Amazon Connect now gives business users greater control over daily contact center operations without requiring technical resources. With new capabilities to create customer UIs that adjust queues, routing behavior, and customer experience settings in real time, business users can respond to changing conditions immediately while maintaining enterprise-grade governance and security. For example, during a weather disruption, an airline contact center operations manager can shift agents to rebooking queues, update after-hours routing, and activate a pre-approved protocol that refreshes IVR prompts and triggers customer notifications, all in minutes and without technical team intervention. This reduces wait times, increases agent productivity, and improves the customer experience at moments of peak demand.
Contact center administrators can start by defining key business configurations such as queue assignments, operating hours, skill mappings, and escalation rules, in data tables that directly drive contact flows. Guides can then be configured to surface role-specific actions for each business user within persona based workspaces. Together, these updates enable a business-led operating model that keeps contact center operations fast, consistent, and secure, all without relying on IT.
Amazon Connect now gives business users greater control over daily contact center operations without requiring technical resources. With new capabilities to create customer UIs that adjust queues, routing behavior, and customer experience settings in real time, business users can respond to changing conditions immediately while maintaining enterprise-grade governance and security. For example, during a weather disruption, an airline contact center operations manager can shift agents to rebooking queues, update after-hours routing, and activate a pre-approved protocol that refreshes IVR prompts and triggers customer notifications, all in minutes and without technical team intervention. This reduces wait times, increases agent productivity, and improves the customer experience at moments of peak demand. Contact center administrators can start by defining key business configurations such as queue assignments, operating hours, skill mappings, and escalation rules, in data tables that directly drive contact flows. Guides can then be configured to surface role-specific actions for each business user within persona based workspaces. Together, these updates enable a business-led operating model that keeps contact center operations fast, consistent, and secure, all without relying on IT. These new capabilities are available in all AWS regions where Amazon Connect is available. To learn more, see the Amazon Connect Administrator Guide. To learn more about Amazon Connect, please visit the Amazon Connect website.
Por qué Microsoft Copilot Studio es la base para la transformación empresarial agéntica
Por: Dan Lewis, vicepresidente corporativo de Copilot Studio.
Las organizaciones líderes actuales atraviesan una transformación empresarial agente. Este cambio lleva la IA de concepto a un impacto medible, al automatizar flujos de trabajo existentes y utilizar agentes para aumentar la productividad y reinventar funciones completas. Copilot Studio, la plataforma de agentes de Copilot, ofrece una solución gestionada por completo para lograr esto.
Por medio de Copilot Studio, organizaciones de todo el mundo pueden incorporar con rapidez los beneficios de la IA a su negocio. Copilot Studio permite a las empresas optimizar y automatizar sus procesos con flujos de trabajo agentes, crear agentes de propósito único para resolver problemas específicos y desarrollar soluciones multiagente que generen resultados empresariales medibles a gran escala. El resultado: una base escalable, segura y gobernable que apoya las necesidades de los administradores de TI y los propietarios de negocios que miden el retorno de la inversión (ROI, por sus siglas en inglés). Este sistema acelera la transformación agéntica al ofrecer la relación calidad-precio sin sacrificar calidad ni control.
Al mismo tiempo, con Microsoft 365 Copilot, los usuarios pueden utilizar con facilidad la IA para mejorar su productividad personal y de equipo. Esta experiencia personalizada para usuarios de Microsoft 365 Copilot ofrece una forma rápida y guiada de configurar agentes que apoyen su trabajo y automaticen tareas diarias, eliminándolas de su agenda.
Hoy nos entusiasma compartir nuevas capacidades en Copilot Studio que apoyan todos estos escenarios y grupos que utilizan nuestro producto, para facilitar a los creadores y administradores moldear el comportamiento de los agentes, hacer cumplir los estándares organizativos y ampliar la funcionalidad con IA.
Mejoras para el usuario final
Nuestra experiencia en Copilot Studio para crear agentes y flujos de trabajo, así como nuestras capacidades de creación de agentes en Microsoft 365 Copilot, continúan el apoyo de la creación de agentes para todos los usuarios, desde creadores profesionales y administradores de TI que realizan transformaciones de IA empresarial, hasta empleados que crean agentes y flujos de trabajo para su uso personal. Las actualizaciones recientes se centran en hacer el proceso más sencillo y eficiente.
