Smart inbox triage
Watches a shared inbox or distribution alias and classifies each incoming message: what kind of request it is, how urgent, who should own it, what (if anything) the sender wants. Routes the message to the right destination — a person, a team channel, a ticket queue — with a one-paragraph summary so the recipient doesn't have to re-read the original to know what's needed. The pattern's value comes from compressing the human triage step (currently done by someone scanning the inbox several times a day) into something that happens within seconds of arrival.
Requirements describe capabilities the pattern needs in your environment, not the vendors you must buy. Any system that fills a requirement satisfies it — that’s what makes the catalog portable across the long tail of SMB tooling.
shared_inbox_sourceThe inbox or alias being triaged. The pattern reads from here and acts on each new message.
- shared mailbox for info@, support@, hello@
- distribution list that forwards to multiple people
- alias inbox in a business email system
routing_taxonomyThe categorization the pattern uses to decide where each message goes. Specific to the client, refined over time.
- configuration file maintained by the engagement team and updated quarterly
- small admin UI inside the pattern
- internal wiki page listing the categories
routing_destinationsThe various places routed messages land. Different category, different destination.
- ticket queues in the helpdesk
- channels in team chat
- individual mailboxes with internal tags
- tasks in the project management system
sender_context_lookupIf the sender is a known customer, partner, or contact, fetch their context so routing and summary can reflect it.
- CRM lookup by email address
- customer database with relationship data
- vendor or partner directory
misroute_feedback_loopHow recipients flag that a message was misrouted. Without this, the pattern drifts and no one can tune it.
- thumbs-down button on the routed message summary
- a designated mailbox to forward misroutes to
- a Slack reaction the team uses to flag bad routing
- 01Detect a new message arriving in the shared inbox
shared_inbox_source - 02Look up sender context if available
sender_context_lookupDECISION Skip if sender_context_lookup not filled. - 03Classify the message against the routing taxonomy, identifying category, urgency, and suggested owner
routing_taxonomy - 04Generate a one-paragraph summary covering: what the sender wants, what (if any) information they provided, any urgency signal
- 05Route the message and summary to the destination per the taxonomy
routing_destinations - 06Capture misroute feedback if recipients flag the routing, log for taxonomy refinement
misroute_feedback_loop
Structured outputs this pattern produces. Other patterns and client systems can subscribe to them, which is how the catalog composes over time.
inbox_volume_signalCategorized inbox traffic over time, useful for understanding what the business is dealing with.
- operations dashboards
- team capacity planning
- marketing or product teams looking at inquiry patterns
taxonomy_drift_signalMessages that classify poorly or trigger misroute reports, surfaced as candidates for taxonomy refinement.
- taxonomy maintenance workflow
- engagement quarterly review