If you've connected an advanced AI agent to email, the AI agent can have multiple interactions with the customer over email, offering greater automation potential. For example, if a customer emails a request but leaves out key details, such as order ID, the AI agent can request the missing information before going any further.
Email conversation flows notify the AI agent when there is a new customer reply, and recognize when a human agent is needed. Using these data points, you can track reopen rates and measure automation performance for the AI agent.
This article covers the following topics:
Understanding email conversation flows
You use the dialogue builder to create conversation flows for an email AI agent, similar to creating conversation flows for a messaging AI agent. However, the available block types differ between the two types of AI agents. For details, see Available block types.
Additionally, email conversation flows support automating the first triggered use case in
every conversation. When the dialogue of the triggered use case is complete, and the ticket
won't receive any more responses from the AI agent, the tag
escalated_by_ultimate is added to the ticket to indicate that the
automation is complete.
escalated_by_ultimate tag is automatically applied in the following
scenarios:
Whenever this tag is added, the AI agent does not provide any more responses. This includes instances where a human agent manually adds the tag before the automation is complete.
Applying actions without sending a reply
Simply add actions in a reply and leave the text reply block empty. This way your email AI agent will apply actions without sending anything to your customer.
Using single-reply dialogues
Single-reply dialogues with conversation flows work the same way as without conversation flows. If nothing follows a ticket reply block in the dialogue builder, the automation is considered complete.
Using link to
While email conversation flows are limited to one use case per conversation, linking allows you to continue the conversation in another dialogue, so the link to block is not considered the end of the conversation. Even though it's the final block in the dialogue, you can link to other single- or multi-reply dialogues.
Using multiple-reply dialogues
Multiple-reply dialogues can use the additional block options available for email conversation flows, including customer messages, link to blocks, and multiple ticket replies.
These dialogues allow the AI agent to send follow-up questions to confirm the customer's intention or request missing information. Additional messages from the customer can be processed and used during the automation.
The number of blocks is not limited, but it's a good idea to use no more than three messages to gather the required information to automate a case.
There following events are supported for advanced AI agents for email, and can be triggered in multiple-reply scenarios:
- Ticket received by AI agents - Advanced: This event is triggered only once per conversation, when the first customer message is received.
- Ticket processed by AI agents - Advanced: This event and the related actions are triggered with each ticket reply.
- Ticket reply delay events: The delay events are triggered for each reply. When using delays with email conversation flows, don't set long reply delays, but consider reply delays of 10-30 minutes.
Escalating from a multiple-reply dialogue
When escalation is needed in a multiple-reply scenario, following the customer message or conditional block, you can add an empty ticket reply block. The empty reply adds the escalation tag to the ticket, can trigger additional actions, and does not send a reply to your customer so a live agent can take over.
Limitations for email conversation flows
Email conversation flows have the following limitations:
- Automation is limited to one use case per conversation
- No rule-based escalations
- No AI agent replies to tickets older than three days