certificate Manager documentation or the AWS Secrets Manager documentation.
AWS Elastic Beanstalk now provides a CloudWatch Logs integration directly in the environment Logs tab of the Elastic Beanstalk console. Previously, customers had to navigate to the CloudWatch console to find the relevant log groups and log streams for their environments. With this launch, customers can view CloudWatch log events without leaving the Elastic Beanstalk console.
The Logs tab displays log groups that an environment streams logs to, as well as log groups matching the aws/elasticbeanstalk/<env-name>/* prefix. Customers can select a log group to view its log streams, with the most recently active stream selected by default. A log stream dropdown allows switching between streams and filtering results. For deeper analysis, a View in CloudWatch dropdown provides direct links to the log group, log stream, or CloudWatch Logs Insights in the CloudWatch console.
This feature is available across all Elastic Beanstalk platform branches in all AWS Commercial Regions and AWS GovCloud (US) Regions where Elastic Beanstalk is available. For a complete list of supported Regions, see AWS Regions.
AWS Elastic Beanstalk now provides a CloudWatch Logs integration directly in the environment Logs tab of the Elastic Beanstalk console. Previously, customers had to navigate to the CloudWatch console to find the relevant log groups and log streams for their environments. With this launch, customers can view CloudWatch log events without leaving the Elastic Beanstalk console.
The Logs tab displays log groups that an environment streams logs to, as well as log groups matching the aws/elasticbeanstalk/<env-name>/* prefix. Customers can select a log group to view its log streams, with the most recently active stream selected by default. A log stream dropdown allows switching between streams and filtering results. For deeper analysis, a View in CloudWatch dropdown provides direct links to the log group, log stream, or CloudWatch Logs Insights in the CloudWatch console.
This feature is available across all Elastic Beanstalk platform branches in all AWS Commercial Regions and AWS GovCloud (US) Regions where Elastic Beanstalk is available. For a complete list of supported Regions, see AWS Regions.
For more information about using Elastic Beanstalk with Amazon CloudWatch, see the AWS Elastic Beanstalk developer guide. To learn more, visit the AWS Elastic Beanstalk product page.
Nuestro proceso continuo para construir un sistema de diseño orientado a la IA que apoye el trabajo hoy, mientras nos lleva al mañana.
Por: Jon Friedman.
A medida que Copilot evoluciona de manera gradual hacia un socio de pensamiento —una presencia inteligente tejida en su flujo de trabajo—, su columna vertebral se convertirá en el Copilot Design System, un sistema de diseño orientado a la IA que creamos para que resulte intencionado y humano.
Los sistemas de diseño siempre han sido planos vivientes, pero en la era actual de la creación de productos centrada en IA, no se limitan a considerar el diseño de interfaces. Orquestan la coherencia a través de sistemas complejos, codifican cómo moldear el comportamiento de los modelos con una perspectiva centrada en el ser humano e introducen nuevos comportamientos de usuario y modelos mentales basados en la capacidad de la IA para reconocer y apoyar la intención humana.
Desde patrones de orquestación hasta iconografía, la experiencia que construimos tendrá en última instancia componentes que trabajan juntos para amplificar el pensamiento, guiar decisiones y desbloquear la creatividad—de manera fluida, dondequiera que ustedes trabajen. Basada en la retroalimentación de los clientes para crear mejores experiencias, una pregunta fundamental guía la evolución de nuestro sistema: ¿cómo se vería y comportaría un socio reflexivo?
«Las aplicaciones de Microsoft 365 han moldeado el comportamiento organizacional durante décadas, al establecer patrones de diseño y modelos mentales en los que confían miles de millones de personas cada día.«
01
El sistema que moldea el sistema
Las aplicaciones de Microsoft 365 han moldeado el comportamiento organizacional durante décadas, al establecer patrones de diseño y modelos mentales en los que confían miles de millones de personas cada día. A través de ese trabajo, hemos aprendido que la productividad no es solo una función de las herramientas; está moldeada por el sistema más amplio en el que la gente piensa y trabaja. Ahora podemos unir estas dimensiones a través de Copilot, para apoyar maneras más enriquecidas de colaboración y creatividad a través de interacciones humano-humano, humano-IA y humano-IA-humano.
