Conversation design (CUI)

Voice and tone

Automated conversations are dynamic, they feel alive. Customers naturally project personalities onto them. Our brand's personalities are built from our voice and tone guidelines. But they need to flex into something more—bot personas.  

Importance of personas

Bot conversations can go anywhere. Expressing our brands in ways we never imagined. For conversational experiences, personas are the source of truth.

Our bot personas

When writing for a bot, you’ve got to know its persona. You’ve got to internalize it so you can write in the voice of bot without thinking about it. 

Relationship to the customer

Bot conversations are more intimate than standard product UI. This intimacy affects the possibilities for interaction. Things can get personal, funny, or incredibly serious. Besides helping customers get answers and complete tasks, the bot also needs to maintain an ongoing relationship. Customers don’t just want answers, they want to feel cared for and empowered, to be given clear direction, and to be understood.

On empathy

Running a business or working through taxes can be both challenging and rewarding. It’s important to acknowledge both when you can. Empathizing isn’t about guessing a customer’s emotional state. Instead, find ways to show the bot understands what they are going through by citing the circumstances of their situation.

Talking money

Money is a sensitive subject. Not everyone’s money goals are the same. It’s not a bot’s place to judge. But because it’s a complicated system, it’s OK to assume customers need help with it.

Using I, you, and we

Pronouns can get slippery when a bot talks about itself, the company, or the customer. Also, bots often offer suggestions that get posted into the chat as if the customer said them. Here’s how to think about these pronouns.

Using "I"

Using "we"

Using "you"

Writing for conversation

Conversation has been part of your life since you were about 2 years old. You already know in your bones what makes a good conversation. You can trust yourself and follow your gut. That said, here are a few things to consider when you write for conversation. 

Conversational style

The word “conversational” gets thrown around a lot, often as a proxy for “informal.” It’s true that conversation is inherently more casual or intimate than some other forms of writing. But how casual you get still depends on the situation. And there’s more to making your style conversational.

To achieve conversational style, follow our content design system's great principles. This guidance incorporates and expands on these in the context of conversation design.

Stay casual and natural

Shape the bot's side of the conversation

One great tip is to say your content out loud. How does it sound? How does it flow? Anything feel off? If it’s hard to say, it’s probably not conversational.

Acknowledgments

Acknowledgements go at the beginning of a bot’s response. They signal that the bot heard the customer’s input and help the customer feel understood. They also smooth the transition from the customer’s input to the meat of the bot’s response—keeping the bot from feeling too abrupt.

Example

CUSTOMER: I’d like to upgrade my subscription.
BOT: Wonderful! Here’s how you can change your subscription...

Here the word “wonderful” creates a quick moment of understanding between the bot and the customer, and, in this case, is also a mini-celebration. You can use acknowledgements to express surprise, concern, or simply to signal understanding. There are many types, here are a few common ones.

Discourse markers

Discourse markers are similar to acknowledgements. But instead of just happening at the beginning of a response, they happen throughout a conversation. They’re less about signaling understanding and more about shaping meaning.

Discourse markers help the participants manage the flow and structure of what they’re talking about. In bot conversations, they help the customer follow what the bot is saying. They’re critical to shaping bot responses, managing customer expectations, and making things sound conversational.

Example

CUSTOMER: I’d like to upgrade my subscription.
BOT: Wonderful! So, there are a couple quick steps to upgrading. First you have to select what to upgrade to.  Then you have to update your billing info. Let’s get started!

There are lots of discourse markers for lots of situations. Some are overly formal, like “therefore,” or “ergo,” and should be avoided. Here are a few flavors.

They’re a great tool for shaping your conversations to make them more comprehensible. This is especially true for ephemeral, voice-based experiences.

Brevity and clarity

As with most content, it’s important in conversation design to keep things short. Text-based bots usually display in space-constrained chat panels with limited formatting. This makes long bot responses hard to read.

The ephemeral nature of voice-based bots puts the burden on customers to remember what was said—and people can only remember so much. 

There are 3 basic parts to bot responses:

1. Signal understanding (acknowledgement)
2. Deliver a response (body)
3. Offer an action or next step (button, pill, question)

Pare them down to their most essential. Trim off anything extra, be brutal. Adding extraneous info adds confusion. For more help, see our tips for writing small.