Novedades en Microsoft 365 Copilot
Experiencia de creación rediseñada: Construyan y perfeccionen agentes mediante una interfaz conversacional mejorada que guíe a los usuarios y acceda a un conjunto ampliado de fuentes de conocimiento relacionadas con el trabajo.
Generación de archivos con lenguaje natural: Los agentes integrados en Microsoft 365 Copilot ahora pueden crear archivos de Word, Excel y PowerPoint en segundos por medio de comandos en lenguaje natural.
Camino de actualización fluido: Copien agentes de Microsoft 365 Copilot a Copilot Studio con un solo clic, para desbloquear la personalización avanzada de agentes de IA.
Agente de flujos de trabajo en Microsoft 365 Copilot: Creen, construyan y gestionen flujos de trabajo por medio de lenguaje natural en el chat. Aumenten la productividad con escenarios rápidos como triaje diario, resúmenes semanales y aprobaciones ligeras, todo de manera directa dentro de Copilot.
Los desarrolladores de aplicaciones de TI y otros creadores profesionales del sector ya pueden crear agentes sofisticados en Copilot Studio sin necesidad de programar. Copilot Studio incluye capacidades como conectar y actuar a través de más de 1.400 sistemas de registro mediante Model Context Protocol (MCP), conectores Power Platform y Microsoft Graph. También incluye herramientas amplias y profundas como escribir y ejecutar código de forma autónoma, ofrecer análisis de agentes y medición de ROI y datos completos de implementación, y más, todo basado en la plataforma de gobernanza y seguridad de Microsoft. Estamos entusiasmados de compartir nuevas capacidades que brindan a los creadores aún más flexibilidad y control para diseñar agentes empresariales adaptados a sus necesidades organizativas únicas.
Elijan su propio modelo: Seleccionen entre opciones líderes como GPT5 de OpenAI, Sonnet 4.5 de Anthropic y Opus 4.1 para potenciar a sus agentes. Esto les permite adaptar la inteligencia de los agentes a su escenario empresarial específico, optimizar el rendimiento, experimentar con nuevas capacidades y entregar agentes que se adapten a las necesidades únicas de su organización.
Asegúrense de que los agentes estén listos para el lanzamiento y que no retrocedan con el tiempo, con Evaluaciones: Las herramientas de evaluación integradas les ayudan a probar agentes frente a escenarios reales, comparar versiones y seguir el rendimiento con métricas claras. Las evaluaciones pueden dar a los equipos mayor confianza en que sus inversiones funcionan como se espera.
Uso del ordenador: Los agentes ahora pueden automatizar tareas entre aplicaciones y sitios web, por medio de experiencias seguras de Windows 365, desde navegadores alojados para automatización web rápida hasta pools de PC en la nube gestionados por TI para escalabilidad rápida.
Mejoras para el administrador
A medida que los agentes se convierten en piezas centrales para automatizar el trabajo y transformar flujos de trabajo, Copilot Studio introduce nuevas capacidades de gobernanza y protección diseñadas para ayudar a las organizaciones a mantener una supervisión sólida.
Análisis ampliados de agentes: Visión clara del rendimiento conectado y del agente infantil, visibilidad detallada del consumo y límites de créditos de Copilot, resúmenes generados por IA de los principales análisis de información de valor y analítica de interrogación mediante lenguaje natural.
Protección en tiempo real: Copilot Studio se integra con Microsoft Defender y otras plataformas de seguridad de confianza, lo que proporciona monitorización continua y protección contra amenazas como la inyección rápida, lo que ayuda a que cada agente funcione de manera más segura.
ID de Agente Microsoft Entra: Cada agente creado en Copilot Studio ahora recibe un ID único de Agente Microsoft Entra, lo que facilita registrar, gestionar y gobernar toda su flota de agentes.
