![\"gartner](\"https:\/\/www.intercom.com\/blog\/wp-content\/uploads\/2017\/12\/Lessons_Learned_Building_Bots_Inline_03.png\")
<\/p>\nWhen a new technology emerges, there\u2019s an initial trigger.<\/p>\n
The masses react and become disillusioned, and then the trend slowly builds through a state of enlightenment and finally productivity. This is known as the Gartner Hype Cycle.<\/p>\n
<\/p>\n
If we view bots \u2013 the biggest trend in software today \u2013 through that lens, they would fit squarely in the trough of disillusionment.<\/p>\n
![](\"https:\/\/www.intercom.com\/blog\/wp-content\/uploads\/2017\/12\/Lessons_Learned_Building_Bots_Inline_021.jpg\")
<\/p>\n
Early attempts at chatbots have fallen flat in their execution, mostly because they rely too much on natural language processing or A.I. capabilities that simply don\u2019t yet exist. Despite this, we’re bullish on bots, but only those that are built to solve a very specific problem.<\/p>\n
No matter what we’re building, we always start from first principles<\/a>. That means we do deep exploration into the roots of the problem, to try to understand what the problem is and why we are going to solve it. When debating whether or not a bot was for us, we discovered there are some simple tasks that don\u2019t make sense for humans to do \u2013 and bots could be helpful in these cases.<\/p>\n Let\u2019s say you\u2019re going to chat to a business, but it\u2019s the middle of the night. No one is there to actually reply to you. In a situation like this, most messengers would display their own version of a closed sign. Something like, \u201cSorry, we’re not here yet. Get back to us in the morning and someone will reply to you\u201d. What if a bot stepped in to set expectations for the user while the team is away and collected their contact information. Down the line, a bot could suggest help articles using machine learning or ask users to rate a conversation when it comes to an end.<\/p>\n It took us a year and a half to build our own bot, Operator<\/a>, and in doing so we learned five important lessons, all of which you\u2019ll want to consider if you plan to do the same.<\/p>\n In our earliest days of bot building, a person would start a conversation in our messenger, and we\u2019d have the bot respond with a simple reply, \u201cHi, I’m Interbot, Intercom\u2019s digital assistant. The team will reply here as soon as they can.\u201d<\/p>\n When the bot introduces itself, people start to form expectations.<\/p>\n We didn\u2019t want to pretend that this was a human. We wanted to be extremely clear and polite, and let the bot introduce itself. What could go wrong?<\/p>\n When we tested the concept, users hated it. It turns out that when the bot introduces itself, people start to form expectations. Some people believe it’s a fully-fledged chatbot, one that will work instead of real human support<\/a>, and some people just don’t want to talk to robots.<\/p>\n We tried multiple versions of this introduction, but what actually worked best was no greeting at all. In this case, when the person starts a conversation, the bot gets straight to the point and says something like, \u201cThe team usually responds in under two hours this time of day. Check back here later, or enter your email below.\u201d No introduction required, and nothing is said that isn\u2019t related to the human’s task.<\/p>\n As our exploration continued, we began to ask questions around the bot\u2019s character. Does it need a personality? Should it be male or female?<\/p>\n In some cases, when the product is a bot itself, it’s fine to have some character. But if people are really expecting to have live chat with humans, any kind of personality is a distraction. For example, look at the Quartz News App below. It delivers your news in a conversational UI, and it doesn’t have any personality. You’re just reading news in conversation.<\/p>\n1. Some people just don\u2019t want to talk to bots<\/h2>\n
2. Your bot probably doesn\u2019t need a character<\/h2>\n