Your Voice in Atom

Requirement: that all users who have been typified as "Not profiled" should not be re-assigned to an agent when they type again. Instead, the customer would like them to receive an automated message stating that they don't qualify for the credit and that the conversation should then be closed. I've been reviewing different alternatives and, so far, I haven't found a viable solution: 1. Conditionals I tried to create a conditional based on typifications or labels, but it's not possible. Conditionals only allow us to evaluate the typification of the last call, so we cannot build logic based on historical typifications or conversation labels. 2. Views and trays I also checked if it could be solved using views or trays, but these don't allow filtering by end typifications (positive or negative). They only allow you to work with tracking typifications. 3. Automated tasks Automated tasks don't seem to be an option either, since their conditions are based on events such as receiving messages from the customer or agent. There is currently no condition that allows actions to be executed based on a typing.

I request that there be a button or way to be able to export my flows in a format other than JSON and that is pdf or png.

Allow the current conversation summary to be used as a variable within flowbuilder, without the need to generate it until the conversation is assigned to an agent

If you rescue, for example, with a webhook as you send it after the inbound flow so that you don't have to rebuild all the inbound in the outbound.

That the undo button also works with prompts and texts. for example: if I delete or adjust something in the formatter, if I press the arrow to undo that action, let it work too

Being able to duplicate branches and have it come with the filters applied just to change the name of the field, and not have to select each field again

Description: Inconsistent behavior was identified in the AI Summary generated for conversations coming from the same flow of the Antioquia Oncology Center (COA) client. Currently, the agent summary does not always consistently reflect all the fields collected during the conversation, especially those captured through buttons, menus, and structured flow selections. 📌 Observed scenario In some cases, the AI Summary manages to correctly reflect fields such as: type of care utility option/quote EPS However, in other similar scenarios, although the bot does correctly collect information during the conversation, the generated summary omits important operational fields and primarily prioritizes textual/cadastral information. 📌 Example of fields omitted in some cases: Type of care Requested service Study/procedure Desired time for the appointment 📌 Expected behavior If the fields were correctly provided and collected during the conversation, they should be consistently reflected in the structured section of the summary generated for the agent. 📌 Impact This affects the rapid visibility of important operational information for human agents, forcing them to manually review the entire conversation to obtain relevant context of the case.

Previously, variables were shown as small labels or pills, which made it easier to identify them.

Currently, I am unable to send audio files through Instagram using Atom. It would be beneficial if Atom could support sending audio files, as it would enhance communication capabilities on this platform.