Amazon Connect Release Notes

Amazon Connect Updates

AWS Service Quotas support in Amazon Connect Cases

Amazon Connect Cases now supports AWS Service Quotas, giving administrators a centralized way to view applied limits, monitor utilization, and scale case workloads without hitting unexpected service constraints. You can request quota increases directly from the Service Quotas console, and eligible requests are automatically approved without manual intervention.

Larger text fields in Amazon Connect Cases

Amazon Connect Cases now supports larger, multi-line text fields with up to 4,100 characters. Administrators can use the Admin UI to select the appropriate configuration (single-line or multi-line) on a per-field basis, improving case documentation capabilities.

Per-channel auto-accept and ACW timeouts

Amazon Connect now enables per-channel auto-accept and after contact work timeout settings for chat, tasks, emails, and callbacks to optimize how agents spend their time. Previously, these settings were available only for inbound voice contacts. To learn more, see Configure agent settings.

Please note that if you currently integrate with the UpdateUserPhoneConfig API, we recommend you migrate to the newly released UpdateUserConfig API instead. Per-channel auto-accept and ACW timeouts can only be updated via UpdateUserConfig API.

Audio Enhancement for agents

Amazon Connect now offers Audio Enhancement to improve audio quality on the agent's side by reducing background noise and isolating the agent's voice during calls. Administrators can enable noise suppression or voice isolation modes for agents through user management settings. Agents with the appropriate security profile permissions can also adjust their own Audio Enhancement settings during work sessions.

For more information, see Enable Audio Enhancement.

CSV upload for dependent field options (Amazon Connect Cases)

Amazon Connect Cases now supports CSV upload for dependent field options
Amazon Connect Cases now enables you to bulk configure cascading dropdown menus for case fields by uploading CSV files containing field option mappings. This capability significantly reduces manual configuration time for complex hierarchical data structures such as geographic hierarchies (Country → State → City) or product categorizations (Category → Subcategory). You can include multiple field pairs in a single CSV file.

For more information, see CSV upload for dependent field options.

In-app notifications keep users informed of urgent updates and actions

In-app notifications keep users informed of urgent updates and actions
Amazon Connect Now users in the Amazon Connect admin website can be provided notifications in their header, so urgent updates and follow-on actions can be seen from any page within the Amazon Connect admin website. APIs allow services and customers to publish brief messages (including URLs) to a specified audience, and a new header icon will indicate when unread messages are available. On click, the user can read the message, mark as unread if necessary, and follow links to reports or other UIs if follow-on actions are advised.

For more information, see In-app notifications keep users informed of urgent updates and actions.

Original source Report a problem

Amazon Connect Launches Wait Time Estimates to Improve Customer Experience

Amazon Connect now delivers improved estimated wait time metrics for queues and enqueued contacts, empowering organizations to enhance customer satisfaction. This allows contact centers to set accurate customer expectations, provide convenient options such as callbacks when hold times are extended, and balance workloads effectively across multiple queues. By leveraging the estimated wait time metric, contact centers can make strategic routing choices across queues while gaining enhanced visibility for better resource planning. For example, a customer calling about billing during peak hours with a 15-minute wait is seamlessly transferred to a cross-trained team with 2-minute availability, getting help faster without repeating their issue. The metric works seamlessly with routing criteria and agent proficiency configurations.

This feature is available in all AWS regions where Amazon Connect is offered. To learn more about estimated wait time see the Amazon Connect Administrator Guide. To learn more about Amazon Connect, the AWS cloud-based contact center, please visit the Amazon Connect website.

Amazon Connect now supports file attachments for tasks via StartTaskContact API

Amazon Connect now enables you to include file attachments when creating tasks using the StartTaskContact API. You can attach up to 5 files per task in various formats such as .pdf, .docx, .csv, .txt, .png, .jpg, .mp4, and more. This capability allows you to provide agents with relevant documents, images, or other files directly within the task context, streamlining workflows and improving agent efficiency.

Amazon Connect now supports tag-based access controls for cases

Amazon Connect now enables you to use tag-based access controls to define who can access specific cases. You can associate tags with case templates and configure security profiles to determine which users can access cases with those tags. For example, you can restrict access to fraud-related cases so that only agents in the fraud department can view or edit them.

Amazon Connect now simplifies linking related contacts to cases using flows

Amazon Connect now makes it easier to link related contacts such as email replies, call transfers, persistent chats, and queued callbacks to the same case so agents can view the complete customer journey and resolve issues faster. You can use flows to search for a case associated with a prior contact in the chain to follow-up contacts more easily.

In addition, you can now use flows to link a related contact to a case. For example, when you create a case via a Step-by-Step Guide, you can link that case to the main contact (e.g., voice, chat, email, or tasks) directly using flows.

Recurring overrides and visual calendar for hours of operation

Amazon Connect now makes it easier to manage contact center operating hours for recurring events like holidays, maintenance windows, and promotional periods, with a visual calendar that provides at-a-glance visibility by day, month, or year. You can set up recurring overrides that automatically take effect weekly, monthly, or every other Friday, and use them to provide customers with personalized experiences, all without having to manually revisit configurations. For example, every January 1st you can automatically greet customers with "Happy New Year!" and route them to a special holiday message before checking if agents are available, then on January 2nd your contact center automatically returns to normal operations.

