Claudia - Feature Requests

Currently, the AI terminates the ticket abruptly when activating the N2 transfer trigger. In my scenario, we don't attend the weekend. In these cases, the AI must not transfer or close the ticket abruptly in the customer's face, after sending the message that it is going to transfer. The suggestion would be to block the N2 triggers during off-office hours and not send the transfer message, inserting a message at the beginning of the conversation or only when the customer requests a transfer, preventing escalation. Note: This is the biggest offender in our CSAT. 14%

Today only CLAudia can process files and images. The idea is that flows that require Eddie can also process files and images.

Currently, the auditing process can be complicated, mainly because when you select an action to take, it is often not the most appropriate to solve your problem. This creates waste of time and frustration. Our goal is, when identifying an error, to automatically direct it to the specific solution needed in the system, instead of offering generic solutions. Today, the standard solution only boils down to changing the content, which makes the process less efficient. With this improvement, we hope to simplify audits, saving time and reducing confusion.

Today, auditing is, for the most part, economical. And the problem with this is that, many times, most of the tickets that are audited don't have any gain; it's just a confirmation that it was correct. We already have enough data in the system and the idea is that we can suggest what to audit based on what our client would like to improve. For example: quality or retention. Once selected, we will direct you to exactly the tickets that need to be audited, which will help improve that quality or retention.

Today there are some answers that are fixed, for example, when experimenting with one of two or even the first message. Although this message is selected by our own client, it is robotized because it is always the same response. The idea is that we make these answers more flexible to humanize Claudia

We already have a Generative CX Score (Gen CX Score) in beta internally, where we can monitor the quality of a ticket. The idea is that we evolve this score after the beta and make it available for our clients to use—everything even to define audits.

Today, during the auditing process, when an edit needs to be made to content that doesn't exist or creation, it needs to be done from scratch. The idea is that we help save time and make this process more fluid, providing a suggestion for this change based on the audit carried out.

This is a specific feature for customers using Cloud Chat. Nowadays there is already a lot that is done on N2 itself, and because it is within our ecosystem, we can know what those messages are. The idea is to provide suggestions for content that N2 has to help increase retention and automation.

This is probably something that will be more feasible for Cloud Humans customers and customers who use WhatsApp. In short, we would set some rules based on analysis of when the customer returns in a very short period to talk about the same topic or not (and to have the option to automatically tell us). This is also dependent on analysis to see how much this influences CSAT and customer satisfaction.

Today CLAudia is already able to interpret photos, audios and PDFs, but she is unable to do that. The only thing it can do is send links. The idea is that we allow CLAudia to also send files (for when a specific IDS session is used). This one will still depend on technical refinement. It is possible that it will only be able to be sent to that call chat. This will depend on the technical possibility of the API of the helpdesks with whom we integrate so that this can happen.