Script Responses

Edit on GitHub

The next step after creating a multi-modal experience map is to write a script. When users express an intent and your app responds, we call this interaction a turn. Your script will represent dialog for turns defined in your experience map.

Setting the scene

Identify the starting point of your experience map and provide some context. Format contextual clues in italics.

  • What might the user be thinking about?
  • What are they trying to do?
  • Where are they currently in the flow?
  • Have they granted the necessary permissions?

Here’s an example:

The user has gone through onboarding and has their microphone on. They are familiar with using the app including voice commands. In this scenario, the app is open in the background on their phone. They are currently in the middle of a recorded run with their phone in an armband. To speak to the fitness tracker, they move their arm towards their face.

Writing a Script

Keep the context of this scene for each turn in mind when reviewing your experience map. With this in mind, repeat the following steps:

1. Select an Intent or Gesture

Give your user a clear label. Be descriptive. Specify whether this is a new or return user. Treat this like you would any other script by bolding the user’s name and following it with a colon. Use quotes to differentiate between a user’s intents and gestures. Include descriptions of what you would expect to happen on the screen in [square brackets]. Keep these broad and don’t make any specific UI decisions at this point.

Here’s an example:

RETURN USER: [Listening] “MyRunBuddy, how fast am I running?”

2. Draft a Response

Focus on the conversational aspect of your response for now. We’ll get to visual responses later. Refer to our best practices if you get stuck. Label each turn with its corresponding intent. Write any variations below each response. Note any assumptions and remaining questions below each turn.

RETURN USER: [Listening] “MyRunBuddy, how fast am I running?”
MYRUNBUDDY: [Pace] “You’re running a 9-minute mile pace.”

3. Move to the Next Intent or Gesture

Once you’ve exhausted your experience map, write turns for anything outside that flow. This is where your list of intents will come in handy.

  1. How will you respond if you weren’t able to match what the user said with an intent?
  2. If you ask a question, how will you respond if the user responds with a negative?

Your script is complete once you’ve exhausted both your experience map(s) and list of intents. Write several variations for responses where necessary. Go back to best practice rule #6 if you get stuck.

Here’s an example of a drafted script excluding visual output. We’ll get to that in a later step.

Test and Refine Your Script

Does your interaction sound human and natural? Type responses here to hear how a synthetic voice might read them. Refer to step #5 if you get stuck.

Introduce Visuals

Now that you’ve established what you’re going to say, it’s time to make UI decisions. We use Sketch to wireframe and mock up ideas. Export screens from your tool of choice and pair them with corresponding turns. Create a prototype if it’s helpful. Adobe XD is the best option we’ve found for prototyping with voice.

Need help executing? We can provide the design and linguistic support you need for your next project.

Email us for more details →