For more information, see Set overrides for extended, reduced, and holiday hours.

Cases now supports AWS CloudFormation

Amazon Connect Cases now supports AWS CloudFormation, enabling you to model, provision, and manage case resources as infrastructure as code. With this launch, administrators can create CloudFormation templates to programmatically deploy and update their Cases configuration—such as templates, fields, and layouts—across Amazon Connect instances, reducing manual setup time and minimizing configuration errors.

For more information, see documentation.

Agent screen recording status tracking

Amazon Connect now offers customers the ability to view status of agent screen recordings in near real time in CloudWatch using Amazon EventBridge. With screen recording, supervisors can identify areas for agent coaching (e.g., non-compliance with business processes) by not only listening to customer calls or reviewing chat transcripts, but also watching agents' actions while handling a contact (i.e., a voice call, chat and task). Using Amazon EventBridge, customers can see status of each agent screen recording including success/failure, failure codes with description, installed client version, agent web browser version, agent operating system, screen recording start and end times from CloudWatch.

Customers can start using Amazon Connect screen recording status tracking by subscribing to Screen Recording Status Changed event type in Amazon EventBridge event bus.

For more information, see Set up and review agent screen recordings in Amazon Connect Contact Lens.

Store nested JSON object and looping arrays

Amazon Connect now enables you to store and work with complex data structures in your flows, making it easy to build dynamic automated experiences that use rich information returned from your internal business systems. You can save complete data records, including nested JSON objects and lists, and reference specific elements within them, such as a particular order from a list of orders returned in JSON format.

Additionally, you can automatically loop through lists of items in your customer service flows, moving through each entry in sequence while tracking the current position in the loop. This allows you to easily access item-level details and present relevant information to end-customers. For example, a travel agency can retrieve all of a customer's itineraries in a single request and guide the caller through each booking to review or update their reservations. A bank can similarly walk customers through recent transactions one by one using data retrieved securely from its systems. These capabilities reduce the need for repeated calls to your business systems, simplify workflow design, and make it easier to deliver advanced automated experiences that adapt as your business requirements evolve.

For more information, see Flows in Amazon Connect.

Original source Report a problem

Workspace and data table resources provide business users with greater control over daily operations

Amazon Connect now gives business users greater control over daily contact center operations without requiring technical resources. With new capabilities to 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. 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.

For more information, see Set up workspaces for your admin website users.

Dashboards now support filtering metrics based on custom business dimensions

Amazon Connect dashboards now support filtering metrics based on custom business dimensions such as business divisions, product lines, or customer segments. Using predefined attributes, you can create business dimensions to filter metrics helping you customize the dashboards based on your unique business need. For example, if your queue handles contacts across product lines, you can filter metrics by product line to compare handle times and determine where agents need product training.

For more information, see Dashboards in Amazon Connect for getting contact center performance data.

Automated agent performance evaluations support 5 additional languages

Amazon Connect now automates agent performance evaluations in Portuguese, French, Italian, German, and Spanish using generative AI. Managers define custom evaluation criteria in natural language and receive AI-generated evaluations with justifications in their preferred language. Performance evaluations also supports cross-language evaluation and can complete assessments in English, even when the conversation is in another language. This enables multilingual contact centers to use a standardized evaluation framework across languages.

For more information, see Evaluate agent and self-service interaction performance in Amazon Connect.

Additional details available within real-time metric alerts

Amazon Connect alerts on real-time metrics now provide the specific agents, queues, flows, or routing profiles that exceeded thresholds and triggered the alert. This enables managers to respond faster to customer experience and operational issues by eliminating the need to manually investigate the root cause of the alert. For example, alerts on elevated queue wait times now include the exact queues affected, so managers can reassign agents to those queues. These detailed alerts can be sent through email, tasks, and Amazon EventBridge.

For more information, see Create alerts on real-time metrics in Amazon Connect.

Multiple choice and date questions now possible in evaluation forms

Amazon Connect provides two new evaluation question types to capture deeper insights on human and AI agent performance. Managers can now create questions that allow multiple answer selections, such as the products that the customer was interested in during a sales conversation. Additionally, managers can capture dates for customer and agent actions within evaluation forms. For example, you can record when a customer applied for a loan and when it was approved.

For more information, see Create an evaluation form in Amazon Connect.

WhatsApp channel for Outbound Campaigns

Amazon Connect Outbound Campaigns now supports WhatsApp, expanding on the WhatsApp Business messaging capabilities that already allow customers to contact your agents. You can now engage customers through proactive, automated campaigns on their preferred messaging platform, delivering timely communications such as appointment reminders, payment notifications, order updates, and product recommendations directly through WhatsApp. Setting up WhatsApp campaigns uses the same familiar Amazon Connect interface, where you can define your target audience, choose personalized message templates, schedule delivery times, and apply compliance guardrails, just as you do for SMS, voice, and email campaigns.

