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
  • When
  • How
  • Consider LLMs
  • Don't use LLMs
  • References
  1. CREATE AI APPLICATIONS
  2. Designing your application
  3. Conversation Design
  4. Best practices

Subject Matter Expertise

What

An important aspect of informed design is to understand the subject matter of the product or service you are designing. Many design decisions will be dependent on that knowledge.

For instance, imagine you are creating an application to refill pharmacy prescriptions. Certain medications may be referred to using different names, yet some of those names refer to the generic version of the medication, while others may be patented or branded medications. Understanding these nuances is critical in building the correct dialog flow.

Similarly, industries such as finance and health care are heavily regulated, and certain information must be gathered at specific moments in a user's interaction with a brand. This imposed rigidity is largely non-negotiable, even when it negatively impacts the user experience. Being aware of the constraints helps the designer be more efficient in the design process.

When

Consider a thorough knowledge transfer at the start of a project. Make the information available to the entire team, including product and design, engineering and QA since everyone on the team will benefit from this.

How

If the subject matter expertise in question is available in a written format, for instance in a knowledge base, share access.

Unfortunately, subject matter expertise all too often lives in the heads of people, and live real-time knowledge transfers may be necessary.

Desk research may be a helpful source, for instance an internet search or using a LLM. This type of research may yield information that is not applicable; it could be too basic, or too specific to another brand or method. Ideally, such information can be reviewed by subject matter experts for applicability.

Consider LLMs

LLMs can be helpful in getting a basic understanding of the subject matter at hand, but the information tends to be very generic. For instance, at the time of writing this (April 2023), a prompt such as: "You are designing an experience for users to get access to their health records. What specific information do you need to gather from the user in order to comply with regulations in the US?" did not generate anything more than a list of common items.

The information need to be verified and may be specific to the use case.

Don't use LLMs

Don't expect that LLM output provides a complete and specific view of the subject matter expertise or regulatory guidelines that are needed for your specific use case; use it as a starting point only.

References

PreviousUse CaseNextBusiness Goals

Last updated 1 year ago