Product Update: Tagging (and filtering!) chatbot answers
Hey y’all — just a quick note to let you know about two recent improvements we’ve made to GeckoChat.
Tagging (and filtering) chatbot answers
It’s fantastic to see all the different areas our clients are using their chatbots in, institution-wide. But expanded usage increases the importance of staying organized — and our latest update gives clients another method to do just that… 😎
Yep, you can now add tags to your chatbot answers (and skills)!
Tags can be used for a number of different purposes:
- Any program-specific answers can be tagged accordingly, allowing those stakeholders an easy way to find answers they’re responsible for maintaining.
- Common topics can also tagged. Using filters (see below), it’s easy to group answers or skills together.
- Tags can also be used for managing user tasks within the Chat application. For example, in the image above you’ll notice tags named To Be Reviewed and Time Sensitive. This is a quick way of flagging answers that need actions — such as information that will go out of date after a certain period.
Our on-campus implementation team have plenty of experience helping teams find a tagging structure that works for them, so if you’ve any questions for them, let us know!
Of course, tagging is only one side of the coin — they’re useless without the ability to filter answers… And (drum roll, please) that’s exactly what you’re now able to do. 😍
And it’s not only tags you can filter. Filters can be created on almost a dozen answer attributes.
Filtering your answers based on Answer Success Rate or Number of Times Used, are two examples. These filters give your team a shortcut to the most actionable answers; namely those that aren’t working as well as they could be in answering student queries, and those that are used often (and which might benefit from being broken out into more granular answers).
Trigger actions based on closed conversations
Our second product update allows teams to automate certain actions whenever a conversation is closed.
Whether the conversation was closed by a human agent, or by a chatbot, you have a few options:
Use cases include:
- Sending a message to the student when the conversation has been marked as closed — and informing them of some possible next steps.
- Adding tags to the conversation. This can be useful for flagging which conversations were auto-closed by the bot, or closed at the weekends.
- Adding a specific field to the student’s contact record — handy for triggering a sync to any 3rd-party systems you may have integrated with. For example, you can flag in your CRM that a student first started a conversation with your chatbot via Twitter.
So that wraps it up for today. As always, if you have any questions on these new features please reach out and we’ll get back to you ASAP.
(Alternatively, if you haven’t implemented Chat at your institution and you’re intrigued by how the product could help — and you also love the sound of our Jonny coming to campus and helping you get set-up — reach out and set up a demo!)