Previously, Outbound Campaigns supported SMS, email, and voice channels, while WhatsApp was available only for customers to initiate conversations with your agents. With WhatsApp support in Outbound Campaigns, you can now proactively reach customers through an additional messaging platform while maintaining a unified campaign management experience. You can personalize WhatsApp messages using real-time customer data, track delivery and engagement metrics, and manage communication frequency and timing to ensure compliance. This expansion provides greater flexibility to connect with customers on their preferred platforms while streamlining your omnichannel outreach strategy.

For more information, see Create an outbound campaign in Amazon Connect.

Original source Report a problem

Conditional case field visibility and dependent options

Amazon Connect Cases now supports conditional field visibility and dependent field options, so you can simplify case layouts and ensure agents capture the right information faster. For example, you can show a Return Reason field only when the case involves a return, and limit Issue Type choices to hardware-related options when Issue Category is set to Hardware.
For more information, see Add case field conditions to a case template in Amazon Connect.

October 2025 Updates

Preview dialing mode for outbound campaigns

Outbound campaigns support preview dialing, allowing agents to review customer information before placing calls. Campaign managers can configure review time limits and enable contact removal. New analytics dashboards provide visibility into agent behavior and campaign performance.
For more information, see Set up Amazon Connect outbound campaigns.

Configure thresholds for schedule adherence

You can configure thresholds for schedule adherence, giving you more flexibility in how you track agent performance. You can define thresholds for how early or late agents start or end their shifts, as well as for individual activities. For example, agents can start their shift 5 minutes early and end 10 minutes late, or end their breaks 3 minutes late, without negatively impacting their adherence scores.
You can further customize these thresholds for individual teams. For example, teams that handle contacts with long ha...

Original source Report a problem

Conditional case field visibility and dependent options

Amazon Connect Cases now supports conditional field visibility and dependent field options, so you can simplify case layouts and ensure agents capture the right information faster. For example, you can show a Return Reason field only when the case involves a return, and limit Issue Type choices to hardware-related options when Issue Category is set to Hardware.

For more information, see Add case field conditions to a case template in Amazon Connect.

Custom metrics

Amazon Connect now supports creation of custom metrics, enabling contact center supervisors to analyze tailored performance measurements without requiring technical skills. This feature provides a simple, no-code interface for performing mathematical operations (e.g., addition, subtraction, sum, average) on existing Connect data to build metrics that align with your organization's specific business requirements. Custom metrics are available to use in the dashboards and APIs.

For more information, see Custom metric primitives.

Native testing and simulation capabilities

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 issuesWith 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.

For more information, see Amazon Connect call simulation.

New criteria to automatically select relevant contacts for performance evaluation

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.

For more information, see Evaluate agent and self-service interaction performance in Amazon Connect.

Support for third-party speech-to-text and text-to-speech AI models for end-customer self-service

Amazon Connect now supports third-party speech providers for end-customer self-service, giving you greater flexibility in how you deliver voice experiences. You can integrate Deepgram for speech-to-text and ElevenLabs for text-to-speech directly within Amazon Connect, using them together with Amazon Connect's native speech capabilities, built-in orchestration, analytics, and compliance controls. This feature is available with Amazon Connect unlimited AI and in all commercial AWS regions where Amazon Connect is offered.

For more information, see Configure third-party speech-to-text (STT) providers.

Enhanced agent assistance capabilities

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.

For more information, see Create AI agents in Amazon Connect.

Granular access controls for performance evaluations

Amazon Connect now enables businesses to restrict access to specific performance evaluation forms, preventing unauthorized access to evaluation form templates and completed evaluations. Businesses can provide managers access to modify or use only the evaluation form templates that are relevant to their business line or function, improving security and making it easier for managers to select the right form while completing evaluations. Additionally, both managers and agents can be restricted from viewing certain completed evaluations. For example, you can restrict agents from viewing test evaluations filled with a form template that is yet to be finalized.

For more information, see Assign security profile permissions for users to create and access evaluation forms.

Simplified linking of related contacts to cases using flows

Amazon Connect now makes it easier to link related contacts such as email replies, call transfers, persistent chats, and queued callbacks to the same case so agents can view the complete customer journey and resolve issues faster. You can use flows to link a follow-up contact to an existing case, eliminating the need for custom logic or manual linking.

For more information, see Flow block in Amazon Connect: Cases.

Chat now supports agent-initiated workflows

Amazon Connect now supports agent-initiated workflows, enabling agents to send interactive forms to collect sensitive data or share general policies and disclosures within customer chat conversations, increasing efficiency and improving customer experience. For example, when a customer needs to update their address, agents can now send a form that customers complete without leaving the chat interface.Agents can trigger these workflows at any point during a chat conversation, making interactions more dynamic and responsive to customer needs. By handling everything within the ongoing chat conversation, businesses can maintain security and compliance standards while helping customers get faster solutions.

For more information, see Enable agent-initated flows during active chat sessions.

