Cognigy.AI Docs

COGNIGY.AI is the Conversational AI Platform focused on the needs of large enterprises to develop, deploy and run Conversational AI’s on any conversational channel.

Given the arising need of voice interfaces as the most natural way of communicating with brands, Cognigy was founded in 2016 by Sascha Poggemann and Phil Heltewig. Our mission: to enable all devices and applications to intelligently communicate with their users via naturally spoken or written dialogue.

Get Started

Intent Hierarchy

The intent training module includes a Hierarchy feature that enable intent grouping and layering. This means that parent intents are created which can inherit the example sentences from child intents to provide more flexibility to the agent's understanding and increase the chances of the correct intent being identified.


Intents are added as children by dragging and dropping on the parent intent via the intent list.

Intents can be structured into three layers:

  • Parent Intents
  • Child Intents
  • Grandchild Intents


Tip: Use Intent Naming Conventions

It is recommended to follow a pattern when naming your intents. Either create a topic category name or use a numbering system to group intent families.

Parent Intents can inherit Example Sentences from their child Intents, which can inherit Example Sentences from the grandchild Intents.


Enable the "Inherit Example Sentences from Child Intents" slider for each intent to incorporate the example sentences of all child intents in the training model.

When an inherited example sentence is found, both the parent and the child intent will score a high intent mapping result but the child intent will be placed in the input.intent property. Find the parent as an additional high scoring intent in the input.nlu.intentMapperResults.scores array.


Inheritance is not mandatory

Inheritance of child intents is not required to use intent hierarchy. Layering can simply be used to group larger intent databases for ease of maintenance.

Updated 10 months ago

Intent Hierarchy

Suggested Edits are limited on API Reference Pages

You can only suggest edits to Markdown body content, but not to the API spec.