top of page

The art and science of conversation design

How we interact with technology is always evolving, and chatbots represent a prototype of how we will increasingly interact with brands, organisations and data as AI develops further. Even now, bringing an almost human touch, chatbots and conversation design seek to make these experiences as intuitive as possible, next to having a conversation with a real person.

But have you ever wondered what goes into creating one of these bots yourself? Let us walk you through what it takes to turn the ones and zeros into a personable experience.

What is conversation design?

Conversation design is where content meets design thinking. It’s a discipline that sets the scene for engaging and productive interactions between bots and humans. Effective conversation design creates seamless bot conversation experiences that help users gather information, self-serve on high-traffic enquiries and navigate their way to the most relevant products or information.

How this helps organisations scale up

Conversation design is a type of automation, which means it carries with it many of the benefits that come with automated solutions – including the ability to scale.

Businesses that rely heavily on person-to-person conversations between employees and customers can level up with this scalability. Conversation design can be applied across:

  • Information and support: Bots and virtual assistants are brilliant for handling enquiries and directing users to resources.

  • Task automation: Bots can manage the day-to-day tasks of processing requests and transactions, making appointments or reservations, or altering profile details.

  • Advice and recommendations: With advances in AI, bots are becoming increasingly good at nuanced conversations that represent lateral problem-solution thinking, helping users discover information or products that either support the user’s drive to action or that even sit outside of it as a form of personalisation.

In the right setting, a bot can free up resources, reduce wait times and enhance customer satisfaction – benefits any business would welcome.

What does the end product of conversation design look like?

Conversation design teams work together to develop bots that users access through text and voice interfaces.

Text-based bots

Text-based bots are the most common and the easiest to derive value from when you already have a strong online presence. They’re great when leveraged by:

  • Businesses with a physical product

  • High-volume consumer-facing businesses

  • Service-oriented businesses

Voice assistants

The other way we typically engage with bots is through voice. This is an area that is growing fast in popularity with more of us using voice assistants more regularly.

Some of the most popular voice assistants include:

  • Amazon’s Alexa: Used with Amazon Echo devices and integrated into many other smart home devices and third-party platforms.

  • Apple’s Siri: Siri is Apple's voice assistant, available on iOS devices, Macs, and HomePod.

  • Google Assistant: An Android bot used on Google Home speakers, phones, and other smart devices.

There are also chatbots developed for enterprise-scale solutions like IBM Watson and Microsoft Cortana. Each is engineered to assist in generating operational efficiency and incorporate powerful AI and data integrations.

The differences between text and voice in conversation design

The work that conversation designers do to create text-based chatbots and voice assistants is very similar, but the actual content we write needs to be quite different. That’s because users interact with text and voice interfaces differently.

Consider how you might like to receive information from a bot. If you’re driving and using Google Maps for directions, you don’t want to be overloaded with information, so short and timely directions are best. But if you’re at home and using a bot to pick out a recipe to cook tonight, you can make use of a little more detail.

Voice is more like a natural conversation, where it feels more personal but it’s also easy to frustrate the user. That means you need content that presents simply and clearly the first time it’s heard. Text won’t ‘connect’ with users the same way, but it does give you a little more space to present options and share more detail.

Deciding what kind of automation is best for your intended use cases is something a conversation designer can help with from the outset.

Strengths and weaknesses of automated conversations

Every solution has its strengths and weaknesses. The primary strengths of a good chatbot or voice assistant is that it can:

  • be made available 24/7 (no down time!)

  • eliminate wait times and get to customers faster

  • ensure consistency and generate clear outcomes

But bots aren’t a complete solution to every customer enquiry. Wherever a bit of lateral thinking is required, a human agent is going to be essential. Part of the conversation design process is recognising the limitations of a bot and where it’s better to direct a complex or sensitive matter to a human agent or elsewhere. Of course, this is an ongoing process as the capabilities of AI exponentially increase to solve more nuanced and complex problems for people.

How does the conversation design process work?

That’s all the background detail out of the way. Now, you might be wondering – where do we get started?

You’d be relieved to know the total process isn’t that complicated when looking at it from above. Just like anything technical though, the smaller details mean everything when it comes to getting a quality result.

An example of a typical conversation design process between us and a client:

Step 1: Understand the user and use case

Conversation designers begin by identifying their target users, and that user’s needs and preferences. That involves looking at what kinds of channels your customer has access to, the types of enquiries they are likely to have, and how a voice or text bot might be best developed to service those needs.

Step 2: Gather technical requirements

Gathering technical requirements means identifying answers to questions like:

  • How much will a user know? What are their likely goals?

  • What likely obstacles will the user and the bot need to overcome together?

  • How much will our bot know about the user?

  • Where will the conversation end? And where do we send enquiries that can’t be handled by a bot?

  • What data management platform do we/will we use and how will this affect the discoverability of content?

It’s all important because these questions shape the ‘facts’ of the conversation and ensure we’re getting the best results possible out of this automation.

Step 3: Script sample dialogue

Personality and persona are essential to building trust between the user and our automation. It’s also an important part of getting your branding right through a channel that can feel quite direct and personal to your user.

This part of the process includes developing a tone of voice, a consistent vocabulary, and even a bit of a backstory for your bot. A lot of this work goes ‘unseen’ by the user, but it’s all there, and felt in every exchange.

Step 4: Design flows

Natural conversation is interactive, so it’s important that an automated conversation feels that way too. This means the user has some choice in the route the conversation takes, and the way we cater for that is the use of ‘conversation flows’.

These flows are like conversational decision trees, and they’re one of the most important tools in a conversation designers toolbox. They sequence the different paths that a conversation can take and help us steer the user in the right direction.

You might hear conversation designers talk about the ‘happy flow’. This is shorthand for the paths that are most common and most productive. Edge case enquiries can usually be either turned away, or directed to a human agent.

Step 5: Testing

Testing happens throughout the conversation design process, but one of the most important types of testing in conversation design is Wizard of Oz testing. This is where you take test dialogue and simulate conversations between users and your bot to see how the conversation plays out.

There are platforms that make this easy for text-based chatbots, but you can also test early versions of your voice assistant by having testers sit back-to-back (or use the phone) and read draft copy out loud. This allows you to verify the bot's responses and identify any issues in the flow of the conversation.

Step 6: Deployment and ongoing iterations

Once testing is done, you’re ready to deploy. But while the bulk of the work is already handled, there’s always something to be learned through continual monitoring and testing. Tracking progress and making adjustments where necessary is the best way to get the most out of these powerful automation tools.

You may also find that iterative changes to your bot are a great way to keep the tone current. Over time, you might also find that new flows can be developed to make the most of new backend integrations and more.

How to know if you need conversation design in your organisation

Essentially, if your organisation deals with a high volume of customer interactions, either complex or simple, and you want to find long-term savings in customer management, chatbots can be a useful investment. We say ‘simple’ because savvy investment in conversation design for even simple user journeys can provide a range of benefits, including improved user experiences, cost savings, easier customer marketing management and access to insights and analytics.

Your first step is to reach out to specialists in conversation design to map out the scope of your investment and create a clear plan for how chatbots can be integrated into your business model to help you scale.

Cover image: storyset on Freepik


Los comentarios se han desactivado.
bottom of page