Following this basic structure also helps keep things clear for customers. It signals when the bot is finished and it’s their turn to take action in the conversation. 

Benefits first

Customers want instant answers. Craft bot responses that give direct answers right away. Don’t bury the lede with lots of preamble.

Actions last

Be clear when ending bot responses or conversational threads. Once the bot has given its  response, make it clear when it’s the customer’s turn to do something. There should be no ambiguity about who’s turn is next, especially in voice. Explicitly resolve one subject before starting another or stopping.

Context and conversational logic

Customers may know they’re talking to a machine, but they don’t want it to feel that way. Using context and conversational logic makes conversations flow more naturally. Context is the information the bot should carry forward or refer back to in a given conversation.

For example, if a customer initially asks about bank errors, then the bot can assume we’re talking about bank errors without constantly repeating or reconfirming that information.

With context

CUSTOMER: Help fixing bank error 103
BOT: To fix an error 103 try this… Did that work?
CUSTOMER: No
BOT: OK, try this instead

Without context

CUSTOMER: Help fixing bank error 103
BOT: To fix a bank error 103 try this… Did that work?
CUSTOMER: No
BOT: OK, another way to fix a bank error 103 is like this…

Prompts

Prompts are cues to the user that keep the conversation going. They tell users what to do next, inviting them to respond to our bot in a way that it will understand. Use them to ask for needed information, to present choices, and to confirm actions.

Bias toward action

Always lean into action wherever you can in a conversation to help drive it forward. Actions are better than suggestions, which are better than instructions. 

There is a usefulness spectrum of action value. Consider your customer’s next step and provide the appropriate action for them.

Turn taking

Signaling a user's turn to speak in the bot conversation should be obvious and generally presented as a question. If you want the user to do something, ask them explicitly. 

Engage users early on. Invite them to join the conversation as soon as possible. People have a hard time leaving questions unanswered, use that to get the info you need in your conversation.

Managing expectations

Be upfront about being a bot and set clear expectations right away. This will help define the scope of both your bot and the user, keeping things productive and mutually beneficial.

The way you ask your question will shape how it’s answered. Be mindful of how you phrase your prompt to ensure that you’ll get the answer you’re looking for—that will keep the conversation moving in a clear and understandable way.

Scoping

A prompt’s scope directly affects the type of answer you’ll receive. Use a narrow question to get singular answers and open questions to get many. It all depends on the information you need from the customer to move the conversation forward.

Seeding

Customers will reuse words they see from the bot in their responses, so be careful to use language you’re actively listening for. There is power in suggesting or seeding responses. Only use language that you want to get in return.

Simplicity

Keep conversations simple by asking one question at a time. Combined questions, or confusing yes/no questions like, “Do you mind …?” will only confuse both the bot and your user.

Presenting options

It’s important to establish trust with your customer by providing options or answers that the bot can actually perform. Be clear about the impact or consequences of each option you present—users should know exactly where they will go next. 

A quick recap or re-prompt at the end of an informational sequence can boil info down to an easy choice for the user. You can turn a whole idea into a single word that they can choose from.

Welcome messages

The bot welcome message should break-the-ice and explain how customers can use the digital assistant. It can provide insight on the scope of bot capabilities, promote engagement, and proactively offer support. It not only greets the customer, but sets the friendly, conversational tone for their entire interaction. 

Whenever possible, craft distinct first-time and return welcome messages. This helps build trust and remove redundancies.

Upselling

Our bots are meant to be helpful, valu​​ing our customer’s friendship and trust more than driving a sale. Therefore upselling should only be an option when it is helpful for a customer—if they ask for it or if they need it to complete their task.

Smalltalk

Smalltalk is where a lot of the bot’s persona shines through. Your bot should handle basics like, hello, goodbye, thank you, who are you, are you a bot? Just make sure your responses are brief and on-brand, don’t go too far off.

Listening

Listening is at the core of conversation. It creates trust and confidence in the answers the bot provides, acknowledging the answer the customer sees is correct. Matching an intent isn’t enough—you have to prove that you heard the customer, understood them, and care about what they’re saying. It's important to leave them with the feeling that they've been thoroughly heard.

