OpenDialog Docs
opendialog.aiStart BuildingTalk to an expert
  • GETTING STARTED
    • Introduction
    • Getting ready
    • Billing and plans
    • Quick Start AI Agents
      • Quick Start AI Agent
      • The "Start from Scratch" AI Agent
        • Chat Management Conversation
        • Welcome Conversation
        • Topic Conversation
        • Global No Match Conversation
        • Supporting LLM Actions
        • Semantic Classifier: Query Classifier
      • A Process Handling AI Agent
  • STEP BY STEP GUIDES
    • AI Agent Creation Overview
    • Add a new topic of discussion
    • Use knowledge sources via RAG
    • Adding a structured conversation
    • Add a 3rd party integration
    • Test and tweak your AI Agent
    • Publish your AI Agent
  • CORE CONCEPTS
    • OpenDialog Approach
      • Designing Conversational AI Agents
    • OpenDialog Platform
      • Scenarios
        • Conversations
        • Scenes
        • Turns and intents
      • Language Services
      • OpenDialog Account Management
        • Creating and managing users
        • Deleting OpenDialog account
        • Account Security
    • OpenDialog Conversation Engine
    • Contexts and attributes
      • Contexts
      • Attributes
      • Attribute Management
      • Conditions and operators
      • Composite Attributes
  • CREATE AI APPLICATIONS
    • Designing your application
      • Conversation Design
        • Conversational Patterns
          • Introduction to conversational patterns
          • Building robust assistants
            • Contextual help
            • Restart
            • End chat
            • Contextual and Global No Match
            • Contextual FAQ
          • Openings
            • Anatomy of an opening
            • Transactional openings
            • Additional information
          • Authentication
            • Components
            • Example dialog
            • Using in OpenDialog
          • Information collection
            • Components
            • Example dialog
            • Using in OpenDialog
            • Additional information
          • Recommendations
            • Components
            • Example dialog
            • Additional information
          • Extended telling
            • Components
            • Example dialog
            • Additional information
          • Repair
            • Types of repair
            • User request not understood
            • Example dialog
            • Additional information
          • Transfer
            • Components
            • Example dialog
            • Additional information
          • Closing
            • Components
            • Example dialog
            • Using in OpenDialog
            • Additional information
        • Best practices
          • Use Case
          • Subject Matter Expertise
          • Business Goals
          • User needs
            • Primary research
            • Secondary research
            • Outcome: user profile
          • Assistant personality
          • Sample dialogs
          • Conversation structure
          • API Integration Capabilities
          • NLU modeling
          • Testing strategy
          • The team
            • What does a conversation designer do
          • Select resources
      • Message Design
        • Message editor
        • Constructing Messages
        • Message Conditions
        • Messages best practices
        • Subsequent Messages - Virtual Intents
        • Using Attributes in Messages
        • Using Markdown in messages
        • Message Types
          • Text Message
          • Image Message
          • Button Message
          • Date Picker Message
          • Audio Message
          • Form Message
          • Full Page Message
          • Conversation Handover message
          • Autocomplete Message
          • Address Autocomplete Message
          • List Message
          • Rich Message
          • Location Message
          • E-Sign Message
          • File Upload Message
          • Meta Messages
            • Progress Bar Message
          • Attribute Message
      • Webchat Interface design
        • Webchat Interface Settings
        • Webchat Controls
      • Accessibility
      • Inclusive design
    • Leveraging Generative AI
      • Language Services
        • Semantic Intent Classifier
          • OpenAI
          • Azure
          • Google Gemini
          • Output attributes
        • Retrieval Augmented Generation
        • Example-based intent classification [Deprecated]
      • Interpreters
        • Available interpreters
          • OpenDialog interpreter
          • Amazon Lex interpreter
          • Google Dialogflow
            • Google Dialogflow interpreter
            • Google Dialogflow Knowledge Base
          • OpenAI interpreter
        • Using a language service interpreter
        • Interpreter Orchestration
        • Troubleshooting interpreters
      • LLM Actions
        • OpenAI
        • Azure OpenAI
        • Output attributes
        • Using conversation history (memory) in LLM actions
        • LLM Action Analytics
    • 3rd party Integrations in your application
      • Webhook actions
      • Actions from library
        • Freshdesk Action
        • Send to Email Action
        • Set Attributes Action
      • Conversation Hand-off
        • Chatwoot
    • Previewing your application
    • Launching your application
    • Monitoring your application
    • Debugging your application
    • Translating your application
    • FAQ
    • Troubleshooting and Common Problems
  • Developing With OpenDialog
    • Integrating with OpenDialog
    • Actions
      • Webhook actions
      • LLM actions
    • WebChat
      • Chat API
      • WebChat authentication
      • User Tracking
      • Load Webchat within page Element
      • How to enable JavaScript in your browser
      • SDK
        • Methods
        • Events
        • Custom Components
    • External APIs
  • Release Notes
    • Version 3 Upgrade Guide
    • Release Notes
Powered by GitBook
On this page
  • What
  • Tone blueprints
  • Consider LLMs
  • Templates
  1. CREATE AI APPLICATIONS
  2. Designing your application
  3. Conversation Design
  4. Best practices

