Today, temporary attributes in Intercom are limited to the lifecycle of a single procedure. This creates friction in conversations that involve multiple procedures or handoffs, since any intermediate state is lost when switching contexts. To work around this, we currently promote short-lived data to permanent attributes, which introduces latency, adds complexity, and clutters our data model.
We’re requesting a way to make temporary attributes persist for the duration of a conversation (i.e., session-scoped), so they can be shared across procedures without needing to be written to permanent storage. This would allow us to pass state more efficiently between workflows, reduce unnecessary read/write cycles, and improve responsiveness.
A conversation-scoped attribute layer—automatically cleared when the conversation ends—would make it much easier to build fast, reliable, multi-step conversational experiences without compromising performance or data hygiene.