Agentic self-service with more natural, expressive, and adaptive voice interactions

Amazon Connect is introducing agentic self-service capabilities that enable AI agents to understand, reason, and take action across voice and messaging channels to automate routine and complex customer service tasks. Connect enables you to blend deterministic and agentic experiences, allowing you to deploy these AI agents at scale, reliably and safely. With integration with advanced speech models from Amazon Nova Sonic, voice self-service experiences now deliver more natural and adaptive interactions. Connect's self-service voice AI agents understand not only what customers say but how they say it, adapting voice responses to match customer tone and sentiment while maintaining natural conversational pace across multiple languages and accents. For example, when a customer calls about an order issue, your AI agent can greet them by name, ask clarifying questions, look up their order status, and process a refund, with voice interactions that adapt to the customer's tone and respond expressively throughout the conversation. This enables your contact center to automate complex troubleshooting, account management, and consultative interactions while maintaining the ability to escalate to a live representative at any point.Nova Sonic support with Amazon Connect is available in two commercial AWS Regions: US East (N. Virginia) and US West (Oregon) and fully available in English and Spanish and in preview for French, Italian, and German.

For more information, see this blog post.

Chat now supports in-flight data redaction and message processing

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.

For more information, see Enable in-flight sensitive data redaction and message processing.

Automated email responses using conditional keywords and phrases

Amazon Connect now allows you to automate email responses and agent routing logic using keyword and phrase conditions, helping organizations increase self-service, reduce manual handling time, and improve routing accuracy. For example, if a customer sends an email asking if a certain product is in stock, or is checking on their shipment status, an automated response can be sent without involving an agent.To enable this feature, add the Get stored content block to your flows and use accompanying flow blocks such as Check contact attributes and Send message to configure automated email responses and routing.

For more information, see How Amazon Connect email works.

AI agent assistance and summarization for Agentforce Service

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.

Support for multiple knowledge bases and integrates with your Amazon Bedrock Knowledge Bases

Amazon Connect now allows you to bring your own Amazon Bedrock Knowledge Bases and supports multiple knowledge bases per AI agent, giving you greater flexibility in how you organize and access knowledge content for your AI agents. You can now connect your existing Bedrock Knowledge Bases directly to Amazon Connect AI agents in just a few clicks, with no additional setup or data duplication required. This allows you to leverage your current data sources and the Amazon Bedrock Knowledge Base connectors, including Adobe Experience Manager, Confluence, SharePoint, and OneDrive, giving you flexibility to use existing content repositories.With support for multiple knowledge bases per AI agent, you can configure AI agents to query multiple sources in parallel for more comprehensive responses. For example, a financial services company can easily connect separate knowledge bases for compliance documentation, product information, and internal policies, enabling AI agents to provide complete guidance across all relevant content during customer interactions.This feature is available in all AWS Regions where Amazon Connect AI agents and Amazon Bedrock Knowledge Bases are offered.

For more information, see Amazon Bedrock Knowledge Base configuration.

Stream messages for AI-powered interactions

Amazon Connect now supports message streaming for AI-powered chat interactions. This new capability shows Connect AI agent responses as they're being generated, which reduces perceived wait times and improves the customer experience.When using Amazon Connect AI agents, customers see status updates like "One moment while I review your account" during processing, and watch responses appear progressively. This experience gives customers confidence their request is actively being worked on while AI agents reason, invoke tools, and craft comprehensive solutions.

For more information, see Enable message streaming for AI-powered chat.

Model Context Protocol (MCP) support

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 more information, see this blog.

Agent workspace now supports custom visual themes

Amazon Connect now allows you to customize the visual appearance of the agent workspace. You can apply a custom theme, including a logo, font, and color palette for light and dark modes, so the agent workspace aligns with the brand identity of your company or business unit.Contact center agents spend hours each day in the Amazon Connect agent workspace, which provides them with all of the customer information, applications, and step-by-step guidance they need to deliver superior customer experiences. With today’s launch, organizations can change the default Amazon Connect theme to their own branded experience, creating a more familiar and intuitive experience for agents who use the agent workspace and other company applications. The agent workspace also has a new header bar where agents can easily access their settings, including their preference of light and dark mode, contributing to greater agent satisfaction and efficiency.

For more information, see Customize the Amazon Connect agent workspace.

AI-powered case summaries

Amazon Connect now provides AI-powered case summaries that give agents complete context into customer issues, reduce manual wrap-up work, and help resolve cases faster. With a single click, agents can generate a concise case summary even when the case spans multiple interactions, follow-up tasks, and teams, capturing key details such as issue background, actions taken, and next steps. Administrators can configure custom prompts and guardrails to ensure that summaries align with organizational style and preferences.

For more information, see Amazon Connect Cases.

Outbound Campaigns now supports multi-step, multi-channel customer engagement journey builder

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.

For more information, see Set up Amazon Connect outbound campaigns.

Automated performance evaluations for self-service interactions

Amazon Connect now provides businesses with the ability to automatically evaluate the quality of self-service interactions and get aggregated insights to improve customer experience. Managers can define custom criteria to assess the quality of self-service interactions, that can be filled manually or automatically using insights from conversational analytics, and other Connect data. For example, you can automatically assess if the AI agent repeatedly fails to understand the customer, resulting in poor customer sentiment and transfer to a human agent. Managers can review these insights in aggregate and on individual contacts, alongside self-service interaction recordings and transcripts, to identify opportunities to improve AI agent performance.Manually filled evaluations of self-service interactions are available in all regions where Amazon Connect is offered. Automated evaluations of self-service interactions are available in the following AWS regions: US East (N. Virginia), US West (Oregon), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), and Europe (Frankfurt).

