Amazon Connect Contact Lens

Real-time contact center analytics and quality management powered by artificial intelligence

Essential insights at your fingertips

Amazon Connect Contact Lens provides contact center analytics and quality management capabilities that enables you to monitor, measure, and continuously improve contact quality and agent performance for a better overall customer experience. With analytics that provide a complete view of your customer conversations for both voice and chat, you can automatically transcribe customer calls, analyze customer sentiment, discover top contact drivers, redact sensitive data, and more, all natively within Amazon Connect. Generative AI capabilities automatically create post-contact summaries, freeing up time for agents to assist more customers by eliminating manual note-taking, and facilitating supervisors in understanding customer conversations to ensure the completion of committed follow-up actions. Contact Lens enables agent performance evaluations against defined quality  standards, aided by conversational analytics and screen recording capabilities. Supervisors can perform evaluations assisted by generative AI recommendations, or automatically complete evaluations for 100% of agents’ customer interactions, and get aggregated agent performance to identify coaching opportunities.

Uncover trends and insights from every conversation

Contact Lens uses natural language processing (NLP) and conversational analytics to understand sentiment, conversation characteristics, themes, and agent compliance risks during customer calls and chats. Supervisors can use conversational analytics to verify that standard greetings and sign-offs are used, help train agents, and replicate successful interactions. Set real-time alerts to flag agent coaching opportunities and discover customer insights with detailed analysis in the analytics dashboard. Use real-time data streams to build customized dashboards that include sentence-by-sentence transcripts, sentiment analysis, and categories from customer conversations.

Uncover trends and improve customer service

Automatically summarize conversations in seconds with generative AI

Save valuable time with generative AI-powered post-contact summaries that provide essential information from customer conversations in a structured and easy to read format. Agents can use summaries that are generated within seconds after a call ends, significantly reducing After Contact Work (ACW). Additionally, supervisors can review a synthesized, context-rich summary of customer interactions to quickly understand issues and provide feedback to agents, without having to read through transcripts or monitor calls.

Improve agent productivity and customer service

Enhance contact center security and compliance

Detect and redact sensitive customer data such as credit card details, addresses, and social security numbers from audio recordings and transcripts. You can also improve agent compliance with company policies or regulatory requirements by tracking all customer conversations for script adherence using categorization-based on criteria you determine. For example, you can track words or phrases used in required disclaimers, greetings and sign-offs.

Enhance contact center security and compliance

Use automation and generative AI to evaluate agent performance

Evaluate agent performance alongside contact details, recordings, transcripts, and summaries, without the need to switch applications. Contact Lens with generative AI enables generative AI-powered insights and recommendations to perform evaluations or use conversational analytics to automatically evaluate agent performance on 100% of customer interactions. Automated evaluations enable managers to comprehensively monitor and improve regulatory compliance, script adherence (e.g. customer greetings), and sensitive data collection, while reducing the time spent on evaluating agent performance.

Use evaluation forms to improve agent performance

Analyze agent performance metrics to identify coaching opportunities

Analyze aggregations of agent performance and insights across cohorts of agents over time, and trigger supervisor alerts or follow-up tasks. Results of evaluations are aggregated for each agent, enabling supervisors to drill down on particular areas of performance, such as compliance adherence, or sales effectiveness and compare the performance against organizational benchmarks. You can use public APIs where other aspects of agent performance can be supplemented with data from third-party tools such as agents’ sales results as a component of your evaluation. Additionally, performance evaluation forms and contact categorization identify specific contacts and automatically notify supervisors to do coaching follow-up tasks with agents. 

Use evaluation forms to improve agent performance

Review agent actions handling customer contacts using screen recording

Review and assess agents' interactions with customers, ensuring adherence to quality standards, compliance requirements, and best practices, helping you effectively evaluate agent's performance and identify coaching opportunities. You can also review the recording to identify bottlenecks, inefficiencies, and areas of improvement in your processes in order to streamline workflows, and enhance overall operational efficiency.

