Intervention requests give your robot the ability to request user input to determine a course of action. You can add intervention requests to your robot's logic via the Formant Agent SDK.

Selection request

You can use a selection request to prompt a user to select from a list of options (max 100).

Example

Your robot is moving along a route and detects an obstacle. It stops in its path and prompts the user, "Is this obstacle dangerous?"

If the user answers Yes, the robot holds in place for 30 seconds, and then checks its surroundings again.

If the user answers No, the robot continues along its path.

Labeling request

You can use a labeling request to prompt the user to draw a boundary around an object and provide a label for that object. You'll be able to use both the label provided by the user and the coordinates of each point of the boundary.

Example

Your robot is selecting and sorting objects from a bin. It detects several different types of objects. It prompts the user, "Draw a boundary around the object you want me to select, and give it a label."

The user draws a box around the object to select and gives it a label. Using the coordinates of the box drawn by the user, the robot determines which object to select, and sorts it according to its label.

API reference

You can find reference materials for the Formant Agent SDK in our API reference:

• POST Intervention request
• POST Intervention response

For an example of how to implement intervention requests using the Agent SDK, see this sample code on our GitHub page.

👋

If you notice an issue with this page or need help, please reach out to us! Use the 'Did this page help you?' buttons below, or get in contact with our Customer Success team via the Intercom messenger in the bottom-right corner of this page, or at [email protected].