Have you ever wondered how a chatbot can understand natural language and answer as a human being would?
The answer is simple: behind every one of our chatbots there’s a human being, or, to be more precise, a team of humans who work in perfect synergy. This way, while Heres Developers give our chatbots a brain, Conversation Designers give them a human voice.
Conversation Designers: who are they and what do they do?
To express themselves, conversation interfaces need somebody to give them a voice, personality and context awareness that are similar to human’s. Conversation Designers plan these characteristics in order to create a personalised conversation experience and a captivating UX.
This figure, lying between a linguist and a copywriter and who we decided to call Conversation Designer, has been labelled in many other ways, each one highlighting a different perspective: Chatbot Writer, Chatbot Copywriter, Conversational Copywriter, AI Copywriter, AI Interaction Designer, etc.
Whatever label you choose, though, the meaning doesn’t change: a Conversational Designer is somebody who designs and writes conversations. Let’s see how.
How to give a voice to a chatbot in 3 steps
What does it mean to give a voice to a chatbot? It means looking after its communicative side, and therefore giving users the answers they are looking for, by engaging them in a pleasant dialogue.
This is what we do in Heres.
STEP 1 – RECOGNISING and remembering users and contexts
When a chatbot recognises the users and a series of contexts that can have an influence on the conversational flow, it can reply in a different way according to the features of the environment and the person it’s talking to.
These parameters are connected to external factors, like the page of the website the user is visiting or the moment of the day or of the year, and to users’ personal data, like language, age, number of orders or frequent purchases, all of which can be retrieved by already existing marketing automation and CRM tools or through internally-created dynamics.
While conversing, these parameters are memorised, so that the chatbot won’t have to ask for the same piece of information more than once.
Below, you can see two examples of conversations with two different users, on different website pages, in different moments of the year.
STEP 2 – ENTERTAINING: modelling the chatbot’s personality
Is it better to have a formal or informal automatic assistant? A serious or funny one? To be respectful or ironic? Is it better to have a polished, eloquent language or simple, straightforward slang? Is it better to give brief, practical solutions or to entertain with jokes and puns?
Tone of voice and formality, of course, mostly depend on the brand and on the target of users you are talking to. Writing the conversations for a chatbot, though, doesn’t simply mean paying attention to correct grammar, an appropriate tone and an accurate lexical choice, but also playing with words, with cultural standards and with shared knowledge, so that the bot’s answers sound as natural as possible and the conversational experience is well targeted. Let’s see a few examples of small talk, meaning those off-topic conversations exclusively aimed at entertaining the user.
STEP 3 – ANSWERING: leading the user to the answer
The third step in planning a conversation is to design its actual flow, and so guiding the user towards the answer. To do so, here in Heres we use an interface called Conversational-CAD, or CCAD, that allows you to associate users’ questions to their answers, and to plan tree-structured paths based on a careful analysis of the reference domain.
Information can be provided through the NLP or Wizard mode (compared through a SWOT analysis in a previous article), depending on whether you decide to let the users free to ask questions or to lead them through the topics managed by the chatbot.
There is no perfect copy, only perfectly flexible copywriters
Finally, when you design and write conversations, you need to keep in mind that the perfect conversation copy does not exist (for now). Each chatbot has to model itself on the clients and customers’ needs, and this is why in Heres we aim at making each feature of our bots customisable, voice included.
Moreover, the Conversation Designer’s job was born just recently, so the only real rule is to learn from experience in order to identify the most satisfying UX.