For more information, see Evaluate agent and self-service interaction performance in Amazon Connect.

Improved analytics and monitoring for AI agents

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.

For more information, see Dashboards in Amazon Connect for getting contact center performance data.

Business users can create custom UIs to adjust contact center configurations in real time

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.

For more information, see Set up workspaces for your admin website users.

Lex now supports LLMs as the primary option for natural language understanding

Amazon Lex now allows you to use Large Language Models (LLMs) as the primary option to understand customer intent across voice and chat interactions. With this capability, your voice and chat bots can better understand customer requests, handle complex utterances, maintain accuracy despite spelling errors, and extract key information from verbose inputs. When customer intent is unclear, bots can intelligently ask follow-up questions to fulfill requests accurately. For example, when a customer says “I need help with my flight,” the LLM automatically clarifies whether the customer wants to check their flight status, upgrade their flight, or change their flight.

For more information, see Amazon Lex documentation.

Flow modules now support custom inputs, outputs, and version management

Amazon Connect flow modules now support custom inputs, outputs, and branches, along with version and alias management. With this launch, you can now define flexible parameters for your reusable flow modules to math your specific business logic. For example, you can create an authentication module that accepts a phone number and PIN as inputs, then returns the customer name and authentication status as outputs with branches such as "authenticated" or "not authenticated". All parameters are customizable to meet your specific needs.Additionally, advanced versioning and aliasing capabilities allow you to manage module updates more seamlessly. You can create immutable version snapshots and map aliases to specific versions. When you update an alias to point to a new version, all flows using that module automatically reference the updated version. These new features make flow modules more powerful and reusable, allowing you to build and maintain flows more efficiently.

For more information, see Flow modules for reusable functions in Amazon Connect.

Agents can send follow-up replies to email contacts

Amazon Connect now allows agents to send follow-up replies to email contacts, making it easier to share additional information or continue assisting customers without starting a new thread. This capability preserves the full conversation history, helping agents maintain context and deliver consistent, seamless support.

For more information, see Set up email in Amazon Connect.

Monitor contacts queued for callback

Amazon Connect now provides you with the ability to monitor which contacts are queued for callback. This feature enables you to search for contacts queued for callback and view additional details such as the customer’s phone number and duration of being queued within the Connect UI and APIs. You can now pro-actively route contacts to agents that are at risk of exceeding the callback timelines communicated to customers. Businesses can also identify customers that have already successfully connected with agents, and clear them from the callback queue to remove duplicative work.

For more information, see Search for in-progress contacts in Amazon Connect.

Amazon Lex extends wait & continue feature in 10 new languages

Amazon Lex now supports wait & continue functionality in 10 new languages, enabling more natural conversational experiences in Chinese, Japanese, Korean, Cantonese, Spanish, French, Italian, Portuguese, Catalan, and German. This feature allows deterministic voice and chat bots to pause while customers gather additional information, then seamlessly resume when ready. For example, when asked for payment details, customers can say "hold on a second" to retrieve their credit card, and the bot will wait before continuing.

For more information, see Lex documentation.

Multi skill agent scheduling

Amazon Connect now enables you to optimize scheduling based on agent’s multiple specialized skills. You can now maximize agent utilization across multiple dimensions such as departments, languages, and customer tiers by intelligently matching agents with multiple skills to forecasted demand. You can now also preserve multi-skilled agents for high-value interactions when needed most. For example, bilingual agents can now be strategically scheduled to cover peak periods for high-value French language queues that frequently experience staffing shortages, while handling general inquiries during off-peak times.

For more information, see Scheduling in Amazon Connect.

Persistent agent connections for faster call handling

Amazon Connect now offers the ability to maintain an open communication channel between your agents and Amazon Connect, helping reduce the time it takes to establish a connection with a customer. Contact center administrators can configure an agent’s user profile to maintain a persistent connection after a conversation ends, allowing for subsequent calls to connect faster. Amazon Connect persistent agent connection makes it easier to support compliance requirements with telemarketing laws such as the U.S. Telephone Consumer Protection Act (TCPA) for outbound campaigns’ calling by reducing the time it takes for a customer to connect with your agents.

For more information, see Enable persistent connection for Amazon Connect agents.

Conversational analytics for voice and chat bots

Amazon Connect now provides conversational analytics for end-customer self-service interactions across voice and digital channels, helping you better understand and improve your customers' self-service experiences. This includes across PSTN/telephony, in-app and web-calling, web and mobile chat, SMS, WhatsApp Business messaging, and Apple Messages for Business.With this launch, Connect now provides rich conversational analytics across both human-agent interactions and end-customer self-service interactions. You can now automatically analyze the quality of automated self-service interactions including customer sentiment, redact sensitive data, discover top contact drivers and themes, identify compliance risks, and proactively identify areas for improvement through easy-to-customize dashboards. Connect’s conversational analytics also enables you to use semantic matching rules to categorize interactions based on customer behavior, keywords, sentiment, or issue types, such as billing inquiries or agent escalation requests.

