Feature requests

If you want to add multiple tags to a chat, you'll have to do it over and over again. Useful if you can “stick” in the tag menu, so you can click on all tags at once. It would be useful for us if you can break down “main theme tags” into subtags. For example, the main theme, health, and then sub, anxiety, illness, disabilities, etc. In this way, you can make very specific analyses in the long run.

On wednesday October 8th, it was agreed that a support request could be submitted to update AI Search so that URLs would be included in answers

Improve the layout for the field data so we can see most important first

Ask the user in the end of the conversation, if the conversation was useful. They can then upvote an downvote. If they downvote there should be the option to provide more detailed feedback. There should then be an analysis in the dashboard how many people upvoted and downvoted and there should be an option to also read the feedback.

At the moment, Watermelon GPT Chat only allows users to ask a question and receive an answer in the chat window. We would love to see an improved experience where there is a single unified search field that lets users choose — via a toggle — whether they want to perform a traditional search or ask the AI Agent. Additionally, we believe it’s important that the AI’s response is presented clearly and with sufficient space, ensuring optimal readability. When sources are provided, it would be very helpful if these are displayed in a well-structured list, making it easy for users to review or verify them.

Would be great to have real-time product statuses via an XML feed.

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.