A plea for boring bots

because not all bots need to be great at conversation.

Lots of great chat- and voicebots have been developed and presented to the public in the last couple of months. Think about Google home, Amazon Alexa, Invoke and Apple HomePod. The tech industry was baffled when Google presented Google Duplex at Google I/O. Microsoft announced late May that it had acquired the AI Startup ‘Semantic Machines’ in an effort to make its bots and intelligent assistants sound and respond more like humans. And the list goes on. It’s clear that big tech corporations are investing in making the bot experience feel more like natural conversations.

Although we’re big fans of the virtual assistants mentioned above; we should ask ourselves ‘does my bot need to be thàt smart in order for it to be successful?’.

Not every bot requires its own persona: you don’t want a social chatbot personality in a business setting, but you also don’t want a sturdy business persona in a social bot experience. It’s important to consider the use case.

Your bot can be great at conversations. If you’re designing a virtual assistant, it should be! It can have a vast vocabulary and can even make great jokes, tell you about the weather or help you discover music you like. But unless it addresses the problems that your users need to solve, these capabilities may contribute very little to making your bot successful. According to our findings, we shouldn't assume any correlation between a bot’s intelligence and how much Natural Language it can handle, and the user adoption of the bot.

If you want your bot to be successful, you need to assure you are creating a bot experiences that actually solves a business problem, in a way the users will prefer the bot experience over alternative experiences like apps, websites, phone calls, or other means of addressing their needs. Ensuring a great user experience should be your number one priority during the design phase of a bot. Forget about trying to create the next Siri, Google Home or Cortana for a minute.

Here are some of the key questions you could ask yourself during the design phase of a bot:

  • Does the bot easily solve the user’s problem with the minimum number of steps?
  • Does the bot solve the user’s problem better/easier/faster than any of the available alternative experiences (app, website, phone call, …)?
  • Does the bot run on the devices and platforms where my users are?
  • Do the users naturally know what to do when using it?

Note that none of these questions are directly linked to how ‘smart’ the bot is. In most cases, it is unlikely that making your bot smarter will guarantee happy users or adoption of your platform. In reality, many bots have little advanced machine learning or natural language capabilities. And that’s perfectly fine, because a lot of use cases don’t require those capabilities. A bot may include those capabilities if they’re necessary to solve the problems that it’s designed to address, but often a ‘dumb’ (yet effective) bot with a limited scope and an effective flow has a far more successful user adoption rate.

this article was originally published on our arinti blog page: https://blog.arinti.be/a-plea-for-boring-bots-f62ff0eb14cc


要查看或添加评论,请登录

Wouter Baetens的更多文章

  • My lessons from 15 months in sports marketing & partnerships ??????

    My lessons from 15 months in sports marketing & partnerships ??????

    In October ‘22 I took a deep plunge into the world of sports marketing after 13 years in tech. My passion for sports…

    10 条评论
  • An AI Love Story: Intelligent Receptionist

    An AI Love Story: Intelligent Receptionist

    Chatbot working together with RPA bot: a game changer! We recently teamed up with the guys at Roborana for the InQbet…

  • Robots in the City Hall?

    Robots in the City Hall?

    About our Proof of Concept with TomorrowLab and the city of Aalter (BE). Last week, Arinti made national press with a…

  • When Chatbots meet RPA bots

    When Chatbots meet RPA bots

    An AI Love Story “How can we merge Chatbots and RPA?” is a question we’ve asked ourselves a few months ago, when we…

  • Chatbots?—?Promising opportunity or overrated hype?

    Chatbots?—?Promising opportunity or overrated hype?

    While we position ourselves as a company that “creates innovative AI solutions”, about 50% of our project inquiries…

社区洞察

其他会员也浏览了