For more information, see Enable persistent connection for Amazon Connect agents.

Outbound campaigns supports ring time configuration for unanswered calls

Amazon Connect outbound campaigns now offers campaign managers the ability to configure how long voice calls should ring—between a range of 15 and 60 seconds—before marking a call as “no answer” and moving to the next contact. Each contact also records when ringing began and ended for precise reporting and traceability.When ring duration is static, businesses struggle to balance calling efficiency and customer reach. Calls that ring too briefly may miss customers who take longer to answer, while excessive ring times delay overall campaign pacing. This lack of control leads to inconsistent contact rates and reduced agent productivity.With configurable ring time, campaign managers can tune dialing behavior to their audience for each campaign, use analytics to see exactly how long each call rang, and understand where connections were missed. This visibility helps identify patterns, refine calling strategies, and continuously improve campaign effectiveness.

For more information, see Set up Amazon Connect outbound campaigns.

Metrics on completion of agent performance evaluations by managers

Amazon Connect now provides metrics that measure completion of agent performance evaluations, improving manager productivity and evaluation consistency. Businesses can monitor if the required number of evaluations for their agents have been completed, ensuring compliance with internal policies (e.g., complete 5 evaluations per agent per month), regulatory requirements, and labor union agreements. Additionally, businesses can analyze evaluation scoring patterns across different managers, to identify opportunities to improve evaluation consistency and accuracy. These insights are available in real-time through analytics dashboards in the Connect UI, and APIs.

For more information, see Evaluate agent and self-service interaction performance in Amazon Connect.

Configuration of email address aliases

Amazon Connect now lets you configure aliases for email addresses, so customers see trusted identities when sending or receiving messages, helping maintain a consistent brand experience and simplify email management. For example, when forwarding a customer-facing address such as [email protected] to an address in Amazon Connect, you can configure an alias to ensure customers continue to see [email protected] as the sender.

For more information, see Create email addresses.

Original source Report a problem

Release notes

• Conditional case field visibility and dependent options simplify case layouts and ensure agents capture the right information faster.
• Custom metrics creation enables supervisors to analyze tailored performance measurements without technical skills.
• Native testing and simulation capabilities allow easy validation of contact center experiences with configurable test parameters and detailed logs.
• New criteria automatically select relevant contacts for performance evaluation.
• Support for third-party speech-to-text and text-to-speech AI models for end-customer self-service.
• Enhanced agent assistance capabilities provide AI agents that guide representatives through customer interactions.
• Granular access controls restrict access to specific performance evaluation forms and completed evaluations.
• Simplified linking of related contacts to cases using flows.
• Chat supports agent-initiated workflows to send interactive forms during conversations.
• Agentic self-service with natural, expressive, and adaptive voice interactions using advanced speech models.
• Chat supports in-flight data redaction and message processing for compliance.
• Automated email responses using conditional keywords and phrases.
• AI agent assistance and summarization for Salesforce Contact Center with Amazon Connect.
• Support for multiple knowledge bases and integration with Amazon Bedrock Knowledge Bases.
• Stream messages for AI-powered interactions show responses as they are generated.
• Model Context Protocol (MCP) support enables AI agents to use standardized tools for information retrieval and actions.
• Agent workspace supports custom visual themes.
• AI-powered case summaries provide complete context and reduce manual wrap-up.
• Outbound Campaigns support multi-step, multi-channel customer engagement journey builder.
• Automated performance evaluations for self-service interactions provide aggregated insights.
• Improved analytics and monitoring for AI agents with customizable dashboards and automated actions.
• Business users can create custom UIs to adjust contact center configurations in real time.
• Lex supports Large Language Models (LLMs) as the primary option for natural language understanding.
• Flow modules support custom inputs, outputs, and version management.
• Agents can send follow-up replies to email contacts.
• Monitor contacts queued for callback with additional details.
• Amazon Lex extends wait & continue feature in 10 new languages.
• Multi skill agent scheduling optimizes scheduling based on multiple specialized skills.
• Persistent agent connections reduce call handling time.
• Conversational analytics for voice and chat bots provide insights across channels.
• Outbound campaigns support ring time configuration for unanswered calls.
• Metrics on completion of agent performance evaluations by managers.
• Configuration of email address aliases.
• For more information, see the respective Amazon Connect documentation links.

Original source Report a problem

Preview dialing mode for outbound campaigns

Outbound campaigns support preview dialing, allowing agents to review customer information before placing calls. Campaign managers can configure review time limits and enable contact removal. New analytics dashboards provide visibility into agent behavior and campaign performance.

For more information, see Set up Amazon Connect outbound campaigns.

Configure thresholds for schedule adherence

You can configure thresholds for schedule adherence, giving you more flexibility in how you track agent performance. You can define thresholds for how early or late agents start or end their shifts, as well as for individual activities. For example, agents can start their shift 5 minutes early and end 10 minutes late, or end their breaks 3 minutes late, without negatively impacting their adherence scores.

