Building the World's Largest Community of CX Professionals

Learn More
Call center automation

ASAPP Launches AutoSummary Service API to Enable Automatic Call Center Functions

Automated Conversation Summaries and Analytics-Ready Data Input Can Help Agents Be More Productive

  • Share

Beyond interacting and servicing customers, call center agents are typically required to handle the additional tasks of documenting each interaction they have, usually by typing up conversation summary notes, or inputting information via a drop-down menu interface. To provide the most value to the organization, in terms of better serving customers, identifying points of friction, and improving agent training, these summaries should include the reason for the call, the resolution steps that were taken, and the result or next action.

However, due to high volume of calls and the limited time to complete these call summaries before they need to answer a new customer inquiry, agent-completed contact summaries often are inconsistent in the terminology used, inaccurate, or simply too poorly written to quantify what actually occurred.

That’s why ASAPP, Inc. today launched AutoSummary, its new AI Service API that is designed to provide contact centers with automatic conversation summaries and analytics-ready data. Although the machine learning (ML) technology used to generate the summaries is not new, it is the first time ASAPP has offered the service via an application programming interface (API) that can be integrated within any existing technology stack and contact center/customer relationship management (CRM) application or platform.

While many organizations have tried to reduce the load on live agents by deploying more advanced AI bots, smarter interactive voice response (IVR) systems, and other deflection technologies, most companies have had to add agents to handle increased inquiry volume, according to Macario Namie, chief strategy officer with ASAPP.

“The labor that [organizations] spend on agents today equates to typically 80% or more of their budget,” Namie says. Instead of simply using technology to reduce costs, “we believe that we can make the same economic benefit occur by making agents twice as productive.”

Typically, agents are asked to type up summaries either during an interaction, or directly after it occurs, which can eat up anywhere from 1 to 2 minutes of time, per call. Worse, due to the inconsistency with agent-written summaries, Namie says that “very rarely have we seen organizations actually use the data that comes out of these summaries.”

ASAPP’s AutoSummary service allows agents to focus on serving customers, instead of writing summaries. ASAPP’s ML and natural language processing (NLP) models are used to ingest interaction transcripts, and create two different summaries, which are designed to meet the needs of agents, managers, and CX executives.

  • Readable Summary. AutoSummary automatically generates a detailed, paragraph-style summary from the conversation transcript without agents having to type a single word. The free-text summary, typically stored in a case management or CRM system, provides agents the level of detail they need to quickly get up to speed on previous interactions with a customer. 
  • Analytics-Ready Summary. For managers and executives, AutoSummary produces high quality, structured data about the content and outcome of every call, that is architected for Business Intelligence and Analytics systems. This structured data can provide rich insights into how to improve operations, create new revenue generation opportunities, and enhance products.

ASAPP works with customers in advance to gather historical transcripts of interactions, and develops company-specific ontology and taxonomy notes that will be used to analyze and classify calls. The ML model is trained on this data, ensuring that key insights and actions that can be used to improve CX are pulled out in each summary, so it can be used by a variety of end users. As more live transcripts are generated (either via the company’s AutoTranscribe transcription service, or via third-party services), the model will continue to improve.

“We don’t go to market with a generic, one-size-fits-all text-summarization model, because it frankly doesn’t work well,” Namie says. ASAPP typically asks for around 500 to 1,000 transcripts to get initial ML model training completed, though “as is the case with any machine learning, more data is better,” Namie says. He says that as part of the initial work with their customers, ASAPP will monitor and tweak the AI model so that each summary is an accurate reflection of what Namie terms the three “Rs”: the reason for the call, the resolution steps that were taken, and the result or next action to be taken. Says Namie: “That’s how we measure quality.”

In terms of results, Namie says that customers can expect a 9% to 10% reduction in average handle time (AHT), which results in more time for agents to interact with customers, as well as better summaries that can be used to positively impact CX.

Namie adds that while the concept of using NLP and ML to create text summaries of transcripts is not new, ASAPP’s service is unique in that it is specifically designed around the domain of the contact centers, and the broader CX mindset, and is designed to incorporate company-specific ontologies and taxonomies to create data outputs that are useful and actionable.

“The technology needs to be able to summarize what could be a 10, 15, or 20 minute call into three or five sentences that can be read by an agent, a manager, or a supervisor in 10 seconds,” Namie says. “Understanding that ontology or taxonomy for the structured data is vitally important, and needs to be unique and specific to that company, or it doesn’t have any value.”

Latest Research

Customer Insights & Feedback

Market Drivers and Barriers, Key Industry Players, Market Sizing and Forecasts, and Case Studies

omnichannel customer engagement

Omnichannel Customer Engagement

Case Studies, Market Drivers, Market Barriers, and Best Practices for the Adoption of Omnichannel Engagement Strategies and Software

CX for contact centers

CX for Contact Centers

Case Studies, Market Drivers and Barriers, and Market Sizing and Forecasts Focused on the Adoption of CX Platforms and Applications in Contact Centers

CX Market Ecosystem

150 Key Players and Industry Participants Providing Offerings in Customer Data & Analytics, Customer Relationship Management, Contact Center, Personalization & Optimization, Customer Insights & Feedback, and Employee Experience

Related Articles

Avaya contact center as a service

Avaya Showcases One Cloud CCaaS as Composable Solution

Avaya, the North Carolina-based multinational technology provider of cloud communications and workplace collaboration programs, is promoting its One Cloud CCaaS offering as a composable contact center solution that delivers a complete and…

Read More
Hotel customer experience

Two Hotel Chains Turn to CX Technologies to Improve Guest Experience

The ability to provide positive experiences for customers along digital and in-person touchpoints over the entire customer journey, from research and booking to check-in and boarding, to hotel departure and more, has always been a challenging task…

Read More
Contact center AI and automation

Helping Agents Respond to Inquiries Via Automation and AI

One of the major challenges involved with managing customer interactions is ensuring that live agent staff are delivering the correct and most appropriate responses during customer support conversations. Incorrect – or incorrectly delivered –…

Read More
Zoom and Genesys partnership

Zoom and Genesys Expand Partnership with New CX Offering

The California technology companies Zoom Video Communications and Genesys Telecommunications Laboratories are expanding their partnership with an offering that provides organizations with a feature-rich cloud contact center and unified…

Read More
more related articles