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
  • In-person versus remote research
  • Remote moderated versus unmoderated research
  • The research "product"
  • Choosing a method
  1. CREATE AI APPLICATIONS
  2. Designing your application
  3. Conversation Design
  4. Best practices
  5. User needs

Primary research

Primary research refers to any method of getting input directly from users. There are a number of different methods available. They all have their unique use, value, pros and cons. Consider them all a part of your research toolkit.

In-person versus remote research

In-person research is often conducted in a research lab, although there are discount methods such as hallway testing, where you stop a coworker in the hallway to ask a few questions. Advantages include that you can observe the person, the whole person and their body language, and that you can build a rapport as a researcher face-to-face. The downsides are that it is expensive and logistically complex.

Remote research has steadily been gaining ground and its popularity received a boost during COVID time. While the advantages of in-person research are not available, this method has a much wider geographical reach, no travel is required from either party, users are participating in their own environment where they likely feel comfortable and their equipment is familiar to them, and overall it is far less expensive and logistically less complex.

Remote moderated versus unmoderated research

Remote research can further be divided into moderated and unmoderated methods. Moderated interviews are typically conducted using specialized software or generic call conferencing software (e.g. Zoom, ...). Unmoderated research is done asynchronously, the participant may record a video of themselves as they complete a task using a product, or they may be answering survey questions (both multiple choice questions and open-ended questions).

The main advantage of moderated research in addition to the advantages of remote research is the ability to observe the participant (e.g. hesitations as they speak, frowning when using webcam, ...) and to ask follow-on questions based on observed behavior or participant feedback. The main disadvantages include the inability to observe and interact in real life, possible technical challenges with software, connections, audio, screen share, etc.

The advantages of unmoderated methods include a more natural environment, since participants don't feel "observed", logistically light which may make it easier to gather feedback from a larger number of participants, and fast turnaround. Disadvantages include the lack of follow-on questions or guidance to participants who are stuck or not understanding the questions or tasks, and possible lack of clarity around authenticity of the user feedback since it's done asynchronously.

The research "product"

It is entirely feasible to conduct user interviews or surveys that only ask about users' past experiences with similar products or similar situations, and their desires for future products, etc. as a set of questions.

It is also possible to have users use a product while providing feedback and answering questions. This product could be a competitor's product, in which case we call this "competitive user research". It is a great way to understand what users like and don't like in terms of features and their experience, what's missing and what's superfluous. This can be very valuable input to the design cycle. The disadvantages of competitive user research are the effort involved; each product that is reviewed is essentially a user research study on its own. Review 3 products and effort, cost and time have just tripled. It may also be difficult to recruit participants who use a specific product, depending on the nature of the product.

Choosing a method

The method of choice very much depends on the particular circumstances, including the type of product or service, the type of user you want to get feedback from, budget, timeline, etc... Further details are outside of the scope of this documentation. Consider Remote Usability Testing by Inge De Bleecker and Rebecca Okoroji or similar titles.

PreviousUser needsNextSecondary research

Last updated 1 year ago