La forma en que diseñemos esa colaboración influirá en cómo se desarrolla la productividad en organizaciones grandes y pequeñas, hoy y dentro de diez años. Nuestra filosofía de diseño era construir a la velocidad de la vida, no el bombo de la IA: co-crear con los clientes e integrar la investigación de los usuarios en cada paso del proceso.
02
Arquitectura de Copilot en las aplicaciones de Office
A medida que avanzamos hacia un sistema de diseño centrado en la IA, una parte temprana pero esencial de esa historia es cómo Copilot aparece en las aplicaciones de Office. Cuatro elementos arquitectónicos clave conforman en la actualidad el sistema dentro de la app, diseñado para funcionar según la mentalidad humana. La cognición no es un estado fijo. Es un movimiento dinámico entre exploración y enfoque, un objetivo que hace zoom continuo dentro y atrás. Estos dos movimientos—hacia afuera para descubrir, hacia dentro para refinar—se repiten de manera continua, para moldear cómo entendemos y actuamos sobre el mundo. Si la inteligencia no los encuentra en el nivel adecuado de ese ciclo, no se siente como un compañero. Se siente como una interrupción.
Esa información es la base estructural de cómo se comporta Copilot en las aplicaciones de Office. Ve en qué trabajan y entiende el contexto, permitiéndole actuar dentro del entorno dado. Implementamos esto a través de cuatro elementos arquitectónicos que operan en diferentes niveles cognitivos:
El Botón de Acción Dinámica (DAB)
Un Copilot siempre disponible dentro de la app que es adaptativo a nivel contextual y un punto de entrada principal al Chat.
Chat
La interfaz principal de Copilot y el punto de entrada del panel lateral, donde se capturan el razonamiento, las acciones y las salidas.
En el lienzo
Una interfaz ligera que aparece cuando seleccionan texto u objetos, realizan una acción en su lienzo con Copilot, o un punto de entrada contextual para Copilot y Chat.
Acciones de usuario sugeridas (SUAs)
Prompts contextuales, capacidades y funciones que surgen en los momentos adecuados de su flujo de trabajo.
03
Un Copiloto, donde sea que trabajen
El comportamiento humano es bastante contextual y matizado: cómo se dice o hace algo suele importar tanto como qué. La gente entiende el mundo mientras se mueve de manera física y mental por él, incluidos los espacios liminales entre momentos más definidos. Las palabras, sentimientos, experiencias y pensamientos asociados fluyen con nosotros, pero la inteligencia sin continuidad puede sentirse como una interrupción en lugar de un compañero de pensamiento. Cambiar de aplicación o superficie puede ser como salir de la corriente. Deberían poder invocar Copilot cada vez que avancen en su trabajo.
La cognición colaborativa se basa en conversaciones pasadas para entender el contexto, reconocer patrones y cambiar de dirección. Eso significa que el mismo Copilot con el que interactuaron en Word debería ser el mismo con el que conversan en Excel. En M365, DAB es su socio de pensamiento de referencia en escritorio, web, iPad y móvil.
En cada superficie dentro de la app, DAB reconoce su contexto local inmediato. Es cómo Copilot sigue de manera constante su línea de pensamiento, para ofrecer sugerencias relevantes y accionables mientras mantiene la conversación continua entre aplicaciones—al adaptar su conciencia cuando cambian de contexto, para no tener que repetir la misma conversación que acaban de tener en otra superficie.
Las palabras, sentimientos, experiencias y pensamientos asociados fluyen con nosotros, pero la inteligencia sin continuidad puede sentirse como una interrupción en lugar de un compañero de pensamiento.
Cuando se selecciona DAB se abre el Chat, la interfaz universal de Copilot. Más que una simple interfaz, el chat es la memoria de su compañero de pensamiento—para registrar todas sus interacciones y sugerencias con Copilot en Microsoft 365 para que puedan aprovechar conocimientos previos, actualizar su estrategia y perfeccionar su visión. Es donde vive la exploración amplia: un espacio para sintetizar, cuestionar y mirar atrás para avanzar.
