Learn about the conversation design process, including understanding requirements, tech considerations, identifying user personas, intent recognition and more.
We covered how conversation design can make or break virtual assistants in an earlier post. Here, we go into the process involved in the conversation design process. including gathering the requirements at the start, creating the basic conversation design flow and adding more detail to cover all possible scenarios and exceptions.
Begin by Understanding Requirements and Options
The first step in designing conversations involves understanding the requirements of the virtual assistant. The technology available, operational considerations and stakeholders, the user personas to address, and the virtual assistant’s persona are key factors that affect conversation design.
Before commencing a virtual assistant implementation project, it is vital to take stock of what technology resources are available. This includes the technology team and their specialties, platforms available, integrations possible, and channels where the virtual assistant will be active among others.
Generally, the tech team involved in a virtual assistant project comprises front-end and back-end developers, data scientists, and even an AI expert. This also depends on the industry, type, and size of the organization as well. For example, large technology companies may find it easier to create small teams within them that focus on innovation projects like virtual assistants. In contrast, a healthcare firm or an insurance company may not have a core tech team that can spend their time on innovation projects and may have to outsource their virtual assistant development to a specialized vendor.
Platform for deployment
Virtual assistants can be deployed using a variety of platforms and specific installations will have to consider which ones are available. Microsoft Bot Framework, Google Dialog Flow Bot landscape. Microsoft Bot Framework, Google Dialog Flow, and IBM Watson are just a few of the many solutions available in a growing landscape. It is important to include the developers and engineers in the planning process to figure out which ones are most relevant, what they can and can’t do for your project and how they will affect the conversation dialog design process.
Integrations to other systems
A virtual assistant on its own might be able to automate conversations to a certain extent but its value will be limited without integrations to other platforms based on the use case. For example, a healthcare institution will find value in connecting the virtual assistant to their electronic medical records to be able to assist patients with queries about their medical history and hospital staff with details about their treatment history. In an insurance firm, on the other hand, integrating the virtual assistant with policy management software and CRM systems can help customers and policyholders with more personalized service and recommendations.
Channel for virtual assistant deployment
Virtual assistants can be deployed across numerous channels today. They could be sitting on a company’s website helping visitors with FAQs and purchases or on Facebook, automating responses to common queries about opening hours, location, and directions. They could also be in the form of a WhatsApp Business API-enabled virtual assistant to help businesses scale real-time communication with prospects and clients or on other mobile apps. Each of these makes a big impact on the way conversations are designed.
User Identification and Handover
It is also useful to decide at the outset if and how a user of the virtual assistant needs to be identified and when and how they should be handed over to a live agent. In some cases like a general FAQ virtual assistant, anonymous interactions are reasonable but for more transactional, sales conversations, it makes sense to authenticate and identify them before proceeding with personalized responses. For these transactions and sales interactions or when the questions get more complicated in nature, there needs to be a sensible handover to a live agent. Keeping these scenarios in mind can help craft the relevant dialogues during the conversation design process.
Like any technology project, the design of a virtual assistant has to serve a bigger purpose within an organization. This requires thinking about how the virtual assistant will help a business achieve its objectives.
For example, a virtual assistant may be created to help a SaaS product help website visitors or customers with trial sign-ups and onboarding. Or it could be a travel insurance firm helping website visitors compare products, understand policy terms and check out in a self-service experience.
Even within an organization, there could be individual business units and departments that will stand to gain the most from implementing the virtual assistant. Customer service teams, sales and marketing, IT support, and HR are all departments whose functions can be improved with the implementation of a virtual assistant.
This also means that various stakeholders will also be involved in figuring out the direction of the virtual assistant’s development. Some of the most common roles in a virtual assistant development team include Product Owner, Head of Customer Experience, Head of Digital, Innovation Manager, or even the CEO himself in some cases. Knowledge Management and Internal Communications personnel are also critical in virtual assistant projects, as they are often in charge of managing and maintaining internal wikis, communication logs, and reference content that the virtual assistant will use to train.
Lastly, the specific KPIs set out also play a big role in dictating how the conversation design process will progress. Some of the common metrics that are monitored in virtual assistant projects include
- Customer Satisfaction Score and Net Promoter Scores – if the goal of the virtual assistant is to provide better customer service
- Sales Conversion Rate – if the virtual assistant is primarily for purchase and transaction-related goals
- Call Deflection Rate and Average Handling Time – if the virtual assistant is meant to complement a call center team
In the last case, the idea is that when the total interactions with the contact center staff go down, the duration and quality of each interaction go up. This signals a more focused service where high-value conversations are common.