Agent 365 y Copilot Studio: Control unificado para agentes
Los agentes han comenzado a asumir más responsabilidades en las operaciones empresariales y Copilot Studio es su plataforma de lanzamiento para construirlas. Con la introducción del Agente 365 —el plano de control para agentes—, las amplias capacidades de gobernanza y gestión que ofrecemos hoy, incluidos los controles de compartición, políticas avanzadas de conectores, inventario de agentes, gestión del entorno zonificado y más, también se integrarán en la plataforma Agent 365 al utilizar agentes integrados en Copilot Studio.
Además, en Copilot Studio, los creadores pueden ahora crear agentes que usan los nuevos servidores MCP de Agent 365. Estos servidores permiten a los agentes programar reuniones en Microsoft Teams, redactar documentos en Word, enviar correos electrónicos en Outlook y actualizar registros de gestión de relaciones con clientes (CRM, por sus siglas en inglés) en Microsoft Dynamics 365. Esto permite la entrega de flujos de trabajo inteligentes y conformes, así como agentes con rastreos de auditoría integrados y una aplicación granular de políticas, todo desde una sola plataforma.
Agent 365 está disponible a partir de hoy en Microsoft 365 Admin Center con Frontier, el programa de acceso anticipado de Microsoft para las últimas innovaciones en IA.
Escalar hasta la Empresa Frontera con control
La verdadera transformación ocurre cuando los agentes se construyen para escalar, se regulan para el cumplimiento y se miden en cuanto al impacto. Copilot Studio ofrece esa base, para que las organizaciones puedan construir sistemas multiagente empresariales, automatizar flujos de trabajo con precisión y reinventar procesos minimizando riesgos.
Los resultados de EY muestran lo que es posible cuando se invierte en una plataforma de agentes completa, basada en Microsoft. Son solo una de las muchas empresas que implementan agentes con Copilot Studio. En este caso, su PowerPost Agent construido sobre Copilot Studio llevó a grandes mejoras en el procesamiento de diarios:
Reducción del 95% en el tiempo de entrega
37% de ahorro de costes1
Implementar el Agente PowerPost con Microsoft Copilot Studio ha transformado de manera fundamental nuestro procesamiento de diarios. Lo que antes llevaba minutos ahora ocurre en segundos—a través de la optimización de los flujos de trabajo y la mejora en la precisión.
—Paula Korczak, directora de producto para el libro mayor general, EY
Esa es la diferencia entre montar plataformas de agentes aisladas e invertir en una plataforma gestionada y escalable como Copilot Studio: agentes y diseño de procesos con agentes que sean repetibles, auditables y escalables.
Empiecen hoy mismo
Para saber más sobre Copilot Studio y cómo puede transformar la productividad de su organización, visiten la web de Copilot Studio y suscríbanse hoy mismo para una prueba gratuita. Realicen la Evaluación de Preparación de Agentes para comparar la madurez de su organización en cinco áreas críticas—estrategia, datos, procesos, cultura y seguridad—y obtengan un informe personalizado para acelerar la adopción escalable de agentes y promover la transformación empresarial de los agentes.
Amazon Connect now allows you to test and simulate contact center experiences in just a few clicks, making it easy to validate workflows, self-service voice interactions, and their outcomes. For each test, you can configure the test parameters including the caller’s phone number or customer profile, the reason for the call (such as «I need to check my order status»), the expected responses (such as «Your request has been processed»), and business conditions like after-hours scenarios or full call queues. After executing tests, results show success or failure based on your defined criteria, along with the path taken by the simulated interaction and detailed logs to quickly diagnose potential issues
With this launch, you can run multiple tests simultaneously to validate scenarios and workflows at scale, reducing testing time. Companies can view test results and identify common failure patterns across all their tests in Connect’s analytics dashboards. These capabilities enable you to rapidly validate changes to your workflows and confidently deploy new experiences to adapt to your ever-changing business needs.
To learn more about these features, see the Amazon Connect Administrator Guide. These features are available in all AWS regions where Amazon Connect is available. To learn more about Amazon Connect, AWS’s AI-native customer experience solution, please visit the Amazon Connect website.