Use evaluation forms to improve agent performance

Contact Lens customers

Intuit logo
Origin logo
Accolade logo
University of Auckland
Energy Ogre logo
News Corp logo
Amaysim logo
Ameriflex
See customer stories »

Capabilities

  • Conversational analytics
  • The capabilities listed below are included in conversational analytics pricing. These capabilities are available across voice and chat for both real-time and post-contact use cases. Conversational analytics pricing for voice calls is a per minute charge and for chat messages is a per message charge. To learn more information and see examples on pricing go to Amazon Connect pricing.

    Automated contact categorization

    Track customer conversations for compliance with company policies or regulatory requirements. Define and manage categories directly based on your specific criteria (such as words, phrases, conversational characteristics like sentiment, interruptions, and non-talk time) within Amazon Connect using rules. Rules are an ML-based contact categorization engine that can automatically label contacts for real-time and post-contact scenarios.

    Custom vocabularies

    Improve the accuracy of speech recognition for terminology (such as product names and brand names) by expanding the vocabulary of Contact Lens’ speech-to-text engine. You can provide a list consisting of domain-specific words and phrases, words that aren’t being recognized correctly, and proper nouns.

    Generative AI-powered post-contact summaries

    Streamline and automate post-contact work with generative AI-powered summaries of customer conversations that are structured, concise, and easy to read. These summaries capture important information from customer conversations for both voice and chat, so supervisors can quickly review them, understand context, and follow up with customers or take other necessary actions.

    Key highlights

    Automatically identify key parts of the customer conversation, assign tags (such as issue, outcome or action items) and display highlights of the customer interaction that can be expanded to view the full transcript of the contact.

    Real-time data streams

    Access real-time analytics using data streams to provide issue detection, sentence-by-sentence transcripts, sentiment analysis, and categories for ongoing customer conversations with low latency.

    Sensitive data redaction

    Remove sensitive data (such as names, addresses, credit card details, and social security numbers) from both the call or chat transcripts and audio recordings.

    Sentiment analysis

    Capture and analyze the sentiment of words being spoken by the customer through ML-powered natural language processing (NLP). It will generate a score between -5 (most negative) to +5 (most positive).

    Supervisor alerts on conversational analytics

    Create rules to flag any customer experience issue in real-time, with categories based on keywords, sentiment, and phrase matching. This automatically alerts your supervisors in real time when they need to assist an agent on live contacts so they can provide guidance through chat or have the agent transfer the call.

    Speech transcription

    Automatically transcribe call recordings into text to gain deeper insights into the meaning and context of agent-customer conversation.

    Theme detection

    Discover emerging contact themes from your customer interactions such as "cancel reservation" or "delayed order." Leverage machine learning-powered theme detection to cluster contacts with similar issues together and see the resulting groups within the Amazon Connect interface.
  • Performance evaluation
  • The capabilities listed below are included in performance evaluation pricing. Performance evaluation pricing is charged per agent evaluated. To learn more information and see examples on pricing go to Amazon Connect pricing.

    Automated evaluation

    Perform automated evaluations of agent performance on 100% of customer interactions. Populate responses to evaluation form questions using insights and metrics from conversational analytics. You can receive holistic insights to identify agent coaching opportunities, reduce non-compliance risk, and save time evaluating agent performance.

    Evaluation forms and contact scoring

    Define and create a set of agent performance evaluation forms and complete the evaluations side-by-side with call recordings, transcripts, and conversational analytics outputs such as contact categories, sentiment scores, and issues detected. Get a contact scored based on the evaluation result instantly completed for your review.

    Supervisor alerts on agent performance

    Supervisors get automated notifications whenever agents on their team need additional guidance to improve their performance (e.g., evaluation score) and help meet their contact center’s quality assurance requirements. Use multiple methods to notify supervisors such as Amazon Connect Tasks, email notifications, or EventBridge integrations to third party applications.

