At Intuit, we use various patterns to establish trust and move our customers through conversations with AI in a way that feels natural. This guidance gives an overview of common patterns and offers examples of how they can be used.
Trust, transparency, and control
Disclaimers
Disclaimers caution customers about the limits of what AI can do, and encourage them to review any generated content. These patterns help set consistent expectations and help protect Intuit as a brand.
Disclaimers should be:
- Short and written in plain language
- Placed contextually near AI-generated content or actions
- Calm and reassuring, not alarming or full of legal jargon
Make sure to work with a legal partner to ensure the right disclaimers are included near any AI-generated content you work on.
Examples
Bot: Here’s a summary of how your deductions were calculated.
Intuit Intelligence can make mistakes. Intuit protects privacy and adheres to responsible AI principles. How we use AI (Link to relevant policies and resources)
Review
Give customers explicit notice when work has been done by AI. Give them a chance to review before an action is taken by using the pattern “Review before [action].” This reminder should appear contextually near AI-generated content or calls to action. See also: Disclaimers
Status
Trust and accuracy are important to customers when it comes to AI experiences (this has been verified with research). Building customer trust hinges on being clear and transparent about what the model is doing, when it’s doing it, and how outputs are generated.
Processing
AI can sometimes take a minute to process a customer's request. Letting the customer know what's happening on the backend during this time helps them understand the cause of the hold up. It can also build a sense of value for the work being done on their behalf (this is called a labor illusion).
Use the "planning, doing, done" structure
- Start by describing what AI is going to do.
- Indicate progression and that something is being done, whether that’s visually or with content.
- Finish by reiterating the task AI is about to complete.
Examples
Bot: Creating your cash flow forecast…
- Reviewing past income and expenses
- Identifying seasonal trends
- Generating projections
Your forecast will be ready in a moment.
Avoid fake progress indicators. Only show steps that reflect real work being done.
Conversation flow
Errors
At some point, something is going to go wrong. An API fails to get data, or the system fails to commit changes for an automation. The generative model is down. A plug-in is down. The model timed out. All of these situations should be handled with transparency and empathy.
Responses should:
- Protect the Intuit brand
- Be transparent that something went wrong
- Offer a path to another solution, such as self-service with an article or escalation
For more, see our guidance on delivering bad news and writing errors
Front door responses and disambiguation
Front door and disambiguation responses are used to discover more about the customer’s intent, especially when they use just a string of nouns for their request (for example, “taxes” or “address”).
A front door response asks an open-ended question about what the customer wants to do.
A disambiguation response gives the customer 2–3 action options. These are used when the bot is confident the customer will choose one.
Escalation
Escalation means connecting the customer to one of our human agents or experts. Be sure to address the customer's question and why the bot can’t answer, then offer the path to the escalation.
Good escalation paths:
- Show up as an option when something is wrong, when the situation is complex and difficult to navigate (such as reconciliation), or when the customer asks for it.
- Are paired with an offer for self-service, unless the risk is high to the customer or company.
Fallback
We use fallback responses to get customers back on track when a model hasn’t been trained on a good answer.
Fallbacks use other technologies, like search, to:
- Help customers rephrase their question
- Present FAQ search results
- Connect the customer to other help, including human support
Good fallbacks should:
- Be transparent and tell customers what happened, such as, “I couldn’t find anything about that.”
- Be empathetic. The customer may be disappointed that there’s no answer.
- Offer a way to self-serve or get help another way.
- Keep small talk to a minimum. The customer still needs help.
- "Fall upwards" and suggest other things that might be close to the customer's query.
- Always provide options for customers to indicate whether their question has been answered.
How-to instructions
How-to instructions provide steps to achieve a goal. They should:
- Be brief enough to cover the key info (additional info should be in a follow-up or a link)
- Consider the room available for the platform (mobile vs. desktop)
- Be specific to the product the customer is using
- Break things into manageable chunks when steps are lengthy
- Set expectations for how long this will take if it’s a multi-response flow
- Provide a way for customers to track progress or come back later to finish if it takes longer than a few minutes
- Provide warnings that help the customer be successful, like “Once you start a transfer, it can't be canceled.”
Small talk
LLMs are generally pretty good at small talk out of the box. Small talk answers should respond to a customer’s question, but get them back on track with what they need.
Welcome
For conversational interfaces, a welcome message should break the ice and guide customers through the experience. It not only greets the customer, but sets the friendly, conversational tone for the entire interaction.
A well-designed welcome should:
- Have different first-time and return welcome messages to build trust
- Be personalized to the customer
- Contain a brief statement about what the bot can do
- Provide proactive support for the most common questions or issues