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
  1. CREATE AI APPLICATIONS
  2. Designing your application
  3. Conversation Design
  4. Best practices
  5. The team

What does a conversation designer do

At a high level, a conversation designer defines and creates compelling and delightful conversational AI experiences, such as text-based chatbots and voice assistants.

For those who are familiar with the role of a UX designer, there are a number of similarities, although some aspects are specific to conversation design.

The conversation designer's involvement in the software design and development process is as follows:

  • Use case definition. Reviewer / advisor. The high level use case is defined by the product management team and is informed by user insights, business objectives and company direction.

  • User needs. Executor / advisor. Conducting user research and desk research to gain insights into the target users, their wants and needs to use as input to the conversation structure and prompt wording. In larger organizations with dedicated UX researchers, this research can be lead by UX researchers in collaboration with the conversation designer.

  • Assistant personality. Executor. Defining the assistant personality based on existing brand guidelines and brand values is an important part of conversation design. Larger organizations may have a content team that can act as an advisor.

  • Conversation structure. Executor. Defining and building the flow of the conversation.

  • Wording and sample dialogs. Executor / advisor. Prompt wording and overall . In larger organizations, a team of content professionals can take on this task. The final prompt wording generally needs review from the legal department, similar to content on the website or other digital channels.

  • Natural language understanding (NLU). Executor / advisor. Defining intents, gathering sample utterances and training the intents to build the NLU model for natural language in put. In larger organizations, a data scientist/ML engineer/AI trainer may be available to define intents and entities and train them. Given that the conversation designer uses the intents in the conversation, a close collaboration is recommended.

  • Usability testing using prototypes and beyond. Executor. Gathering user feedback iteratively to then improve the current design.

  • Advocate for conversation design and best practices to create engaging conversational experiences. Executor. Spreading awareness around conversational AI and building conversational AI products, since conversational AI and conversation design are still new to many.

Soft skills are important. Ideally, a conversation designer is a:

  • great collaborator: working with the product team, technical team and possibly third parties

  • great communicator: communicate ideas clearly, evangelize and explain what you do as a conversation designer. Exercise patience and listen to others

  • organized individual: needs to be able to manage and schedule their workload within the larger effort

  • understands the big picture: while the conversation designer's prime directive is to create compelling experiences for the user, the conversation designer must at all times consider the entire multi-channel customer experience and the strategic direction of the company

A successful conversation designer:

  • understands and has experience defining and designing digital products using a comprehensive approach including user-centered design and attention to company goals and growth

  • understands AI and how building AI products is different from building other digital experiences such as web or mobile applications

  • has a background in one or more of the following: UX, (computational) linguistics, psychology/cognitive science, writing

  • has passion for the field of conversational AI

PreviousThe teamNextSelect resources

Last updated 1 year ago