Search the Community

Amazon Connect forecasting, capacity planning, and scheduling are now generally available in Europe (Frankfurt), Asia Pacific (Singapore), Asia Pacific (Tokyo), and Asia Pacific (Seoul) AWS regions. These capabilities help you predict, allocate, and verify that the right number of agents are scheduled at the right time to meet your operational goals. Machine learning (ML)–powered capabilities allow you to predict contact volume and arrival rates, convert these forecasts into projected staffing needs, and generate shifts for agents. With forecasting, capacity planning, and scheduling, you can optimize your contact center operations, meet service goals, and improve agent and customer satisfaction. View the full article

Amazon Connect Contact Lens now provides generative AI-powered post-contact summaries, which summarize long customer conversations into succinct, coherent, and context rich contact summaries (e.g., “The customer didn’t receive a reimbursement for a last minute flight cancellation and the agent didn’t offer a partial reimbursement as per the SOP”). This helps supervisors improve the customer experience by getting faster insights when reviewing contacts, saving time on quality and compliance reviews, and more quickly identifying opportunities to improve agent performance. View the full article

Amazon Connect Contact Lens now provides businesses with the ability to automatically submit agent performance evaluations. Managers can now evaluate up to 100% of customer interactions, using insights from conversational analytics to automatically fill and submit evaluations, and get aggregations on agent performance across cohorts of agents over time. With this launch, managers can comprehensively monitor and improve regulatory compliance, script adherence (e.g. customer greetings), sensitive data collection, while reducing the time spent on evaluating agent performance. View the full article

The Amazon Connect agent workspace now supports third-party applications in general availability. Agents can use Amazon Connect’s native agent applications (Q in Connect, Cases, Customer Profiles, and Step-by-step Guides) alongside internal or custom-built agent applications, all within a unified agent workspace. For example, when the customer calls about an order, the agent workspace can automatically open a third-party shipment tracking application and display the details of the customer’s order, saving the agent from needing to navigate multiple applications or manually search for information to solve the issue. With support for third-party apps within the agent workspace, customers can reduce agent handle time and data entry errors, leading to improved customer satisfaction. View the full article