You can further customize these thresholds for individual teams. For example, teams that handle contacts with long handle times can be given more flexibility in when they start their breaks. This enables you to focus on true adherence violations and eliminates the impact of minor schedule deviations on agent performance.

For more information, see Schedule Adherence.

Use granular permissions for conversation recordings and transcripts

You can use granular permissions to manage access to conversation recordings and transcripts in the Amazon Connect admin website. You can separately configure access to recordings and transcripts, allowing users to listen to calls while preventing unauthorized copying of transcripts. Amazon Connect provides flexible download controls, enabling users to download redacted recordings while restricting downloads of unredacted versions.

For more information, see List of security profile permissions.

Set up agent schedule adherence notifications

You can set up agent schedule adherence notifications to make it easier for you to proactively identify when agents aren't adhering to their scheduled activities. You can define rules to automatically send email or text notifications (using EventBridge) to supervisors when agents exceed adherence thresholds. For example, if agent adherence drops below 85% in a trailing 15-minute window, supervisors can receive an email alert.

For more information, see Set up schedule adherence notifications.

Search for related items across all cases within a domain

You can use the SearchAllRelatedItems API to search for related items across all cases within a domain. This is a global search operation that returns related items from multiple cases, unlike the case-specific SearchRelatedItems API.

Generative AI-powered email conversation overviews and suggested responses

Amazon Connect provides agents with generative AI-powered email conversation overviews, suggested actions, and responses. This enables agents to handle emails more efficiently, so customers receive faster, more consistent support.

For example, a customer emails about a refund request. Amazon Connect Connect automatically provides key details about the customer's purchase history on the agent workspace, recommends a refund resolution step-by-step guide, and generates an email response to help resolve the contact quickly.

For more information, see Use generative AI-powered email conversation overviews and suggested responses. Also see the CreateSession API for updates to support this feature, updates to data types such as DataDetails, and new data types such as EmailGenerativeAnswerAIAgentConfiguration.

Amazon Connect makes it easier to get customer input on outbound calls

Amazon Connect supports Get customer input and Store customer input flow blocks for outbound voice whisper flows. The Get customer input block allows a prompt to be played to a customer on an outbound call after they answer the call but before they are connected with an agent, and the customer’s response can be collected through either DTMF input or by using an Amazon Lex bot.

This capability allows you to capture interactive and dynamic customer input on outbound calls before these are connected to an agent. For example, you can use the Get customer input block to obtain customer consent for call recording as part of outbound calls placed by agents, and use it to trigger Amazon Connect Contact Lens recording and analytics.

Original source Report a problem

Dashboards support filtering and comparing metrics by any time range

Amazon Connect dashboards support selecting and comparing any time ranges. This enables you to focus on specific, relevant data and perform in-depth analysis up to a maximum of 35 days in the last 3 months. Additionally, you can select Week to Date and Month to Date time ranges.
For example, if a new sales campaign launches at the start of the current week, a contact center manager can compare the current week's handle time or contact volume with the same time range last week using Week to Date, to decide if additional agents are required to handle the increasing contact volume and maintain service levels.
For more information, see Dashboards in Amazon Connect for getting contact center performance data.

Added two APIs: AssociateContactWithUser and ListRoutingProfileManualAssignmentQueues

Use these APIs to programmatically assign queued contacts to available users and list the manual assignment queues associated with a routing profile: AssociateContactWithUser and ListRoutingProfileManualAssignmentQueues.
These APIs support the functionality described in Access the Worklist app in the Amazon Connect agent workspace.

Customize service level calculations

You can customize service level calculations to your specific needs by selecting if callbacks, abandons, or transfers are included in service level calculations. You can define time thresholds for when a contact is considered to meet service level standards and select which contact outcomes to include in the calculation.
For example, managers can choose to count callback contacts, exclude contacts transferred out while waiting in queue, and exclude short abandons using a configurable time threshold. This enables them to create a service level metric calculation that better aligns with their business operations.
For more information, see Create custom calculations of service level metrics.

Amazon Connect Contact Lens sensitive data redaction in 7 additional languages

Amazon Connect Contact Lens provides sensitive data redaction from voice and chat conversational analytics in French (France, Canada), Portuguese (Portugal, Brazil), Italian, German, and Spanish (Spain).
For more information, see AI features.

Flow designer analytics mode

You can use analytics in the drag-and-drop flows designer. This enables you to make data-driven decisions when optimizing your flows. You can view aggregate traffic through each completed and in-progress step in the flow, allowing you to identify behavioral patterns of your customers or pinpoint where errors are being encountered. For more information, see Monitor flow performance.