Create User Persona and Virtual Assistant Persona
In designing any conversations, you need a good understanding of whom you are writing for. This holds true for creating website content, sales conversations, voice assistants, and virtual assistants. To help arrive at this understanding, it is important to create a user persona.
What is a User Persona?
A user persona is a semi-fictional representation of a specific segment of your target audience. It is semi-fictional because it is informed by real data and not by blind guesswork or stereotyping but at the same time, not a 100 percent accurate mapping of every individual who may fall in the audience segment.
User personas help conversation designers empathize with the audience and in creating dialogue that will most resonate with the audience. Often the data used to create personas may already be available in your organization, in the form of persona research undertaken by your UX or marketing teams. Look for these key elements when arriving at the user persona
- Demographics – age, gender, marital status, location, education, income, and others
- Psychology – goals, motivations, preferences, world view and other aspects
- Experience – any prior experience with the virtual assistants, conversational AI and were these good or bad experiences
- Other categories
For example, an example user persona for an insurance firm selling life insurance products could take the following form:
Alex, a 39-year-old IT Engineer, lives with his wife Sandra, 38, with two daughters Ivy, 7, and Tracy, 4, in Singapore. Alex has a yearly income of SGD 80,000 while Sandra makes SGD 96000 a year and both are graduates of recognized universities.
Alex wants to ensure a financially secure, healthy, and happy future for his family. He intends to work until he is 60 years old when he wants to have saved up enough for living a simple but comfortable retired life with his wife and hopes his children will have grown into stable careers by then.
Alex is familiar with virtual assistants and has interacted with a few while browsing websites, and ordering products from online stores and delivery apps. He found it useful for basic queries but not for more complicated transactions.
What is a Virtual Assistant Persona?
An assistant persona is a character behind the virtual assistant. It is what gives the virtual assistant its personality and differentiates it from a monotonous conversation with a robot. A virtual assistant with a clear persona can help your brand establish trust, consistency, and likability with your audience and users. Deciding on a persona involves thinking about the following aspects of the virtual assistant.
- Context – which organization should the virtual assistant represent, what identity should it have, who is its audience, what channels will it be on, and for what tasks?
- Virtual Assistant Identity – what is its relationship to the user – is it a humble servant, a peer, an advisor, a coach, or a challenger?
- Name, gender, and age – what is the virtual assistant called, is it male or female and how old is it supposed to be?
- Standard vocabulary – are there any common phrases the virtual assistant uses – e.g. for greetings, apologies, explicit and implicit confirmations, and are these phrased casually or in a very matter-of-fact way?
- Chatting Style – does the virtual assistant have an avatar, does it use emojis and punctuation marks, and are these used in a grammatically correct way? How long is the delay between the virtual assistant’s messages?
Identify Your Virtual Assistant’s Use Case
Next, you need to decide the use case for your virtual assistant – what it will help you and your users accomplish. This could be different for different businesses. For example, a healthcare institution will have a virtual assistant helpful in triaging patients and prioritizing patient screening, or a travel and tourism firm could use a virtual assistant for providing weather updates.
Even within an organization, a virtual assistant could have multiple use cases. For example, an insurance firm might use a virtual assistant to provide self-servicing for customers and policyholders and for agents to look up key information on product updates, company announcements, promotions, definitions, and terminology.
Within each use case, the virtual assistant will be asked to perform different tasks. For example, a virtual assistant that helps order food will have individual tasks like ordering breakfast, lunch, and dinner, booking restaurants, confirming orders, ordering cabs, and so on.
From the virtual assistant’s perspective, a use case will come with intents. Thus the first thing that needed to be done in a conversation between a human and virtual assistant is to recognize this intent. Only if the virtual assistant understands what the user wants to accomplish can it deliver the right dialogues to get the tasks done.
Simulate a Sample Dialogue
Once the user and virtual assistant personas and the use cases are decided, it is time to start creating sample dialogues. To achieve this, it is helpful to look at a framework known as the conversation design canvas. This consists of 3 components:
- Setting the scene – where is the conversation taking place, what is the social context, are there any time factors, and what is the user’s emotional state?
