Virtual agents – how to write great dialogue for conversational AI


Share on LinkedIn

Building great dialogue for your virtual agent requires finesse and a clear understanding of the needs of your customers. Interacting with conversational AI should be as easy and natural as talking with a human. However, achieving that almost human level of understanding is not nearly as simple as it seems.

A virtual agent might be the first (and, in many cases, only) point of contact someone has when interacting with your business. It should be a shining example of how you want people to perceive your brand — the ultimate ‘model employee’ — not a messy chatbot that is constantly leaving customers with a bad impression, potentially turning them away for good. To that end, here are my tips to help you create better conversations with conversational AI:

Context is king – Most communication is characterized by the context it occurs in. For example, if someone asked you if you’d like an energy drink, responding with “that will keep me awake”, has a drastically different meaning first thing in the morning, compared to later that night. When writing dialogue for a virtual agent, we need to be mindful of how a query can be interpreted, as this is one of the keys to clear understanding.

Be empathic – if you want to truly help your customers, you need to put yourself in their shoes. Empathy is a crucial part of any conversation, and the same applies to writing good chat dialogue. If a customer comes to you with something positive, your virtual agent’s response should reflect that. Similarly, if they’re approaching you with a delicate matter, it’s advisable to hold back on using a winking-face emoji. There’s a time and a place for jovial replies, but it’s more important to try and show your customers that you recognize their situation. It will go a long way to helping build loyalty towards your brand.

Manage customer expectations – Before you can accurately manage the expectations of someone using your virtual agent, it helps to know (as much as possible) who that person is. Don’t skip customer insight and mapping and get your customers to talk about their needs and expectations. It’s also important to be transparent – customers should understand that they are chatting with a machine. Your virtual agent should make this clear, while also outlining what it can and can’t do, minimizing any potential confusion for customers.

Personalize your content – It’s far easier for humans to express ourselves when we are interacting face-to-face, rather than in writing. The “mmm’s” and “aha’s” we casually throw into conversations work in concert with facial expressions and body language to convey a sense of empathy, which is more difficult to achieve over online chat. A virtual agent powered by conversational AI can, however, still inject personality into its interactions, for example by using emojis (with restraint, depending on the situation) and humor. The skill comes in establishing the right level of personality — too little and you might alienate your customers, too much and you run the risk of coming off as overly familiar.

Get the tone right – An interesting trait in human conversations is that we tend to mimic the tone of voice, choice of words and phrasing of the person we are talking to. We should be mindful of this when building chat conversations. If your virtual agent responds to customers with long, wordy answers it sets the expectation that it is able to understand long and wordy questions. It can be frustrating if, instead, it turns out that your virtual agent isn’t quite as intelligent as its inflated vocabulary makes it out to be. Tailor your conversational AI to fit the situation and you’ll leave a much better lasting impression.

Don’t be afraid of making mistakes – You can try to manage expectations as much as possible, but the truth is mistakes will happen. The important takeaway is to not try and build flawless conversations. You can’t. Instead, prepare for the inevitability of mistakes, whether they are human or machine-made, and find ways to get the conversation back on track. Here are some best practices you can follow to minimize mistakes:

– Own it. If your virtual agent doesn’t understand the question, it should be clear about it and immediately offer human assistance when it’s available
– Take responsibility. Customers should be able to voice their dissatisfaction with an incorrect response and your virtual agent should (if possible) provide an appropriate alternative.
– Be constructive. In the event of a mistake, your virtual agent should provide suggestions on how to move the conversation forward and how to avoid repeating it in the future.
– Have human backup. Sometimes your virtual agent won’t be able to adequately satisfy a customer’s query. In these situations, it’s important to make it as frictionless as possible to hand them off to human support so they can get the help they need.


Please enter your comment!
Please enter your name here