Skip to main content

AI-detected conversation tags

Allow Fibi to automatically set conversation tags based on conversation context, similar to how conversation attributes can currently be detected and updated by AI.

Today, tags can be applied through workflow rules such as keywords or explicit tag actions, which does not cover cases where the correct tag depends on understanding the full conversation.

What AI feature?
Status: Planned3 comments

Log in to comment and vote

Comments3

  • Markus Palm changed status to Already exists
    Team•

    Jun 30

    Pinned

    Hey, this actually shipped last week: Fibi AI Attributes

    • Slava

      •

      Jun 30

      It does works but on the conversation attribute lvl, but not sets conversation tags or allows from workflows to based on conversation set tags. We run our agents add conversation tags

      • Markus Palm

        Team•

        Jun 30

        Ah, got it. We currently recommend using Fibi AI attributes for this. These are built to be automatically detected and applied to conversations, while conversation tags are primarily meant to be manually applied by human agents, even though both can also be applied automatically through Workflows.

        Tags are usually more flexible and team-specific, whereas Attributes are designed for more consistent, system-wide classification, workflow management, and reporting.

        That's also why Fibi can collect Attributes directly from customers - for example, asking them to choose between something like "bug report" and "feature request."

        Currently, we don’t have plans to make Conversation tags automatically categorizable, as this use case is served by AI attributes.