- User needs – list down the user persona attributes
- Virtual assistant needs – list down the assistant persona attributes
This canvas is then taken and briefed to two stand-ins “actors” who will carry out a natural conversation in the form of a role-play – one playing the virtual assistant, and the other playing the user.
Have a third party observe and take notes while observing this conversation. Note down instances where there were issues and miscommunications in the conversation.
The sample dialogue is then used to create a flow-chart that will list the steps in an average conversation – from understanding the intent of the user to listing all the potential responses or transactions to be carried out and any unforeseen steps that might need to be added before the task can be completed by the virtual assistant.
Apply an Expert Rewrite
The sample dialogue created in the previous step will most likely be far from perfect. This is where an expert rewrite comes in, where you apply advanced copywriting skills to polish the conversation and make it flow better. Numerous copywriting techniques can be applied to do the rewrite but a few critical ones are as follows:
- Use the active form – “Enter your info and click Submit to purchase” is better than “The product can be purchased by entering your info and clicking Submit”.
- Reduce adjectives – Too many adjectives can make the copy sound amateur and even inauthentic.
- End prompts with a question – Without a prompt, it will not be clear to the user that they need to act to advance the conversation.
- Breath test – Can the line of dialogue be read in one breath? Otherwise, it is probably too long.
A rewrite like this can also be considered to be a form of “internal testing”, where someone within your team has a look at the effectiveness of the virtual assistant conversation to make improvements.
Test with Real Users
Once the sample dialogues and flow charts have been polished by a copywriter it is time to test the conversation design with external users. Get the help of someone outside of the project team to stand in as a new user. Ask them to converse in the relevant channel and brief them that they will be interacting with a virtual assistant. This could be for example via a WhatsApp business profile, a Facebook Messenger channel, or a website’s virtual assistant interface.
Write down the dialogue created in a Word or Google Document and paste texts from this into the channel in response to the user. Remember to use responses just from the document and don’t improvise or adjust these if there are any hitches. If you observe any gaps or confusion faced by the user, that suggests an area where the conversation design can improve to cover more scenarios.
For a deep dive on testing virtual assistants, check out our article on the 7 golden rules of testing conversational AI solutions
Look at All Possible Scenarios
When you conduct the testing with real users, you will most likely discover scenarios you had not planned for. Consider a virtual assistant that helps visitors to an insurance website. The users of the virtual assistant could either know exactly which product they want or they may be completely new and looking for guidance. The virtual assistant needs to recognize the intent in each case and cover all scenarios.
Responding to each intent involves slightly different conversation design practices.
One approach is to list all the tasks the virtual assistant (VA) can perform at the start, like this.
VA: Hi, my name is ALICE. I can help you learn about our products, compare policies, request a quote, submit a claim, talk to your agent or contact our customer service representative. What would you like to do?
While this is informative and covers all the scenarios, the prompt is too long. A more natural approach involves breaking down the scenarios into smaller, shorter prompts to recognize the user’s intent by elimination. It would go something like this very simplified example:
User: Hi, I need help with my insurance
VA: Sure, would you like to learn more about our products?
VA: Would you like to compare policies?
User: No I am already your customer
VA: Perhaps you would like to submit a claim?
VA: Would you like to talk to your agent?
While this makes the flowchart and conversation longer, it is more natural and easier for the user. Yet another way this can be simplified is by providing buttons or menu items for the user to click and confirm their intents. The same conversation above can be simplified with buttons as follows:
User: Hi, I need help with my insurance
VA: Sure, what would you like to do?
Keep Edge Cases for Human Agents
In most cases, not all conversations with a virtual assistant will be valuable for the business. There will be a significant proportion of cases where the users involved are many and their value to the business is high (head), and a few situations where the number of users involved is fewer and the value to the business is less as well (long-tail). In designing conversations, remember that you don’t have to write for every scenario.
The famous Pareto principle or the 80/20 rule also applies to virtual assistant conversations. Here it means that 80 percent of your users are going to be using 20 percent of the paths that you design. This is the most important part of the conversation and where the most value lies for your business. The remaining 20 percent is often comprised of edge cases that can be handed over to a human agent, or when the user can be informed about the virtual assistant’s limitations.
To find out how KeyReply can help you design engaging and useful virtual assistants for your organisation, talk to our experts today.