Our customers have tons of different, complicated questions, often unique to their individual situation. By breaking down what they’re saying into pieces, you can simplify the various layers of what they’re trying to communicate and provide the answer to their question.

Show you heard

When users feel understood, they are 90% of the way to having a stellar bot experience. Use active listening to acknowledge you’ve heard the customer and demonstrate that the bot understands their request. 

Example

CUSTOMER: I need Form 8962.
BOT: Here’s Form 8962.

Repeating what customers say as an explicit confirmation is the simplest way to show the bot understands (but also the most heavy handed).

Listening isn’t just understanding the words a customer enters. Use data and implicit information to compensate for non-verbal/text cues we don’t have in a bot. 

Example

CUSTOMER: I need Form 8962.
BOT: You have to fill out  information about your dependents to get that form. Do you want to do that now?
CUSTOMER: Yes

Even when the bot doesn’t understand something (fallback), it’s still important to signal that you heard the customer. “I need Form 8962” could be answered with, “OK. One of our agents will reach out shortly.”

There are a number of ways you can signal that you heard the customer, and it’s OK to combine them in your bot. Take advantage of conversational tags like “OK” or “Alright” to not only demonstrate the bot’s understanding, but to keep things conversational. 

You can recall elements of the conversation when it's appropriate—within the same session or one or two exchanges after the detail is stored—but not after too much time has passed. If it's been more than 48 hours, don’t use information they gave you already. It can come off as creepy. Just ask for it again or use it without calling it out.

Remember empathy

It’s important to empathize with our customers by meeting them where they are emotionally. Respond in the same state—meet happiness with the same joy, and anger with humility and cooperation. Get a sense for the customer and fine-tune your content so that it’s both responsive to their feelings and doesn’t leave room for any negative assumptions.

Crafting intents

When you’re writing intents, consider the width and depth of the questions a customer will have. Train your intents to think about the holistic landscape and try to have meaningful variety. The more, the better. Use the phrases you want customers to use so that NLP understands.

The system matches what the customer inputs (what you’re trying to cover with your utterances) to the intent with the highest confidence score. For example, “I’m not seeing my bank transactions!” would match with a connection fix intent and generate that response.

It’s best practice to increase the priority of any follow-up intents. It will help them match contextually.

Utterances

Utterances are the specific words the customer says or types. The utterances you create should cover the breadth of the intent and the various scenarios or ways a customer might ask a question.

For example, when a customer says, “This looks wrong,” they’re really asking “How was this calculated?”

You should also extract values from an utterance to craft a better response. When a customer says “last year,” we understand that to be 2019. Take those into consideration when crafting your utterances.

When things go wrong

Failure is unavoidable, but frustration doesn't have to be. Even when the bot doesn't understand or can't handle a request, we don't abandon our customers. 

Bot failures can appear as: 

Fallbacks

A fallback is a response or action that a bot sends when the customer's input doesn't explicitly identify with one of our scripted responses. It's not practical, scalable, or even possible to predict every potential request a customer might ask the bot. So, we use fallback experiences to catch all of those things we can't match to get customers back on track. 

Fallbacks use other technologies, like search, to:

1. Help customers rephrase their question
2. Present FAQ search results
3. Connect the customer to other help, including human support

Keep smalltalk in fallbacks limited. Customers are already seeing a less-than-ideal experience. Don't make it silly by trying to be fun. Give them the tools to keep going.

When a fallback is presented, tell customers what happened and what to do. 

Errors

Errors are inevitable. Let the bot take the blame, even if the issue came from somewhere else in the technology. 

Responses should:

• Apologize
• Work to fix the relationship
• Protect the Intuit brand
• If necessary, escalate to a human to resolve the issue (see below)

Use "sorry" sparingly. Think of other ways to acknowledge the problem without causing fear. 

To learn more, check out our pattern for delivering bad news.

Escalation

Escalation for the bot means connecting the customer to one of our agents or experts. Handle the customer's response, then connect them to the Contact us flow. 

Depending on your approach, escalation happens in steps.

1. Guide customers to the pain point. For example, "I can't refund your purchase because you've already registered, but I can take you to your account to review your charges."
2. Guide customers to topics and intents. For example, "Looks like you're trying to track your tax refund. Do you want to check on your IRS or state refund?"
3. Guide customers to an agent or expert.

