Keeping up with all of the new features that are constantly being released within the AWS ecosystem is next to impossible. However, keeping up with all of the Amazon announcements that affect just Amazon Connect is much more doable. That’s why we’ve rounded up the latest from Connect in the month of July 2020 and provided you with the breakdown of each
Contact Lens is now generally available
Contact Lens for Amazon Connect is a set of machine learning-based analytics capabilities for Amazon Connect. With Contact Lens, contact centers now have the ability to easily access call transcripts, understand customer sentiment and conversation characteristics (such as non-talk time and interruptions), identify customer issues/call drivers, and monitor compliance with company guidelines. Getting started with Contact Lens requires no technical expertise. In just a few clicks, Contact Lens can automatically begin analyzing your calls and help you get insights into the brand perception and customer satisfaction of your organization.
With Contact Lens, you can quickly identify calls containing specific phrases by doing a keyword-based search. This enables users to quickly identify issues, such as delayed shipments or subscription cancellations. You can dive deep into individual contacts by reading through the turn-by-turn call transcript on the Contact Detail Page and avoid spending time listening to the entire call recording. Contact Lens is also introducing a new Issue Detection feature that highlights call drivers for the customer outreach so that you can focus on a particular section of the transcript. On the same Contact Detail Page, there are visual illustrations that include a customer sentiment trend-line and an audio waveform. These visualizations highlighting various conversation characteristics such as interruptions, loudness, sentiment, and non-talk time are also important indicators of any issues and offer a quick starting point for a further deep dive.
Contact Lens can also automatically detect and redact sensitive information (such as name, address, credit card information, and social security number) from the call transcript and the audio recording. When recording and analyzing calls, businesses can protect sensitive customer information by controlling access to the redacted and unredacted data through user-defined permission groups. The new Rules page in Amazon Connect offers the ability to automatically categorize calls of interest based on specified keywords/phrases. For example, you can use this feature to track all calls where a customer mentioned any of your competitors. All Contact Lens outputs (such as the call transcript, sentiment scores, issues/call drivers, interruptions, talk speed, and contact category labels) are available in your Amazon Simple Storage Service (Amazon S3) bucket in the JSON format.
With Contact Lens for Amazon Connect, you only pay for what you use based on the number of call minutes. There are no required up-front payments, long-term commitments or minimum monthly fees. Please visit the Contact Lens pricing page for more details.
Contact Lens is available in the US West (Oregon), US East (N. Virginia), Europe (London), Europe (Frankfurt), Asia Pacific (Singapore), Asia Pacific (Tokyo), and Asia Pacific (Sydney) regions. Click here for the press release and here for the launch announcement video
Call Recording API's
Amazon Connect now provides four new APIs that enable you to start, stop, pause, and resume call recording. Using the new APIs, you can control recording with a button from your custom agent user interface, build integrations to set recording behavior based on telephony attributes (e.g., area code), or pause and resume recording based on programmatic triggers. For example, when interacting with a CRM application, you can automatically pause call recording when an agent tabs into a field that accepts sensitive customer information, such as a credit card number. You can also provide agents the ability to manually turn on or off call recording to comply with regulations that require customer consent.
Salesforce Service Cloud Voice integration
On July 21st Salesforce announced the general availability of Salesforce Service Cloud Voice with Amazon Connect. Service Cloud Voice brings together phone, digital channels, and CRM data into one unified contact center experience. Amazon Connect offers pre-integrated cloud telephony and automatic speech recognition for both agents and supervisors in Service Cloud, the leading customer service platform.
Amazon Connect has natural text-to-speech built-in so you can create personalized messages in real-time with Amazon Lex to automate interactions and improve customer service. Agents now have native, embedded call control with integrated email, chat, and messaging within the Service Cloud Console. This increases agent productivity by handling calls quickly and intelligently, reducing average handle time, data entry, and call wrap-up time. Supervisors can view incoming and current calls next to digital conversations in real time for live routing and call assist.
Supervisors and agents will have access to real-time transcription via Amazon Transcribe, call recording playback via Amazon Simple Storage Service (Amazon S3), and CRM integration with call analytics. Service Cloud Voice uses AWS AI/ML Services and Einstein for Service, allowing agents to leverage knowledge articles, next best actions, and recommendations in real time. Now, customers will receive faster, more personalized customer service than ever!
To learn more on using Amazon Connect with Service Cloud Voice, visit the Salesforce Service Cloud Voice website.
Speaking styles with neural text-to-speech voices
You can now adapt Amazon Polly’s Text-to-Speech (TTS) voices to the context of your customer conversation. For example, the TTS voice Matthew can be adapted to be more relatable for a welcome prompt and take on a formal persona when informing customers of their bank balance. These speaking styles allow businesses to design more engaging and relatable interactions. The Conversational and Newscaster speaking styles are currently available with the Joanna and Matthew voices.
This feature is available in the US East (N. Virginia), US West (Oregon), and Asia Pacific (Sydney) regions and is included in the Amazon Connect service. There is no additional charge for using neural Text-to-Speech voices. To learn more, see the help documentation, or visit the Amazon Connect website