Cuando el objetivo se estrecha, On-Canvas trae Copilot directo a su espacio de trabajo. Su compañero de pensamiento aparece a través de la interfaz contextual en los momentos de la ejecución, centrándose en el contenido específico que han seleccionado—para pasar del contexto general de la app al contenido preciso de su documento, apoyándolos justo donde trabajan sin interrumpir su flujo.
Para completar el sistema, las Acciones de Usuario Sugeridas se adaptan a DAB, Chat y On-Canvas para ofrecer pasos útiles a nivel contextual en cada punto del espectro cognitivo, ya sea que miren una página en blanco o un borrador que necesita una chispa. Solo surgen cuando tienen un propósito, para ofrecer el empujón que los pone más allá de lo esperado.
Lanzar y atrapar
04
Un nuevo patrón: Lanzar y atrapar
El corazón del aspecto dentro de la app de la experiencia es una conciencia mutua del enfoque, el suyo y el de Copilot, y cómo ambos se mantienen alineados. Refuerza el concepto de que Copilot se mueve con su pensamiento, en lugar de actuar como un conjunto de características fragmentadas. Para hacerlo bien, la coherencia debe diseñarse con matices o pierden los contextos de comportamiento de las personas. Requiere una comprensión profunda de cómo las personas piensan, crean significado y desarrollan ideas a medida que avanzan en su trabajo—el punto de partida de nuestra investigación.
Basándonos en estudios de seguimiento del mouse y exploraciones de prototipado a través de un equipo multidisciplinar, diseñamos un mecanismo de trabajo que regula cómo Copilot se mueve de manera fluida entre DAB, On-Canvas y Chat: un conjunto orquestado que llamamos Throw & Catch (Lanzar y Atrapar). Los puntos de entrada del sistema deben comunicarse de manera rutinaria entre sí—para pasar interacciones y razonamientos de manera fluida mientras los dirigen a donde está enfocado Copilot.
Al sincronizar y señalizar el comportamiento activo de un punto de entrada justo mientras el otro se retira, el patrón busca construir confianza y reducir la fricción cognitiva. Sea cual sea la superficie en la que esté activo el Copiloto, su comportamiento se vuelve visible y distintivo. La experiencia de Throw & Catch está diseñada para ser ambiental y sentida de manera ligera, para afirmar que ustedes tienen el control—lo que hace de Copilot una extensión de su pensamiento. Siempre donde estén, a su nivel de concentración.
Un sistema simplificado
05
Coherencia que pueden sentir, en cada superficie
Diseñar un compañero de pensamiento es el trabajo silencioso de moldear una experiencia que escuche, responda y se mueva al ritmo del pensamiento de una persona. Dado que ahora la IA puede diseñarse para responder a su intención en lugar de pedirles que se adapten a ella, la oportunidad que tenemos delante es profunda—y la responsabilidad de hacerlo bien es igual de grande. Desde patrones fundamentales como Throw & Catch hasta los elementos arquitectónicos centrales, un profundo conocimiento del comportamiento humano y organizacional guía la creación de cómo se comporta Copilot en las aplicaciones de productividad que les encantan. Con un lenguaje de diseño unificado, interacciones rápidas y agradables, y acceso contextual, Copilot se vuelve más consistente, fácil de descubrir e integrar, crucial para mantener el flujo de los clientes, potenciar el pensamiento y la creatividad humana, y llevar de manera cómoda a los clientes actuales y futuros a la era de la IA.
A medida que continuamos con la evolución del Sistema de Diseño Copilot aquí en Microsoft Design, siempre estamos abiertos a recibir comentarios y sugerencias. Mientras tanto, vamos a compartir nuestro pensamiento, prototipos y avances sobre la marcha.
