Feature requests

If someone has a conversation with one AI Agent and is being forwarded to another one, it would be nice if the AI Agent can forward the AI Agent history too. E.g. AI Agent 1 is on the public website and forwards the conversation history when someone comes to AI Agent 2 behind a login portal.

Based on the Chat widget, the AI Agent can see on which page the website visitor is on, and use this information within the conversation.

We would like to be able to add a document as input to the AI, and receive a similar file as output from the AI. In our case this would be translating the document, based on the domain knowledge in Pulse, so that it will use our professional jargon.

Have the AI Agent only provide answers based on the knowledge added in Watermelon, without relying on OpenAI’s database for additional information. This ensures that the chatbot only shares company-approved documentation and does not generate answers from external sources. This feature would be useful for businesses that need strict control over the chatbot’s responses.

We would like to see an AI assistant that generates a suggestion that the human agent can use to compose an answer

Show multiple buttons for the end-user to choose from to start the conversation.

When using interactive tester we want to have the possibility to add a new category for the instruction.

E.g. when the AI Agent answered correctly and I always want to see this answer regarding this certain topic in next conversations, I want to give a thumbs up.