Overview
PagersDirect is an online specialty retailer of pagers and paging services. All ordering and customer assistance is handled on their website or toll-free customer care call center.
The toll-free call center has operated with Google’s expiring CallJoy service to direct calls, record voice messages, send SMS texts, and record utterances for AI training.
PagersDirect needed a quick solution with comparable features of the now-defunct CallJoy service. My role was to review the efficacy of CallJoy’s dialogue and transfer the chat flows to the Dialogflow phone gateway (beta).
Context switching ruins marketer's productivity
To understand why customers are use pagers, who uses them, the volume of calls, and the needs of PagersDirect, I led a series of client interviews and performed secondary research. Customers call PagersDirect to buy new pagers, trade pagers in for new ones, or troubleshoot problems with their device or services.
I discovered that EMS, technicians, doctors, and other service workers use pagers for the following reasons:
Why CallJoy?
CallJoy was an automated call answering platform built to address small business needs for the low price of $39/month. PagersDirect used CallJoy to manage their high volume of calls. The service supported customers by directing them to specific customer service handoffs or sending SMS text links to FAQ webpages. This flow actively encouraged autonomy by the customer. These flows freed up bandwidth for human agents to answer questions with variable inquiries such as sales of specific pager devices and complex technical issues.Marketing showing the services and features from the now defunct CallJoy.
Dialogflow And The Phone Gateway
Dialogflow’s Phone Gateway integration provides a telephone interface for a Dialogflow agent. I had built many chatbots with Dialogflow but was unaware of its integration limits. I was aware that Dialogflow was not a robust call center solution like CallJoy, and there would be some functions Dialogflow could not do.
Before diving into the Dialogflow, I reviewed the existing 10 intent pathways for clarity, concision, and relevance to the customer’s goals. I mapped the utterances to visualize the experience and created a system to communicate dialogue revisions to the client as we advanced. I observed the following areas to explore further:
Implicit vs. explicit confirmations
Editing particularly long responses
Dialogflow phone gateway’s capabilities compared to CallJoy’s
I also used existing dialogue as a base and kept the end-user profiles in mind as I enhanced the chatbot persona.
Conversation Is Turn-Taking
The agent’s original utterances tended to be casually verbose or ask multiple questions in one turn. The longest original prompt took 59 seconds for the text-to-speech to utter. These prompts then led customers to receive an SMS text that may not solve their issue or contact the business by email.
I tested the dialogue by sitting back-to-back with a participant reading the flows, and recording the interaction to detect and review problem areas.
The current flows did not take advantage of turn-taking, infrequently asked for confirmations that allow end-users to make mistakes or change course. Unlike a live agent, this virtual agent wasn’t able to manage any interruptions whatsoever. Making it even more important to have pointed prompts.
How I attempted to alleviate these pain points:
Eliminated words that did not move the conversation forward
Added smaller digestible chunks
Reserved verbose phrases for follow ups or misrecognition
Gave example phrases to guide users to phrases the bot can understand
Broke up any prompts that grouped more than one question at a time
Interaction exchange gives the customer acknowledgment of their problem and perceived control to the correct solution. In a human conversation, this acknowledgment and contextual escalation create the momentum needed to arrive at a solution.
What’s Technically Feasible?
Because DialogFlow and CallJoy are products with unique audiences, it was inevitable there would be feature tradeoffs. Texting customers was one of CallJoy’s main features. After exploring SMS APIs such as Twillio, I knew adding a code-heavy service exceeded the project scope. I focused on what I could do in Dialogflow. This approach required that SMS texts were changed into handoffs to specific routing numbers for particular intents.
Designing For Voice
Without visual cues such as nods, facial expressions, and eye contact, words hold even more weight. I was given a thorough list of training phrases, but the NLU wouldn’t always get it right when testing. I had to add multiple training phrases so that the NLU would understand. A swap of a pager and trade were not the same. One was an exchange, and the other meant to buy a new one.
No SMS
I spent hours researching ways to add SMS to Dialogflow. This research included using Zapier, integrating Twilio, and speaking with Conversation engineers. Adding it might have been achievable, but working in tandem with an engineer was out of scope for this sprint.
Summary
I explored Dialogflow’s integrations, speech-to-text recognition and became deeply acquainted with the complexities of these integrations.
Next Steps
Revisit the dialogue
The writing could be more concise. Being “conversational” is an interaction, not a monologue. The rhythm and balance of the back-and-forth exchange are as crucial as the writing itself. The feel should be inviting, encourage cooperation, and user-focused. If the website is the primary source of solution information, a chatbot might provide an improved experience.
Encourage a primary channel for customer resolution
Channel switching should enhance the experience. Customers calling are most likely expecting to complete their tasks via the IVR. Directing the customer back to the website is time-consuming, inconvenient, and may potentially lower customer trust.
CallJoy competitors and replacements
CallJoy was a starting point for many small businesses to explore call tracking, analytics, and IVR design. Thankfully, several companies have picked up the torch for small business owners to build on their call center needs strategically since completing this project. These services include but are not limited to CallRail, Invoca, Convirza, and Callcap.