If you manage a contact center, then you know the critical role that agents play in helping your organization build customer trust and loyalty. Those of us who’ve reached out to a contact center know how important agents are with guiding through complex decisions and providing fast and accurate solutions where needed. This can take time, and if not done correctly, then it may lead to frustration. Generative AI capabilities in Amazon Connect Today, we’re announcing that the existing artificial intelligence (AI) features of Amazon Connect now have generative AI capabilities that are powered by large language models (LLMs) available through Amazon Bedrock to transform how contact centers provide service to customers. LLMs are pre-trained on vast amounts of data, commonly known as foundation models (FMs), and they can understand and learn, generate text, engage in interactive conversations, answer questions, summarize dialogs and documents, and provide recommendations. Amazon Q in Connect: recommended responses and actions for faster customer support Organizations are in a state of constant change. To maintain a high level of performance that keeps up with these organizational changes, contact centers continuously onboard, train, and coach agents. Even with training and coaching, agents must often search through different sources of information, such as product guides and organization policies, to provide exceptional service to customers. This can increase customer wait times, lowering customer satisfaction and increasing contact center costs. Amazon Q in Connect, a generative AI-powered agent assistant that includes functionality formerly available as Amazon Connect Wisdom, understands customer intents and uses relevant sources of information to deliver accurate responses and actions for the agent to communicate and resolve unique customer needs, all in real-time. Try Amazon Q in Connect for no charge until March 1, 2024. The feature is easy to enable, and you can get started in the Amazon Connect console. Amazon Connect Contact Lens: generative post-contact summarization for increased productivity To improve customer interactions and make sure details are available for future reference, contact center managers rely on the notes that agents manually create after every customer interaction. These notes include details on how a customer issue was addressed, key moments of the conversation, and any pending follow-up items. Amazon Connect Contact Lens now provides generative AI-powered post-contact summarization, and enables contact center managers to more efficiently monitor and help improve contact quality and agent performance. For example, you can use summaries to track commitments made to customers and make sure of the prompt completion of follow-up actions. Moments after a customer interaction, Contact Lens now condenses the conversation into a concise and coherent summary. Amazon Lex in Amazon Connect: assisted slot resolution Using Amazon Lex, you can already build chatbots, virtual agents, and interactive voice response (IVR) which lets your customers schedule an appointment without speaking to a human agent. For example, “I need to change my travel reservation for myself and my two children,” might be difficult for a traditional bot to resolve to a numeric value (how many people are on the travel reservation?). With the new assisted slot resolution feature, Amazon Lex can now resolve slot values in user utterances with great accuracy (for example, providing an answer to the previous question by providing a correct numeric value of three). This is powered by the advanced reasoning capabilities of LLMs which improve accuracy and provide a better customer experience. Learn about all the features of Amazon Lex, including the new generative AI-powered capabilities to help you build better self-service experiences. Amazon Connect Customer Profiles: quicker creation of unified customer profiles for personalized customer experiences Customers expect personalized customer service experiences. To provide this, contact centers need a comprehensive understanding of customers’ preferences, purchases, and interactions. To achieve that, contact center administrators create unified customer profiles by merging customer data from a number of applications. These applications each have different types of customer data stored in varied formats across a range of data stores. Stitching together data from these various data stores needs contact center administrators to understand their data and figure out how to organize and combine it into a unified format. To accomplish this, they spend weeks compiling unified customer profiles. Starting today, Amazon Connect Customer Profiles uses LLMs to shorten the time needed to create unified customer profiles. When contact center administrators add data sources such as Amazon Simple Storage Service (Amazon S3), Adobe Analytics, Salesforce, ServiceNow, and Zendesk, Customer Profiles analyze the data to understand what the data format and content represents and how the data relates to customers’ profiles. Then, Customer Profiles then automatically determines how to organize and combine data from different sources into complete, accurate profiles. With just a few steps, managers can review, make any necessary edits, and complete the setup of customer profiles. In-app, web, and video capabilities in Amazon Connect As an organization, you want to provide great, easy-to-use, and convenient customer service. Earlier in this post I talked about self-service chatbots and how they help you with this. At times customers want to move beyond the chatbot, and beyond an audio conversation with the agent. Amazon Connect now has in-app, web, and video capabilities to help you deliver rich, personalized customer experiences. Using the fully-managed communication widget, and with a few lines of code, you can implement these capabilities on your web and mobile applications. This allows your customers to get support from a web or mobile application without ever having to leave the page. Video can be enabled by either the agent only, by the customer only, or by both agent and customer. Amazon Connect SMS: two-way SMS capabilities Almost everyone owns a mobile device and we love the flexibility of receiving text-based support on-the-go. Contact center leaders know this, and in the past have relied on disconnected, third-party solutions to provide two-way SMS to customers. Amazon Connect now has two-way SMS capabilities to enable contact center leaders to provide this flexibility. This improves customer satisfaction and increases agent productivity without costly integration with third-party solutions. SMS chat can be enabled using the same configuration, Amazon Connect agent workspace, and analytics as calls and chats. Learn more Amazon Q in Connect product page Getting started with Amazon Connect user guide Send feedback AWS re:Post for Amazon Connect, or through your usual AWS support contacts – Veliswa View the full article

Amazon Connect now provides contact records and real-time contact events for calls and transfers made to external third-party phone numbers. These new contact records can be used for reporting, billing reconciliation, and analytics. Contact events for third-party calls can be used to create analytics dashboards to monitor and track real-time contact lifecycle activity (e.g., calls connected to third-party). To learn more about these new contact records and events, and how you can stream them to your analytics applications, see our documentation for contact records and contact events. View the full article

Amazon Connect Chat now supports up to 15 out-of-the-box chat widgets, making it easy for you to customize chat experiences on different websites with just a few clicks. View the full article

Amazon Connect now allows users to access trailing 90 days (previously 35 days) of historical agent and contact metrics (e.g., service level, average handle time) in GetMetricDataV2 API. Additionally, users can now make requests (spanning up to 35 days) with data broken out by customizable time intervals such as 15 minutes, hourly, or weekly. Using GetMetricDataV2 API, business can build custom dashboards to measure historical queue and agent performance. For example, businesses can track the number of incoming contacts for the last 7 days, with data split by day, to see how contact volume changed per day of the week. View the full article

