multiple-amethyst•2y ago
Programmatically Create Assistants
I can see how Voiceflow's API is used to manage dialog with existing agents.
I'm curious if the API can be used to spin up new agents.
1 Reply
Currently, Voiceflow's API does not support the creation of new agents programmatically. The API is primarily used for managing dialogues with existing agents.
To create a new agent, you would need to manually use the Voiceflow platform. Here's a brief walkthrough:
1. In your workspace, click the 'New Assistant' button on the top right.
2. Give your agent a name and select whether it is a 'Chat' or 'Voice' agent.
3. Once the agent is created, go to the Knowledge Base. Here you can click on 'Add Data Source' on the top right and add as many PDFs, URLs, or Text files as you want to power your agent.
4. Once you've uploaded some initial documents, press 'Preview' on the top of the screen. This will allow you to ask the Knowledge Base questions and see what the responses are.
5. Designing on Voiceflow starts at the step-level, which includes adding, editing, and connecting steps/blocks on the canvas and creating paths in your agent.
6. Once you have a basic agent, run a prototype to make sure that it works the way you intended.
Remember, the more documents you upload, the better the answers will be. There is a 10mb file limit per upload.
For more detailed information, you can refer to the following links:
- How to create an assistant
- What are Steps/Blocks