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
  • Extended team and awareness
  • Specific skillsets
  • Conversation design
  • NLP/NLU modeling/ML
  • Engineering
  • Testing
  1. CREATE AI APPLICATIONS
  2. Designing your application
  3. Conversation Design
  4. Best practices

The team

As with any application development, it takes a lot of people and areas of expertise to define, design, build, test and launch a conversational experience. On the people side, two main factors for success are to have the right skillsets available and to have an extended team that has an understanding and awareness around conversational experiences.

Extended team and awareness

It is critical for the success of a conversational assistant that the business and executive teams have a level of understanding and awareness when it comes to conversational AI. There is a lot of hype and a lot of misinformation that can lead to unrealistic goals. When goals are not realistic, the risk of failure increases dramatically.

A product team who doesn't understand conversational experiences and the technology behind it may have a difficult time defining a product that can be successful. Similarly, a qualitative UX researcher who is not familiar with conversational experiences may not be as effective in running moderated studies (asking questions, distilling insights) as someone who has that familiarity.

Specific skillsets

Conversation design

Conversation design is an interdisciplinary field and requires an understanding of UX principles, including design, strategy, writing and research. A background in linguistics is very helpful and any background in natural language processing (NLP) and computational linguistics will help you understand the bigger picture of building conversational assistants. Knowledge of cognitive science or psychology is useful. Specifically for customer-service assistants, an understanding of customer service and call centers can be helpful, and a deep understanding of the vertical as well. Healthcare and fintech are two main areas for conversational assistants. They are heavily regulated and understanding that subject matter helps with designing appropriate conversations.

In addition to these hard skills, soft skills such as communication, accountability and collaboration are as important as they are in many other jobs.

This may seem like a daunting list of capabilities, and it is understood that a single person won't have all the hard skills. However, be prepared to be curious and learn continuously in this emerging field.

NLP/NLU modeling/ML

This is a broad category, with at its core the need for natural language understanding. Technology is fast developing in this area, and depending on the type of conversational experience additional technologies such as speech recognition in voice assistants may be required. Suffice it to say that this type of knowledge is required in a successful conversational AI deployment.

Engineering

Integrations with existing systems require engineering effort, and this can be frontend or backend engineering.

Testing

As is the case with other digital products and services, testing is critical to success. In immature technology areas such as conversational AI, this is often "forgotten", and the MVP is used to "fail fast". However, applying testing processes from software development has to become an inherent part of developing conversational experiences.

Note that in this section we are describing skillsets as roles. It is possible that a conversation designers is also responsible for NLU modeling. Or it's possible that a conversation designer only concerns themself with the conversation structure, and that other individuals are responsible for writing and NLU modeling.

PreviousTesting strategyNextWhat does a conversation designer do

Last updated 11 months ago