This documentation page is still being written.
The Colang Playground is a prototyping environment that you can use to learn the language and design your conversational bots. Using the playground, you can create your bot models and play with them instantly, using the embedded chat widget.
Editor and webchat
The central component of the playground is the colang editor, which provides both syntax highlight and IntelliSense features like autocomplete or parameters info. On the right, you have the webchat interface, which allows you to play with your model as you're working on it.
COMING SOON: the ability to share your bots publicly for testing purposes.
One of the great features of colang is the ability to include the elements of a model into another model. The playground implements the importing semantics and allows you to include bot models in one another. For example, you can include the chitchat bot model like this:
We're currently in private beta, and we are working on exporting a colang model into various conversational AI frameworks/platforms.
- RASA NLU
- RASA Stories
We're also working on importing models designed with other tools into the playground. This will enable you to play with them and potentially enrich them with other components.
To run your colang model, the playground uses a complete stack of conversational AI components:
- Hybrid NLU: a hybrid NLU engine using a grammar-based system and a machine-learning system using RASA.
- Conversational flows engine: a conversational flows engine that implements the full semantics of the colang language.
- Knowledge graph: an in-memory graph database with support for static data import and connectors to other platforms.
- NLG: natural language generation component with support for context variables, widget templates, and contextual responses.