Amazon Connect Contact Lens now provides manager alerts on real-time metrics via email notifications, EventBridge events, or Amazon Connect Tasks. These new alerts enable businesses to notify their managers on unexpected changes in contact center operations that could impact the end-customer experience. With this launch, businesses can now configure alerts that include choosing a metric (e.g., service level), defining a metric threshold (e.g., service level of 90 seconds drops below 75% on a business critical queue), and sending an automated email notification or assigning a task to a manager for follow-up action. View the full article

Amazon Connect now supports AWS CloudFormation for security profiles. You can now use AWS CloudFormation templates to deploy Amazon Connect security profiles —along with the rest of your AWS infrastructure— in a secure, efficient, and repeatable way, allowing you to apply consistent security policies across instances. CloudFormation allows you to track changes over time, apply updates in a controlled and automated manner, and includes version controls so you can easy roll back changes if needed. For more information, see Amazon Connect Resource Type Reference in the AWS CloudFormation User Guide. View the full article

Looks like it is my turn once again to write the AWS Weekly Roundup. I wrote and published the first one on April 16, 2012 — just 4,165 short day ago! Last Week’s Launches Here are some of the launches that caught my eye last week: R7iz Instances – Optimized for high CPU performance and designed for your memory-intensive workloads, these instances are powered by the fastest 4th Generation Intel Xeon Scalable-based (Sapphire Rapids) instances in the cloud. They are available in eight sizes, with 2 to 128 vCPUs and 16 to 1024 GiB of memory, along with generous allocations of network and EBS bandwidth: vCPUs Memory (GiB) Network Bandwidth EBS Bandwidth r7iz.large 2 16 Up to 12.5 Gbps Up to 10 Gbps r7iz.xlarge 4 32 Up to 12.5 Gbps Up to 10 Gbps r7iz.2xlarge 8 64 Up to 12.5 Gbps Up to 10 Gbps r7iz.4xlarge 16 128 Up to 12.5 Gbps Up to 10 Gbps r7iz.8xlarge 32 256 12.5 Gbps 10 Gbps r7iz.12xlarge 48 384 25 Gbps 19 Gbps r7iz.16xlarge 64 512 25 Gbps 20 Gbps r7iz.32xlarge 128 1024 50 Gbps 40 Gbps As Veliswa shared in her post, the R7iz instances also include four built-in accelerators, and are available in two AWS regions. Amazon Connect APIs for View Resources – A new set of View APIs allows you to programmatically create and manage the view resources (UI templates) used in the step-by-step guides that are displayed in the agent’s UI. Daily Disbursements to Marketplace Sellers – Sellers can now set disbursement preferences and opt-in to receiving outstanding balances on a daily basis for increased flexibility, including the ability to match payments to existing accounting processes. Enhanced Error Handling for AWS Step Functions – You can now construct detailed error messages in Step Functions Fail states, and you can set a maximum limit on retry intervals. Amazon CloudWatch Logs RegEx Filtering – You can now use regular expressions in your Amazon CloudWatch Logs filter patterns. You can, for example, define a single filter that matches multiple IP subnets or HTTP status codes instead of having to use multiple filters, as was previously the case. Each filter pattern can have up to two regular expression patterns. Amazon SageMaker – There’s a new (and quick) Studio setup experience, support for Multi Model Endpoints for PyTorch, and the ability to use SageMaker’s geospatial capabilities on GPU-based instances when using Notebooks. X in Y – We launched existing services and instance types in new regions: ROSA in the Europe (Spain) Region. AWS NAT Gateway in the Los Angeles Local Zone us-west-2-lax-1a. Amazon Simple Email Service (SES) email receiving service in the US East (Ohio), Asia Pacific (Singapore, Sydney, Tokyo), Canada (Central), and Europe (Frankfurt, London) Regions. IAM roles last used and last accessed in AWS GovCloud (US) Regions. AWS Security Hub findings consolidation in AWS GovCloud (US) Regions. C6id instances in the Europe (London) Region. Amazon Location Service in the AWS GovCloud (US-West) Region. Amazon Managed Streaming for Apache Kafka and Amazon FSx for NetApp ONTAP, in the Israel (Tel Aviv) Region. M6i and R6i instances in the Europe (Zurich) Region. C6gd and R6gd instances in the AWS GovCloud (US-West) Region. VPC DNS Query Logging in the Asia Pacific (Hyderabad, Melbourne), Europe (Spain, Zurich), and Middle East (UAE) Regions. High Memory instances in the Asia Pacific (Seoul) Region. Other AWS News Here are some other AWS updates and news: AWS Fundamentals – The second edition of this awesome book, AWS for the Real World, Not for Certifications, is now available. In addition to more than 400 pages that cover 16 vital AWS services, each chapter includes a detailed and attractive infographic. Here’s a small-scale sample: More posts from AWS blogs – Here are a few posts from some of the other AWS and cloud blogs that I follow: AWS DevOps Blog – Using AWS CloudFormation and AWS Cloud Development Kit to provision multicloud resources. AWS Big Data Blog – Managing Amazon EBS volume throughput limits in Amazon OpenSearch Service domains. AWS Contact Center Blog – How contact center leaders can prepare for generative AI. AWS Desktop and Application Streaming Blog – Selecting the right AWS End User Computing service for your needs. AWS Containers Blog – Migrate existing Amazon ECS services from an internal Application Load Balancer to Amazon ECS Service Connect. AWS Community Builders – Level up your Lambda Game with Canary Deployments using SST. Cloudonaut – Self-hosted GitHub runners on AWS. Trek10 – How and When to Use Amazon EventBridge Pipes. Upcoming AWS Events Check your calendars and sign up for these AWS events: AWS End User Computing Innovation Day, Sept. 13 – The one-day virtual event is designed to help IT teams tasked with providing the tools employees need to do their jobs, especially in today’s challenging times. Learn more. AWS Global Summits, Sept. 26 – The last in-person AWS Summit will be held in Johannesburg on Sept. 26th. You can also watch on-demand videos of the latest Summit events such as Berlin, Bogotá, Paris, Seoul, Sydney, Tel Aviv, and Washington DC in the AWS YouTube channels. CDK Day, Sept. 29 – A community-led fully virtual event with tracks in English and Spanish about CDK and related projects. Learn more at the website. AWS re:Invent, Nov. 27-Dec. 1 – Ready to start planning your re:Invent? Browse the session catalog now. Join us to hear the latest from AWS, learn from experts, and connect with the global cloud community. AWS Community Days, multiple dates – Join a community-led conference run by AWS user group leaders in your region: Munich (Sept. 14), Argentina (Sept. 16), Spain (Sept. 23), Peru (Sept. 30), and Chile (Sept. 30). Visit the landing page to check out all the upcoming AWS Community Days. You can browse all upcoming AWS-led in-person and virtual events, and developer-focused events such as AWS DevDay. — Jeff; This post is part of our Weekly Roundup series. Check back each week for a quick roundup of interesting news and announcements from AWS! View the full article

