customer_support · saas · workflow
How Notion uses Custom Agents internally to automate repetitive work across teams
Notion teams spent significant time manually searching for and sharing knowledge-base answers in Slack—sometimes waiting hours for a reply—while product feedback arriving from multiple channels required constant manual effort to route, transcribe, and create tasks.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Question asked in Slack
Someone asks a question in the CX team's #cx-ask Slack channel.
Tools used
Custom AgentsNotion AIEnterprise Search
Outcome
Custom Agents now answer repeat questions instantly with source links, route feedback automatically to the right teams, and have spread across all departments—freeing teams from busywork so they can focus on complex, high-judgment work.
Results
Time savedreplies in minutes
Grounding & classification
Source type: platform led case
36 fields verified against source quotes.
agentic workflowai agentcontent generationenterprise searchknowledge searchsummarizationchat transcriptknowledge basesupport ticketmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedsoftwareemployee productivityresponse time reductiontime savedplatform led caseback office opscustomer supportincident managementit supportmarketing opsticket triageautonomous resolutionextract classify routeintake to triagerag answering