Amazon Connect now allows you to test and simulate contact center experiences in just a few clicks, making it easy to validate workflows, self-service voice interactions, and their outcomes. For each test, you can configure the test parameters including the caller’s phone number or customer profile, the reason for the call (such as «I need to check my order status»), the expected responses (such as «Your request has been processed»), and business conditions like after-hours scenarios or full call queues. After executing tests, results show success or failure based on your defined criteria, along with the path taken by the simulated interaction and detailed logs to quickly diagnose potential issues With this launch, you can run multiple tests simultaneously to validate scenarios and workflows at scale, reducing testing time. Companies can view test results and identify common failure patterns across all their tests in Connect’s analytics dashboards. These capabilities enable you to rapidly validate changes to your workflows and confidently deploy new experiences to adapt to your ever-changing business needs. To learn more about these features, see the Amazon Connect Administrator Guide. These features are available in all AWS regions where Amazon Connect is available. To learn more about Amazon Connect, AWS’s AI-native customer experience solution, please visit the Amazon Connect website.
Amazon Connect now supports Model Context Protocol (MCP), enabling AI agents for end-customer self-service and employee assistance to use standardized tools for retrieving information and completing actions. With this launch, businesses can enhance their AI agents with extensible tool capabilities that improve issue resolution. For example, an AI agent can automatically look up order status, process refunds, and update customer records during a self-service interaction without requiring human intervention.
With this launch, Amazon Connect provides out-of-the-box MCP tools for common tasks such as updating contact attributes and retrieving case information. You can also use flow modules as MCP tools to reuse the same business logic across both deterministic and generative AI workflows. Additionally, you can integrate custom tools or third-party services through flow modules or the Amazon Bedrock AgentCore Gateway.
Amazon Connect now supports Model Context Protocol (MCP), enabling AI agents for end-customer self-service and employee assistance to use standardized tools for retrieving information and completing actions. With this launch, businesses can enhance their AI agents with extensible tool capabilities that improve issue resolution. For example, an AI agent can automatically look up order status, process refunds, and update customer records during a self-service interaction without requiring human intervention. With this launch, Amazon Connect provides out-of-the-box MCP tools for common tasks such as updating contact attributes and retrieving case information. You can also use flow modules as MCP tools to reuse the same business logic across both deterministic and generative AI workflows. Additionally, you can integrate custom tools or third-party services through flow modules or the Amazon Bedrock AgentCore Gateway. For region availability, please see the availability of Amazon Connect features by Region. To learn more about Connect’s AI agents please visit the website or see the help documentation. To learn more about Amazon Connect, the AWS cloud-based contact center, please visit the Amazon Connect website.
Amazon Connect launches real-time AI agent assistance and contact summarization for Salesforce Contact Center with Amazon Connect (SCC-AC). It enables Connect AI agents to automatically leverage customer information and knowledge base articles from Salesforce CRM for accelerated issue resolution and consistent outcomes across voice and chat interactions.
When human intervention is required, the seamless integration within SCC-AC connects customers to agents who have a unified view of customer data, issue context, and interaction history within Agentforce Service and Agentforce Sales. Agents receive real-time voice transcripts and contextual recommendations, while supervisors gain enhanced call monitoring capabilities directly in Salesforce. Upon resolution, automated post-contact summarization enables agents to easily update Salesforce cases, streamlining administrative tasks. Administrators can deploy and configure this integrated contact center solution in minutes, leveraging Amazon Connect’s voice, digital channels, and intelligent routing capabilities.
Amazon Connect launches real-time AI agent assistance and contact summarization for Salesforce Contact Center with Amazon Connect (SCC-AC). It enables Connect AI agents to automatically leverage customer information and knowledge base articles from Salesforce CRM for accelerated issue resolution and consistent outcomes across voice and chat interactions. When human intervention is required, the seamless integration within SCC-AC connects customers to agents who have a unified view of customer data, issue context, and interaction history within Agentforce Service and Agentforce Sales. Agents receive real-time voice transcripts and contextual recommendations, while supervisors gain enhanced call monitoring capabilities directly in Salesforce. Upon resolution, automated post-contact summarization enables agents to easily update Salesforce cases, streamlining administrative tasks. Administrators can deploy and configure this integrated contact center solution in minutes, leveraging Amazon Connect’s voice, digital channels, and intelligent routing capabilities. This feature is available in all AWS Regions where Amazon Connect is available. To learn more and get started, see the Salesforce Contact Center with Amazon Connect documentation. To learn more about Amazon Connect, see Amazon Connect and our strategic Salesforce partnership
Amazon Connect now provides analytics and monitoring capabilities for AI agents across self-service and agent assistance experiences. With this launch, you can measure and continuously improve AI agent performance and customer outcomes through easy to customize dashboards that provide key metrics like number of AI agent led interactions, hand-off rates, conversation turns, and average handle time. You can also compare AI agent performance across versions to identify optimal configurations and review insights to understand where AI agents are performing well and where improvements are needed. Additionally, with this launch, you can configure rules to trigger automated actions, such as sending alerts when self-service contacts are transferred to human agents with low sentiment scores. Amazon Connect also provides AI agent traces via APIs with detailed information such as request and response payloads and tool invocations, enabling you to easily understand AI agent actions and decision-making for faster troubleshooting.