Amazon OpenSearch Service now supports MCP Apps, bringing observability workflows directly into compatible agentic IDEs such as Claude Desktop and VS Code. With this capability, your AI agent in local environment can investigate incidents using logs, traces, metrics, and alerts stored in OpenSearch domains, collections and Amazon Managed Service for Prometheus. You can easily review and verify the results in interactive MCP App visualizations without leaving your local environment.
Each MCP App tool call returns a dual response, a concise text summary for your agent to reason over and an interactive visualization rendered in the same conversation thread for you to review. You can work alongside your observability agent from firing an alert, perform root cause analysis, exploring distributed traces, service maps, PromQL metric charts, and cross-signal correlations all within a single conversation. Available MCP App tools cover log, metrics and trace investigation, service performance, topology, dynamic visualizations, agent health, cluster health, and instrumentation scoring.
Amazon OpenSearch Service now supports MCP Apps, bringing observability workflows directly into compatible agentic IDEs such as Claude Desktop and VS Code. With this capability, your AI agent in local environment can investigate incidents using logs, traces, metrics, and alerts stored in OpenSearch domains, collections and Amazon Managed Service for Prometheus. You can easily review and verify the results in interactive MCP App visualizations without leaving your local environment. Each MCP App tool call returns a dual response, a concise text summary for your agent to reason over and an interactive visualization rendered in the same conversation thread for you to review. You can work alongside your observability agent from firing an alert, perform root cause analysis, exploring distributed traces, service maps, PromQL metric charts, and cross-signal correlations all within a single conversation. Available MCP App tools cover log, metrics and trace investigation, service performance, topology, dynamic visualizations, agent health, cluster health, and instrumentation scoring.
The OpenSearch MCP app experience is available is available in all AWS Regions where Amazon OpenSearch UI is offered. To get started, follow the instructions in OpenSearch Agentic observability with MCP Apps. To learn more about OpenSearch, visit Amazon OpenSearch Service Developer Guide.
Today, AWS announces the expanded availability of OpenAI’s GPT-5.4 and GPT-5.5 models, which are now available in the US East (N. Virginia) Region on Amazon Bedrock. With GPT-5.4 and GPT-5.5, you can build generative AI applications across reasoning, coding, computer use, document workflows, and long-running agentic tasks.
GPT-5.5 is OpenAI’s most capable model, designed for advanced coding, research, analysis, software operation, document workflows, and long-running agentic tasks. It can understand open-ended goals, use tools, reason across longer workflows, navigate ambiguity, and carry complex tasks through to completion with less orchestration. GPT-5.4 brings frontier reasoning, coding, computer use, long-context workflows, and tool use to production applications that interpret context, interact with tools, operate software environments, and verify outputs across multiple steps. Both models support a 272K-token context window, accept text and image input, and are available through the Responses API with support for server-side and client-side tool calling, projects, and response streaming.
With this launch, GPT-5.4 and GPT-5.5 are now available in additional AWS Regions. To get started, visit the GPT-5.5 and GPT-5.4 model cards in our documentation.
Today, AWS announces the expanded availability of OpenAI’s GPT-5.4 and GPT-5.5 models, which are now available in the US East (N. Virginia) Region on Amazon Bedrock. With GPT-5.4 and GPT-5.5, you can build generative AI applications across reasoning, coding, computer use, document workflows, and long-running agentic tasks. GPT-5.5 is OpenAI’s most capable model, designed for advanced coding, research, analysis, software operation, document workflows, and long-running agentic tasks. It can understand open-ended goals, use tools, reason across longer workflows, navigate ambiguity, and carry complex tasks through to completion with less orchestration. GPT-5.4 brings frontier reasoning, coding, computer use, long-context workflows, and tool use to production applications that interpret context, interact with tools, operate software environments, and verify outputs across multiple steps. Both models support a 272K-token context window, accept text and image input, and are available through the Responses API with support for server-side and client-side tool calling, projects, and response streaming. With this launch, GPT-5.4 and GPT-5.5 are now available in additional AWS Regions. To get started, visit the GPT-5.5 and GPT-5.4 model cards in our documentation.
