Recommendation 4.2.7:
Use a linear, time-efficient architecture for clear conversations
Benefits Users
Visual | Cognitive | Physical
Relevant W3C Guidance
Phase 1: Gather & Organize
Read More
- A blog post walking through the conversation development for a chatbot supporting a conference.
User Research
- How do users prefer to complete the task or tasks that the chatbot is going to support? Ask users to break the task down into 3-5 steps. If a step is complex, ask them to break it down again into 3-5 sub-steps. Look for patterns across users. Once a conversation pattern is designed, test is with users in a simple mockup. Can the user finish the task intuitively? Where do they get stuck?
Phase 2: Design & Implement
Design Question
-
How will your chatbot help the user focus on getting through the current task?
- Offer the user options that follow step-by-step workflows. Once the user has begun a workflow, present only content relevant to that workflow. The user should also have the option to exit the current workflow or restart.
Antipattern
- If the conversation diagram is complex or unwieldy, the scope of this chatbot may be too large. Consider narrowing the scope, then adding to the successful system once established.
Phase 3: Test & Evaluate
Ask the User
-
Are you able to steer the conversation to the topic of your choice?
- This question could be subjective or objective. This question should be asked post-study.
-
Were you able to accomplish your task with a reasonable number of commands?
- This question could be subjective or objective. This question should be asked post-study.
-
Did the task take too many steps?
- This question could be subjective or objective. This question should be asked post-study.