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

Trigger Intent


The Trigger Intent feature allows you to manually trigger an Intent by writing cIntent:, followed by the desired intent name in your text input, the regular Intent mapping will be ignored.

As of Cognigy 3.4.1 you can additionally supply additional text for keyphrase parsing.

The full syntax is as follows. Note the pipe | separated text is optional, only the bold text is required. Replace the desired intent and text to parse for slots in the respective placeholders:

cIntent:intent name|text to parse for slots


Full NLU is not run

Note that full NLU logic is not run when using Trigger Intent. If the Intent named has Default Replies, or other advanced options, these are not enacted. Instead, a Flow input is always generated with the specified Intent and (optionally) the given text and derived slots.


Trigger Intent Score

The Trigger Intent feature always leads to an Intent score of 1.


You use the Trigger Intent feature by sending a text input into your Flow that starts with cIntent:. Whatever follows will be your found Intent. If you want your intent to be named myIntent you'd send the text input cIntent:myIntent (do not leave any space). Here's an example:

An Input using the Trigger Intent featureAn Input using the Trigger Intent feature

An Input using the Trigger Intent feature

You may supply additional text that will be parsed for keyphrases using the pipe operator. Here is an example that illustrates the functionality:

Updated 7 months ago

Trigger Intent

Suggested Edits are limited on API Reference Pages

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