Cognigy

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

Interaction Panel

Learn how Interactions with your Flow work

Talk to a Flow

To talk to a Flow click the chat button in the top right corner to open the interaction panel. The interaction panel is available throughout Cognigy and will allow you to interact with your last opened Flow.

You can write a message, click send or simply press Enter. You can also speak to your Flow by clicking the microphone button. You will need to allow your browser to use your microphone. Your own messages will be displayed in grey color on the right side, whereas the AIs responses will be displayed in blue.

To clear the chat log click the Secondary action button above the chat and select Clear chat. This will clear all messages from the chat-box and it will also create and start a new session with our system. This session-restart will give you an empty context and will set the state to "default".

Input Object

The Input Object is a complex object which will be generated for each user input. Please check our Input Object documentation for more information.

Context Object

The Context Object is a complex object which you can use to store and collect data throughout a conversation. Please check our Context Object documentation for more information.

Data Input

In Cognigy AI, the user can send text and data in shape of JSON against a Flow.

You can type a message that consists out of the actual text and/or a data object (JSON) and send it into your current Flow. Your input will get displayed in the message box as well as the output that was generated by your Flow. The chat-bubbles contain additional data objects that are displayed right below your actual text-message.

The data input can be null.

If data is sent into the Flow, the Input property mode changes to either TextData (if text was also sent) or DataOnly (if not text was sent).

Data & CognigyScript


In Flow Nodes, data can be accessed via {{ci.data.key}} with property following dot-notation property.child.child.

Example

The user sends the following JSON object into the Flow:

{
    "user": {
        "id": "1234"
    }
}
  • {{ci.data.user.id}} would return 1234
  • {{ci.data.user.age}} would return (empty string) or - if used in a condition - false

Interaction Panel Settings

NLU Connector


Select the NLU Connector used to process chat input in the interaction panel.

Text to Speech


Reads out messages from the system.

Expert mode


In the Settings tab you can toggle the Expert mode switch to view the conversation in expert mode. In this mode you can see State changes as well as matched Intents and Slots found within your input.

Playbooks


Configure behavior for Playbooks

Updated 9 months ago


Interaction Panel


Learn how Interactions with your Flow work

Suggested Edits are limited on API Reference Pages

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