Amazon Connect now enables contact center managers to view historical contact volumes and average handling time (AHT) in the forecasting UI. This new feature is part of Amazon Connect forecasting, capacity planning, and scheduling (preview) that helps contact center managers predict contact volumes and AHT, determine optimal staffing levels, and plan agent schedules to ensure they have the right agents at the right time. The ability to view historical contact volumes in the forecasting UI provides a quick way for contact center managers to identify any abnormality within forecasts and actuals. View the full article

Amazon Connect Customer Profiles now provides a JavaScript library (CustomerProfilesJS) to integrate Customer Profiles into your homegrown or third-party agent application, equipping your contact center agents with the customer information they need to provide more personalized customer service. Amazon Connect Customer Profiles makes it easier for you to provide agents with quick access to unified customer data by combining contact history from Amazon Connect with data from disparate third-party applications (e.g., CRMs) and homegrown systems, leveraging machine learning based identity resolution to create a single, unified profile for each of your customers. View the full article

Amazon Connect now allows you to further personalize, the automated self-service customer experience using Amazon Lex intent confidence scores as a branch within your flows. Amazon Lex allows customers to create intelligent chatbots that turn their Amazon Connect flows into natural conversations. By branching flows on Lex confidence scores, you can present the right solutions to your customers to help solve their issues faster. For example, when a confidence score is high you may want to present customers a with a self-service option immediately rather than requesting additional information or transferring them to an agent. This new functionality can be set up using the “Check contact attributes” flow block. View the full article