New callback metrics

Added the following metric definitions:

• Average queue abandon time - customer first callback
• Average queue answer time - customer first callback
• Average speed of answer - customer first callback dialed
• Average wait time after customer connection - customer first callback
• Callback attempts - customer first callback
• Contact volume - agent first callback
• Contact volume - customer first callback
• Contacts abandoned - customer first callback
• Contacts handled - customer first callback

Use contact segment attributes

For scenarios where information for a contact varies between transfers or multi-party conferences—such as business unit name, account type, or contact reason—you can use contact segment attributes. Contact segment attributes enable you to centrally manage the information with predetermined values and apply it to a unique contact record. This approach preserves accurate business context throughout customer journeys. It helps minimize data inconsistencies by enforcing standardized attribute values, and ensures reporting and analytics always reflect the true customer journey. For more information, see Contacts, contact chains, and contact attributes and Use contact segment attributes.

New detailed disconnect reasons for improved call troubleshooting

Amazon Connect offers expanded disconnect reasons to help you better understand why outbound calls failed to connect in your contact center. These enhanced reasons are based on standard telecom error codes that provide deeper call insights and enable faster troubleshooting. For more information, see DisconnectReason under ContactTraceRecord.

Use agent hierarchy filters to search for contacts

You can search for contacts by using agent hierarchy filters on the Contact search page in the Amazon Connect admin website. You can drill-down into your hierarchy to review contacts handled by specific contact center sites, departments or teams, for assessing contact quality or agent performance.
This functionality enables centralized teams within contact centers, such as quality management and regulatory compliance, to efficiently locate and review contacts handled by specific teams or departments. This streamlines their workflow for performance evaluation and compliance auditing. For more information see Search for completed and in-progress contacts in Amazon Connect.

Manual work item assignment for agents

Agents can manually prioritize the next important task, email, or chat in a queue. For example, when a customer calls in to enquire about their previously submitted refund request, an agent can search for any pending tickets related to the case, assign it to themselves, and resolve it immediately.
Supervisors and managers can enable manual assignment by updating agent configuration in routing and security profiles. Agents can then use the new worklist application in their agent workspace to manually assign themselves the next important chat, task, or email. For more information, see Access the Worklist app in the Amazon Connect agent workspace.

Original source Report a problem

Contact Lens with external voice expanded to additional AWS Regions

Contact Lens with external voice is now supported in Asia Pacific (Tokyo), Asia Pacific (Sydney), Canada (Central), Europe (Frankfurt), and Europe (London). For more information, see Integrate Amazon Connect Contact Lens with external voice systems and Conversational analytics availability by Region.

Multi-user web, in-app, and video calling

Amazon Connect supports multi-user web, in-app, and video calling, allowing multiple users to join the same session with an agent through a web browser or mobile application. Contact center customers and agents can dynamically add participants during a live call or multiple participants can join a scheduled session with the same agent. Participants can engage in audio, video, and screen sharing for a fully collaborative experience. For more information, see Enable multi-user in-app, web, and video calling.

Recurring activities in agent schedules

Amazon Connect supports recurring activities in agent schedules, allowing you to add repeating events in a few clicks. You can schedule activities such as daily stand-up at 8 a.m. or team meeting every Monday at 9 a.m. as a series that automatically gets added to agent schedules. These can be scheduled as individual recurring series for each agent or a shared recurring series across multiple agents. For more information, see Forecasting, capacity planning, and scheduling in Amazon Connect.

Amazon Connect communications widget supports task and email forms for websites and applications

Amazon Connect provides out-of-the-box embedding of tasks and emails into your websites and applications using the contact form option in the communications widget. You can add the communications widget to your website to enable customers to submit callback requests outside business hours or send emails through webforms.
The feature includes these capabilities:

• Configure customer-facing forms using the drag and drop editor
• Generate code snippets for seamless website integration
• Provide customers with flexible engagement options
• Manage all engagements through existing Amazon Connect workflows
  For more information, see Add the Amazon Connect widget to your website to accept chat, task, email, and web calling contacts.

Amazon Connect Outbound Campaigns supports multi-profile campaigns and enhanced phone number retry sequencing

Amazon Connect Outbound Campaigns supports account-based campaigns, enabling you to reach multiple people associated with the same account. For example, when calling about a joint bank account, if the first person is unavailable, the system automatically tries to reach other authorized members of the account.
The feature includes these enhancements:

• Target multiple profiles within the same campaign for outreach to all associated contacts in an account
• Define prioritized contact sequences across multiple phone numbers (mobile, home, work)
• Configure fallback phone numbers within each profile
• Automatically progress to next preferred phone number after unsuccessful attempts
• Create more flexible engagement workflows to improve right-party contact rates
  This feature is available in all AWS Regions where Amazon Connect Outbound Campaigns is supported. For more information, see Outbound Campaigns.

Use the GetContactMetrics API to retrieve real-time position in queue

You can use the GetContactMetrics API and the Position in queue metric to retrieve real-time position in queue data. (This functionality is not available in flows, only by using the API.) This enhancement provides contact centers with a way to manage customer wait times more effectively by:

• Retrieving accurate queue position for each contact
• Offering proactive callbacks during long wait periods
• Making data-driven decisions between primary and alternative queues
• Monitoring queues with routing criteria and agent proficiencies
• Optimizing agent resource allocation through improved queue visibility
  For more information, see the GetContactMetrics API documentation and the Position in queue metric definition.

Original source Report a problem