This capabilities is available in all AWS Regions where Amazon Connect AI agents are offered. To learn more about AI agent analytics, see the Amazon Connect Administrator Guide. To learn more about Amazon Connect, the AWS contact center as a service solution on the cloud, please visit the Amazon Connect website.
Amazon Connect now provides analytics and monitoring capabilities for AI agents across self-service and agent assistance experiences. With this launch, you can measure and continuously improve AI agent performance and customer outcomes through easy to customize dashboards that provide key metrics like number of AI agent led interactions, hand-off rates, conversation turns, and average handle time. You can also compare AI agent performance across versions to identify optimal configurations and review insights to understand where AI agents are performing well and where improvements are needed. Additionally, with this launch, you can configure rules to trigger automated actions, such as sending alerts when self-service contacts are transferred to human agents with low sentiment scores. Amazon Connect also provides AI agent traces via APIs with detailed information such as request and response payloads and tool invocations, enabling you to easily understand AI agent actions and decision-making for faster troubleshooting. This capabilities is available in all AWS Regions where Amazon Connect AI agents are offered. To learn more about AI agent analytics, see the Amazon Connect Administrator Guide. To learn more about Amazon Connect, the AWS contact center as a service solution on the cloud, please visit the Amazon Connect website.
Amazon Connect now provides customer service representatives with new AI agents that guide them through customer interactions by recommending actions, retrieving information, and executing tasks on their behalf. For example, an AI agent can guide a representative through processing a product return by automatically pulling order history, calculating refund amounts, and initiating the return process. These AI agents analyze conversation context and customer sentiment in real-time, actively completing tasks such as preparing documentation and handling routine processes. This enables representatives to focus on building customer relationships and handling complex situations while AI manages the background work, enhancing productivity and ensuring consistent outcomes. You can get started with out-of-the-box agents provided by Amazon Connect or easily customize AI agent behavior and actions to align with your business needs.
Amazon Connect now provides customer service representatives with new AI agents that guide them through customer interactions by recommending actions, retrieving information, and executing tasks on their behalf. For example, an AI agent can guide a representative through processing a product return by automatically pulling order history, calculating refund amounts, and initiating the return process. These AI agents analyze conversation context and customer sentiment in real-time, actively completing tasks such as preparing documentation and handling routine processes. This enables representatives to focus on building customer relationships and handling complex situations while AI manages the background work, enhancing productivity and ensuring consistent outcomes. You can get started with out-of-the-box agents provided by Amazon Connect or easily customize AI agent behavior and actions to align with your business needs. To learn more about Amazon Connect AI agents, please visit the website or see the help documentation. For region availability, please see the availability of Amazon Connect features by Region. To learn more about Amazon Connect, the AWS cloud-based contact center, please visit the Amazon Connect website.
Amazon Connect now supports message processing that intercepts and processes chat messages before they reach any participant. This new capability enables automatic redaction of sensitive data and custom message processing, helping businesses maintain compliance and security standards while delivering personalized customer experiences.
The built-in sensitive data redaction can automatically detect and remove sensitive information like credit card numbers and social security numbers across multiple languages, including English, French, Portuguese, German, Italian, and Spanish variants. You can choose to redact selected or all sensitive data entities, with options to replace them with generic or entity-specific placeholders (e.g., [PII] or [NAME]). Businesses can also integrate custom processors for use cases such as language translation or profanity filtering, ensuring compliant and effective communications for their specific business needs.