Amazon Connect now allows you to further personalize the automated, self-service customer experience by leveraging Amazon Lex customer sentiment analysis as a branch within your flows. Amazon Lex allows customers to create intelligent chatbots that turn their Amazon Connect flows into natural conversations. With this launch, you can now build flows based on whether the customer expresses positive or negative utterances to your Lex bot. For example, you may want customers who express positive sentiment to be presented with additional upsell opportunities or you may want customers who express negative sentiment to be put directly in queue to speak with an agent. The new functionality can be setup using the “Get Customer Input” or the “Check contact attributes” flow blocks. In addition, all Lex related attributes (e.g., Intent, Slots, Sentiment) within flow blocks are now consolidated under one “type” within attribute selection to help simplify building your Lex experience within flows. View the full article

Amazon Connect Customer Profiles now allows you to automatically merge duplicate customer records on confidence scores. Each time the identity resolution feature finds duplicate records, it provides a confidence score on a scale of zero to one to represent the accuracy of a match, where a score of one represents most accurate match and zero represents least accurate match. You can select a threshold anywhere between zero to one to automatically merge duplicate records into a unified customer profile. View the full article

Amazon Connect Wisdom now provides a JavaScript library (WisdomJS) to integrate agent assistance capabilities into your homegrown or third-party agent application, enabling you to increase agent productivity and improve customer satisfaction without having to migrate your agents to another application. Amazon Connect Wisdom reduces the time agents spend searching for answers and enables quick resolution of customer issues by providing knowledge search and real-time recommendations while agents talk with customers. View the full article

Amazon Connect Cases provides built-in case management capabilities that make it easy for your contact center agents to create, collaborate on, and quickly resolve customer issues that require multiple customer conversations and follow-up tasks, all without having to build custom applications or integrate with third-party products. Cases provides your agents with a unified timeline view of all activities associated with a customer case, including individual tasks that can be assigned and tracked across multiple agents. Additionally, case information can be used to answer customer questions in self-service IVR and chatbot interactions. View the full article

Amazon Connect outbound campaigns now offers organizations an embedded, cost-effective way to contact up to millions of customers daily for communications such as delivery notifications, marketing promotions, appointment reminders, or debt collection, without having to integrate with third-party tools. With outbound campaigns, formerly known as high-volume outbound communications, you can proactively communicate across voice, SMS, and email to quickly serve your customers and improve agent productivity. The new communication capabilities also include features to support compliance of local regulations such as TCPA through point-of-dial checks and calling controls for time of day, time zone, number of attempts per contact, and time required to connect to an available agent. View the full article

Amazon Connect now provides the ability for customers to schedule historical metric reports that generate the latest data every 15 minutes. Historical metrics reports include data about completed customer contacts, agent activity, and performance, such as how many contacts an agent handled. This helps customers quickly identify insights into queue, routing profile, and agent performance. These insights can be used in a variety of ways, including evaluating and adjusting contact center forecasting and staffing plans. View the full article

Amazon Connect now provides an API to programmatically access real-time details about agents’ current activity, such as current status (e.g., “Available”). If an agent is handling a contact, details include the contact’s state (e.g., “Connected” or “Missed”) and duration. Using this API, businesses can build custom dashboards for contact center supervisors to monitor their agents’ activity in real-time. For example, if more agents are needed to handle contacts, you can use this new API to identify agents who are on break the longest and reach out to them to switch to “Available” or change it programmatically using PutUserStatus. View the full article

Amazon Connect forecasting, capacity planning, and scheduling (preview) are now available in the Asia Pacific (Sydney) AWS region. Machine-learning powered capabilities make it easier for contact center managers to help predict contact volumes and average handle time with high accuracy, determine ideal staffing levels, and optimize agent schedules to ensure they have the right agents at the right time. This helps businesses optimize their operations, meet service level goals, and improve agent and customer satisfaction. Getting started takes just a click, eliminating the need to build custom applications or integrate with third-party products. View the full article

Amazon Connect has reduced telephony costs for North America instances calling Canada by 63% and receiving calls from United Kingdom and Germany up to 60%. View the full article

Amazon Connect has reduced five outbound telephony rates in Asia Pacific, including Australia by 50%. Starting September 1st, Amazon Connect, an easy to use contact center service, decreased the following outbound telephony rates: View the full article

Amazon Connect is announcing 10 telephony rate reductions for customers in Argentina, Chile, Mexico, and Peru from the US East (N. Virginia) and US West (Oregon) regions. View the full article