    Generative AI-powered performance evaluations (preview) Contact Lens provides generative AI-powered recommendations for answers to evaluation form questions, along with context and justification for the recommended answers. Managers can use natural language to specify the criteria for answering evaluation form questions and receive generative AI-powered recommendations tailored to your contact center.
  • Screen recording
  • Screen recording pricing is charged per recorded minute. To learn more information and see examples on pricing go to Amazon Connect pricing.

    Screen recording

    Enables companies to easily record agents’ screens along with their audio in Amazon Connect, providing managers the ability to not only listen to, but also watch agents’ actions while handling a customer contact (voice call, chat or tasks).

  • Other Contact Lens capabilities
  • The capabilities listed below are included in Amazon Connect pricing. To learn more information and see examples on pricing go to Amazon Connect pricing.

    Call recording

    Access live and recorded conversations for your contact center calls to address use cases such as monitoring agent compliance, evaluating contact quality, and identifying calls for training purposes. These call recordings are stored in an Amazon S3 bucket, which you can consume outside of Amazon Connect. They are also visualized within Amazon Connect on the contact details page.

    Contact details and analytics

    View all conversational analytics at an individual contact level, including transcripts, agent and customer sentiment, contact categories, non-talk time, response time, and other conversation characteristics, to detect issues and customer trends. Contact details also helps you access details such as contact id, agent name, disconnect reason, and start and end time.

    Contact rules

    Automate common and repeatable actions based on pre-defined trigger conditions such as keywords used on a contact, sentiment trend of a contact, agent evaluation score, agents being silent for long-periods on a contact, filtering specific contact attributes, and more.

    Contact search

    Contact search helps you quickly search a few relevant contacts from many contacts across the contact center. You can use filters such as agent name, queue name, ML-enabled conversational analytics (such as specific keywords, categories, and sentiment score), contact attribute, and many more to drill down to those relevant contacts in less time. This helps you understand customer trends and insights and how to improve customer satisfaction.

    Email notification

    Receive real-time email notifications when configurable conditions of a rule (such as customer sentiment) get initiated. This will help you identify and intervene on contacts where agents might need additional support and provide guidance to deliver better end-customer experiences.

    Supervisor barge-in

    Enables supervisors and managers to proactively join calls and take over an active call as needed. After joining, a manager can speak with the customer, add participants, and even choose to remove an agent, if needed.

Page topics

FAQs

FAQs

For more information, see Amazon Connect.

Amazon Connect Contact Lens pricing is designed to be flexible and cost-effective, allowing you to pay for the capabilities you need. Contact Lens offers separate pay-as-you-go pricing for the following capabilities: conversational analytics, performance evaluation, and screen recording. Each of these capabilities has separate pricing terms and you choose which ones to use. You will be billed for each capability you choose to use based on their individual pricing. Conversational analytics capabilities pricing for voice calls is a per minute charge and for chat messages a per message charge, performance evaluation capabilities pricing is charged by per agent evaluated, and screen recording capabilities pricing is charged by per recorded minute. To learn more information and see examples on pricing go to Amazon Connect pricing.

To get started with Amazon Connect Contact Lens, see Enable Amazon Connect Contact Lens. The documentation provides instructions for how to turn on Contact Lens within your Amazon Connect instance.

To view a list of languages Amazon Connect Contact Lens currently supports for post-call analytics, post-call redaction, real-time analytics, and real-time redaction, see Languages supported by Amazon Connect. We will continue to add support for more languages.

After you have set up Contact Lens you can configure your instance for agent performance evaluation by configuring your security profiles, which set permissions for specific users to define, create, or review contact evaluations. Refer to the Administration Guide to learn more.

You can use the evaluation forms for all contacts within your Amazon Connect instance, including conversations over voice calls, chats, and tasks. You can manually evaluate contacts without conversational analytics, or enable conversational analytics to automate the evaluation process and get results pre-populated within the form. We do not support evaluating customer interactions outside of your Amazon Connect instance.