Interjections and segues

Interjections are things a customer says out of context with the current conversation, but are worth hearing and understanding. Build these into your conversations to limit frustrations.

Think about things customers might say that the bot should be able to understand regardless of where they are in the conversation.

Use segues to manage these transitions from one context to another (and possibly back) so customers know where they are in the conversation.

They aren't always necessary. Sometimes fulfilling the intention of the interjection and repeating the prior prompt is enough. 

Testing

Test, test, test! Before a content release, make a test plan and test all of your content with as many people as you can. The more people explore, ask, and play with your conversations, the better. Be as exhaustive as you can to uncover bugs and things you may have missed. After content is released, test again in production to make sure things are working as expected.

Voice vs text

While voice and text content may appear similar, their forms aren't interchangeable due to their different purposes for customers. Keep their content separate and focus on applying the core skills and adjusting for each type.

Differences include:

• Long voice content causes greater timeout for customers than text. 
• Numbers, abbreviations, and instructions are more obvious in text compared to voice, which are harder to hear or require confirmation.
• Text is faster to read but slower to enter vs. voice content which is quicker to respond to but more time consuming to process.

Unique to voice

Unlike other forms, voice content carries distinct qualities that separate it from text. When writing for a bot, it’s important to see that voice content is:

• Ephemeral—restrict to 2–3 options since short-term memory fails 
• More prone to error
• Unclear with inflection and tone which makes content harder to understand
• Limited in context 

Voice content needs active listening to show customers that the bot is listening and processing their requests. It requires explicit confirmation and integrates words such as “OK” or “alright” to reassure the customer. 

Develop the bot persona and feelings by introducing vocal quality—it helps create mental images. 

Formatting

In general, follow the Intuit content formatting guidelines. There are a few nuances for CUI that you can flex when writing for your bot.

Emoji

Refer to the emoji guidelines for how and when to use them. Emoji are hard to discern on small screens, so only use them to accentuate and add sentiment, not to replace words. They’re the bot’s facial expressions and gestures, not its words.

Buttons

Buttons can be used alone to take customers to a shortcut or article, or in a vertical list to help disambiguate or show options.

Always put CTAs at the end of your text, before your button(s), to prompt a clear action. For example, “Which one of these can I help you with?” followed by a list of multiple vertical buttons a customer would select from.

Message bubbles

There’s no strict character limit for message bubbles, but keep text short. 

Links

For deep links or external URLs, use actions, url cards, or vertical buttons. Don’t use in-line links. They’re hard to select and disrupt readability.

Instructions and navigation

Use similar formatting rules for instructions and navigation in CUI as you would for other content types.

Style

Bold

Follow Intuit style for general bolding principles. Here are some nuances for CUI.

Underline and italics

Don’t underline or use italics. Italic meaning or emphasis isn't always clear in CUI, and presents accessibility issues. See guidance for underlines

Punctuation

Use appropriate punctuation as you would otherwise. Follow the Intuit guidelines.

Sentence case

Always use sentence case according to our capitalization guidelines.

Response components

Use components like answer pills, cards, and vertically stacked buttons to guide the conversation and help frame the next question for the customer. Be cautious: though we want more button-tapping and interactions to help the customer, we also don't want to overload folks with too many buttons and complicate their experience. 

Message bubbles

The main text of the bot itself are message bubbles. When writing for text bubbles: 

• Use punctuation
• Keep text short
• Support emojis
• Can have line breaks and new paragraphs within the bubble
• Include bolded text

Pills

Pills are used for suggested answers. They are prefigured inputs offered by the bot that customers can easily select, or leave. They can make an experience conversational while maintaining efficiency. When writing for pills:

Vertical buttons

Vertical buttons can be used as next steps for the topic being discussed. In certain circumstances, buttons may be more helpful since they can:

Stylistically, vertical buttons (up to 5) are:

• Left-aligned
• Support emoji
• Clickable/tappable
• Persistent 
• Support internal and external URLs and postbacks
• Can include postback text that differs from button text

There are also two forms of vertical buttons: single and multiple vertical buttons. They aren’t interchangeable, but are circumstantial and selected based on context and purpose. 

Data visualization

Data is a key part to clarifying information and clearly conveying metrics with our customers. There are multiple methods to visualize data effectively.