Assistant personality

Assistant tone profile and personality

What

The language and tone used by the assistant uses exhibit a personality that we can attribute to the assistant. It has been established that personality and tone are critical in establishing trust with users and communicating in an engaging manner. As a result, it is important to carefully craft the assistant's personality and tone This personality needs to represent the brand accurately and cater to the target audience as the personality and tone of the assistant are critical in establishing trust with users and communicating in an engaging manner.

“Personality” refers to the set of characteristics that your assistant exhibits. These characteristics need to be in line with your brand, the tasks the assistant undertakes with the user and your users’ needs. For instance, an assistant's personality could be described as "playful, insightful and surprising".

“Tone” is the way in which the assistant speaks to a user. We use the dimensions of tone to define the characteristics of the personality. The tone for the personality in the example above can be defined as casual, enthusiastic and energetic. A casual tone uses contractions such as “it’s” rather than the more formal “it is”. An enthusiastic and energetic tone spurs the user on, e.g. “let’s get moving!”.

Personality

To determine personality for the assistant, we look at the product and brand principles and what type of assistant we are building.

To get access to the product and brand principles, reach out to your marketing and sales departments. If principles haven’t formally been established yet, conduct interviews across the organization to gather information.

While every organization has their own personalized brand principles, there are some commonalities based on the type of assistant (e.g. customer service assistants are helpful and friendly) and based on the industry (e.g. customer-facing healthcare assistants tend to be patient-centric, caring, knowledgeable).

Next determine what type of assistant you are building. Is the assistant:

  • An assistant - completes tasks

  • A peer - collaborates

  • An advisor - gives recommendations

  • A coach - instructs and trains using compassion

  • A challenger - consciously builds others up

Tone

Next define the tone of voice for the assistant. Tone is the way the assistant speaks to the user. It influences how the user feels about and reacts to the assistant’s messages. .

To define your assistant’s tone, draw on any existing brand and product documentation, and add brainstorming sessions as needed. Per Nielsen Norman Group (see references), the 4 primary tone dimensions are:

  • Funny versus serious

  • Formal versus casual

  • Respectful versus irreverent

  • Enthusiastic (energetic) versus matter-of-fact

Per Nielsen Norman Group (see references): “... different tones of voice on a website have measurable impacts on users’ perceptions of a brand’s friendliness, trustworthiness, and desirability. Casual, conversational, and enthusiastic tones performed best.” At an intuitive level, this may apply to chatbots as well.

Outcome: Assistant tone profile

Personality and tone can remain abstract concepts unless we translate that into actual language examples. A voice chart gathers the personality and tone information, and makes us think about details such as the vocabulary, grammar and verbosity that will reflect the personality and tone.

The personality and tone template is available here

Tone blueprints

The personality and tone of an assistant varies depending on the type of task, industry, brand voice etc. However, we can rely to some extent on blueprints, especially for healthcare and financial services.

Due to the nature of healthcare, many assistants will be nurturing, caring, helpful, kind. There is a focus on informing and projecting trustworthiness. The tone is often more formal, more serious, but that isn't always the case. For example, a mental health assistant for college students will use a less serious, more informal tone given the target audience. And because the assistant is a more like a coach, they may exhibit more energy than an assistant who helps patients confirm surgery appointments at a hospital.

Likewise, the tone in the financial sector tends to reflect trustworthiness, and professionalism, clarity, and often a certain level of expediency in completing tasks or progressing through steps of a task. The goal is to provide clear and concise information in a neutral manner. The content may be less verbose compared to the healthcare sector.

Consider LLMs

At first sight, LLMs may seem like a great option for getting personality descriptions, tone and examples. The LLM output however tends to be very generic. It can be a good starting point, especially when no internal supporting materials are available. To really reflect the brand and the situations however, human input is critical.

Templates

Include assistant tone profile.

PreviousOutcome: user profileNextSample dialogs

Last updated 2 years ago

Sample assistant tone profile