No, while Contact Lens screen recording works seamlessly together with other Contact Lens capabilities, conversational analytics is not required in order to use screen recording.

Contact Lens screen recording supports all native Amazon Connect channels, including Voice, Chat and Tasks.

The redaction feature is designed to identify and remove sensitive data. However, due to the predictive nature of ML, it might not identify and remove all instances of sensitive data in a transcript generated by Amazon Connect Contact Lens. We recommend reviewing the results for accuracy after enabling sensitive data redaction to verify they meet your needs.

The redaction feature is not intended to be used to de-identify healthcare data or to remove references to protected health information.

The metadata generated by Amazon Connect Contact Lens (including call transcript, sentiment analysis, non-talk time, categorization labels, talk speed, and interruptions), along with the call recordings for each contact, will be accessible in your Amazon Simple Storage Service (S3) bucket. This data will be linked to Contact Trace Records (CTR) and can be used in BI tools like Amazon QuickSight and Tableau. You can create custom visualizations that fuse the CTR data with data from other systems (such as CRM). Finally, your analytics teams can also use this data to create custom machine learning (ML) models with Amazon SageMaker.

Contact Lens is an out of the box feature for Amazon Connect that leverages Amazon Transcribe to generate call transcripts and Amazon Comprehend to apply natural language processing (NLP) on these transcripts, with no coding required. This approach helps organizations evaluate their customer experience using Amazon Connect Contact Lens, without requiring expertise in Amazon Transcribe or Amazon Comprehend.

Yes. The real-time capabilities of Contact Lens are available through either the Amazon Connect user interface or a synchronous real-time API that help you to build customized solutions for use cases like agent transfers.

Any content processed by Amazon Connect Contact Lens is encrypted and stored at rest in the AWS Region where you are using Contact Lens. Unless you opt out as provided below, some portion of content processed by Amazon Connect Contact Lens might be stored in another AWS Region. This would solely be with the continual improvement and development of your Amazon Connect Contact Lens experience and other Amazon machine-learning/artificial-intelligence technologies. You can request deletion of content associated with your account by contacting AWS Support. Your trust, privacy, and the security of your content are our highest priority. We implement appropriate and sophisticated technical and physical controls, including encryption at rest and in transit, designed to prevent unauthorized access to, or disclosure of, your content and verify that our use complies with our commitments to you. See Data Privacy FAQ for more information. Your content will not be stored in another AWS Region if you opt out of having your content used to improve and develop the quality of Amazon Connect Contact Lens and other ML and artificial intelligence (AI) services on AWS. You can opt out of having your content used to improve and develop the quality of Amazon Connect Contact Lens and other Amazon machine-learning/artificial-intelligence technologies by using an AWS Organizations opt-out policy. For information about how to opt out, see AI services opt-out policy.

For latest region availability, see Amazon Connect feature availability by region.

Amazon Connect may store and use customer inputs processed by the service to provide and maintain the service and, unless you opt out as provided below, to improve and develop the quality of Amazon Connect and other Amazon machine-learning/artificial-intelligence technologies. We do not use any personally identifiable information that may be contained in your content to target products, services or marketing to you or your end users. Your trust, privacy, and the security of your content are our highest priority and we implement appropriate and sophisticated technical and physical controls, including encryption at rest and in transit, designed to prevent unauthorized access to, or disclosure of, your content and ensure that our use complies with our commitments to you. Please see Data Privacy FAQs for more information. As an AWS customer, you can opt out of having your content stored or used for service improvements. Instead of configuring this setting individually for each AWS account that your organization uses, you can configure an organization policy that enforces your setting choice on all accounts that are members of the organization. You can choose to opt out of content storage and use for an individual AI service, or for all of the covered services at once. You can query the effective policy applicable to each account to see the effects of your setting choices. Opting out applies to all AWS Regions excluding AWS GovCloud (US). Opting out deletes all of the associated historical content. For more information, see AI services opt-out policies.