{"id":24535,"date":"2020-08-25T10:55:16","date_gmt":"2020-08-25T09:55:16","guid":{"rendered":"https:\/\/www.intercom.com\/blog\/?p=24535"},"modified":"2021-09-10T14:48:51","modified_gmt":"2021-09-10T13:48:51","slug":"conversational-design-for-better-products","status":"publish","type":"post","link":"https:\/\/www.intercom.com\/blog\/conversational-design-for-better-products\/","title":{"rendered":"Conversational design for better products"},"content":{"rendered":"

We all know what a conversation between two people sounds like.<\/p>\n

\u201cHey, can you help me a sec?\u201d
\n\u201cSure. What\u2019s up?\u201d
\n\u201cI just can\u2019t make sense of this dashboard.\u201d<\/p>\n

Human conversation is a sequence of verbal exchanges \u2013 what linguists call turn-taking. This rhythmic exchange is deeply hardwired into our social neurophysiology, as call-and-response bonding in animals is likely hundreds of millions years old. And as humans, we carry our hardwired back-and-forth expectations into our interactions with computers.<\/p>\n

There\u2019s a lot of discussion around conversational computing these days \u2013 at Intercom, we talk about our customer communications platform<\/a>, conversational support<\/a> and conversational marketing<\/a>. But what makes software conversational? The way it sounds, or something deeper?<\/p>\n

This piece outlines a process for building and structuring effective conversational experiences in software. Along the way, we\u2019ll explore how conversational UX \u2013 cooperative exchanges of inputs and outputs \u2013 closes gaps between products and users.<\/p>\n

Overcoming gaps in understanding<\/h2>\n

Paul Grice<\/a>, a 20th century philosopher of language who studied how conversation works, is a perennial touchstone for teams working in AI, linguistic engineering, and conversational design. Deservedly so. One of Grice\u2019s key insights is what he called the cooperative principle<\/a>. Simply put, it\u2019s the idea that a conversation is a collaborative process aimed at forming meaning by overcoming gaps in understanding.<\/p>\n

\u201cIn human interactions, we instinctively work together to close the gaps in meaning inherent in conversation\u201d<\/p><\/blockquote>\n

In human interactions, we instinctively work together to close the gaps in meaning inherent in conversation. That process still fails a good bit, but most of us know to repair confusion quickly with follow-up questions. And beyond knowing when to disambiguate, we excel at making contextual inferences. So when my child asks, \u201cMay I have ice cream?\u201d and I say, \u201cIt\u2019s not even lunchtime yet!,\u201d she understands that I\u2019m saying no. Whether she accepts that communication is a separate issue.<\/p>\n

In software, gaps in understanding can be relatively small (\u201cHow do I filter by location?\u201d) or fairly foundational (\u201cAre \u2018apps\u2019 different from \u2018integrations\u2019?\u201d). Especially for these bigger understanding gaps, you\u2019ll need to design conceptual frameworks and systems that work for your users. Ask yourself, \u201cHow do I bridge users\u2019 existing mental models and the product itself?\u201d<\/p>\n

To figure out the big and small gaps your conversational UX needs to bridge, start with all the standard things: deeply research users\u2019 problems, understand the competitive landscape, figure out the constraints, align the work with the larger company strategy, and so on. Then define and document the parameters of your cooperative conversational experience \u2013 you can use something like the following \u201cjob story\u201d formula.<\/p>\n

As [user], I\u2019m partnering\/collaborating with [product\/product area\/flow] to [job]. We\u2019re in dialogue about [explicit or implicit user signal].<\/strong><\/p><\/blockquote>\n

This can be a broad formulation, typically for early-stage work. For instance: \u201cAs a teen with an anxiety disorder, I\u2019m partnering with a new mental wellness chat app to feel better over time. We\u2019re in dialogue about my ups and downs.\u201d Or it can be more granular, for targeted parts of a larger experience: \u201cAs a student with test anxiety, I\u2019m partnering with Balm\u2019s breathing coach feature to bring my body back into regulation. We\u2019re in dialogue about how I\u2019m doing moment by moment.\u201d<\/p>\n

Be sure you\u2019ve clearly understood who\u2019s in dialogue (ex: specific user segments and your in-product brand personality), the parameters of the interaction, and the job they\u2019re cooperating on.<\/p>\n

Structure conversations through turn-taking<\/h2>\n

Next, to get a sense of the inputs that will drive the conversation, list the decisions the user will need to make in this experience. You\u2019ll quickly discover that sequence often matters. Pay attention to the implications of sequencing one user decision \u2013 that is, one conversational turn \u2013 before another.<\/p>\n

\u201cAs you work on sequencing, don\u2019t forget to pay attention to the conversational rules that you probably follow intuitively in every day chats with friends\u201d<\/p><\/blockquote>\n

We\u2019ve all encountered conversational problems in the wild and online. As you work on sequencing, don\u2019t forget to pay attention to the conversational rules that you probably follow intuitively in every day chats with friends. For the conversationally challenged, Grice elaborated his cooperative principle<\/a> with rules of engagement. Keeping those rules in mind, we can solve four common UX design problems:<\/p>\n