Designing Conversational Bots for Enterprise
The Future is Spoken presents Greg Bennett as this week's guest. Since its inception, Greg is Conversation Design Principal at Salesforce, leading the company's first dedicated Conversation Design practice. As a linguist, Greg focuses on empowering businesses to create chatbots that feel natural and helpful, build user trust, and meet customer expectations for conversational behaviour. Greg works with Salesforce's Product teams, customers, and partners to tailor their conversation designs for cross-cultural differences across channels and user populations and effectively express personality or conversational style.
Starting with their own experiences, they end up discussing designing conversational bots for the enterprise.
Tune in Now!
[00:32] From Linguistics to Conversational AI
● Greg's academic background is in linguistics. He studied linguistics for his undergraduate and graduate work.
● Linguistics is the science of how language works in practice. Greg talks about the design principles that they teach bots to accomplish a particular outcome.
● Linguistics is getting famous with Conversional design as it provides a natural path forward.
[03:38] Greg's work at Salesforce!
● Greg talks about the approach of Salesforce towards developing Einstein Bot platform. He also explains how they are ensuring the growth of this technology.
● Einstein is an NLU technology that trains chatbots to create a learning model. The learning model helps chatbots built with Salesforce understand customer interactions in a chat window.
● Are there any plans for voice enabling?
● Greg also elaborates on the use cases of Einstein Bots in the enterprise world.
[12:26] Benefits of using Enterprise Bots
● Greg speaks about 'How bots fit in the benefits of a company?'
● Conversational Bots provide you with a better way to show the consumers what your institution is all about.
● He sheds light on the need to make sure that they reflect your brand.
[16:34] Creating your Bot…..
● Greg touches on the customizability of the Einstein Bots. He also talks about the response rate of an Einstein Bot.
● He discusses the Intro Template Bot. It provides the Salesforce Administrators with the ability to launch a bot from the templates.
● How will the customers know how to design their bots?
● Greg also elaborates on the building blocks in designing a Conversional Bot. From the overall implementation perspective, components depend on what your end goal is!
● Greg explains the best practices someone needs to consider when designing a conversational AI.
[37:43] Choosing suitable options!
● Greg talks about deciding what to choose and what not to? As a Conversational Designer, he is biased about the importance of data in selecting suitable options.
● He also touches on how to end the conversation and answer questions like, "Should you always end a conversation with a question?"
● What about ending the Conversion?
● Everything has a variation, so as Conversational Designer, you can use it as an advantage to create an unforgettable experience.
[46:08] Ensuring to stick with your branding traits
● For Greg, it's about creating a list of what fits within the brand. He explains about creating a repository of all the different ways he could acknowledge the receipt of information.
● He also shares his experience of working on Cortana and compares it with developing an enterprise Bot.
[50:16] Measuring the User's Trust
● Greg talks about the different ways to measure the user's conversation with the Bot.
● If you want to build a relationship, that takes time.
[54:10] Must Listen
● Greg's piece of advice for someone trying to get into Conversational AI.
Learn more about Greg at
● Start a free trial at Salesforce Today!
● Lingthusiasm Podcast by Gretchen McCulloch
● Make sure to check out Discourse Markers.
Book by Deborah Schiffrin
If you enjoyed this episode of The Future is Spoken Podcast, then make sure to subscribe to our podcast.
Follow Shyamala Prayaga at @sprayaga