These message processing capabilities are now available in the following regions: US East (N. Virginia), US West (Oregon), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Canada (Central), Europe (Frankfurt) Europe (London), Africa (South Africa). To learn more about Amazon Connect, visit the Amazon Connect documentation and pricing.
Amazon Connect now supports message processing that intercepts and processes chat messages before they reach any participant. This new capability enables automatic redaction of sensitive data and custom message processing, helping businesses maintain compliance and security standards while delivering personalized customer experiences. The built-in sensitive data redaction can automatically detect and remove sensitive information like credit card numbers and social security numbers across multiple languages, including English, French, Portuguese, German, Italian, and Spanish variants. You can choose to redact selected or all sensitive data entities, with options to replace them with generic or entity-specific placeholders (e.g., [PII] or [NAME]). Businesses can also integrate custom processors for use cases such as language translation or profanity filtering, ensuring compliant and effective communications for their specific business needs. These message processing capabilities are now available in the following regions: US East (N. Virginia), US West (Oregon), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Canada (Central), Europe (Frankfurt) Europe (London), Africa (South Africa). To learn more about Amazon Connect, visit the Amazon Connect documentation and pricing.
Amazon Connect Outbound Campaigns now supports visual journey builder, a new feature that lets you create multi-step, multi-channel customer engagements directly in the Amazon Connect console. You can design end-to-end engagement experiences that combine voice, SMS, email, and WhatsApp interactions to reach customers proactively and reduce inbound contact volume.
Outbound Campaigns help you automate personalized communication flows based on customer behavior or time-based triggers. For example, you can send an appointment reminder by SMS, follow up with a voice call if the customer does not respond, and send a confirmation email once the appointment is booked. You can also configure steps in the journey builder that offer customers the option to connect with a live agent through Amazon Connect when additional support is needed. You can use existing Amazon Connect Flow integrations, AI capabilities, and customer data from Amazon Connect Customer Profiles to tailor each interaction. This helps contact centers improve engagement rates, reduce manual effort, and deliver more consistent customer experiences.
Amazon Connect Outbound Campaigns now supports visual journey builder, a new feature that lets you create multi-step, multi-channel customer engagements directly in the Amazon Connect console. You can design end-to-end engagement experiences that combine voice, SMS, email, and WhatsApp interactions to reach customers proactively and reduce inbound contact volume. Outbound Campaigns help you automate personalized communication flows based on customer behavior or time-based triggers. For example, you can send an appointment reminder by SMS, follow up with a voice call if the customer does not respond, and send a confirmation email once the appointment is booked. You can also configure steps in the journey builder that offer customers the option to connect with a live agent through Amazon Connect when additional support is needed. You can use existing Amazon Connect Flow integrations, AI capabilities, and customer data from Amazon Connect Customer Profiles to tailor each interaction. This helps contact centers improve engagement rates, reduce manual effort, and deliver more consistent customer experiences. This feature is available in all AWS Regions where Amazon Connect Outbound Campaigns is supported. To learn more, visit the Amazon Connect Outbound Campaigns documentation.
Amazon Connect provides managers with new criteria while setting up automated evaluations, making it easier to identify relevant contacts for evaluation, and providing additional insights to automatically populate evaluation forms. For example, managers can specify that inbound contacts with no connectivity issues, handled by agents in a specific department, should be automatically evaluated using a particular evaluation form. Additionally, managers can use new metrics criteria on agent call avoidance, contact handling efficiency, and audibility, to automatically fill the selected form.
This feature is available in all regions where Amazon Connect is offered. To learn more, please visit our documentation and our webpage.
Amazon Connect provides managers with new criteria while setting up automated evaluations, making it easier to identify relevant contacts for evaluation, and providing additional insights to automatically populate evaluation forms. For example, managers can specify that inbound contacts with no connectivity issues, handled by agents in a specific department, should be automatically evaluated using a particular evaluation form. Additionally, managers can use new metrics criteria on agent call avoidance, contact handling efficiency, and audibility, to automatically fill the selected form. This feature is available in all regions where Amazon Connect is offered. To learn more, please visit our documentation and our webpage.
