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

The Context is a JSON object which stores persistent information.

Every contact that connects to Cognigy.AI has their own Context which lives throughout the lifetime of the session. When a contact disconnects from Cognigy.AI, the Context is persisted in the database and retrieved upon reconnection.

The Flow can read from and write to the Context by saving user messages, slots, intents or any other data available throughout the session. For more information about the lifespan of the context, see the CognigyScript page.

Accessing the Context object

Flow nodes can dynamically access Context properties via Tokens or CognigyScript e.g. {{}}. The Cognigy Script used to access the context object follows the dot-notation property.child.child.


    "user": {
        "name": "Luke Skywalker"
  • {{}} would return Luke Skywalker
  • {{context.user.age}} would return (empty string) or - if used in a condition - false


Edit, Save or Reset your current Context

You can Save, Cancel or Reset the Context Object by clicking the Save, Cancel or Reset buttons in the bottom option pane of the Interaction Panel. Context manipulations will only manipulate the value(s) in your current session.

Default Context

The default context is the initial state of the context when the session starts. This can be customized to initiate variables that will be accessed and changed throughout the conversation. The default context is configured in the Flow Editor under the Settings tab.

Updated 11 months ago

What's Next



Suggested Edits are limited on API Reference Pages

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