Skip to main content
Intent classification should interpret the customer’s message. Routing should apply the support team’s rules. Keeping those responsibilities separate makes the system easier to test, audit, and improve.

​
What It Does

The intent, tagging, and routing function:
  • Reads the normalized ticket and customer context bundle
  • Classifies the primary intent and secondary topics
  • Identifies product area, urgency, sentiment, language, and missing information
  • Applies allowed categories, attributes, and helpdesk tags
  • Calculates priority and SLA risk
  • Routes the ticket to the right queue, owner, response workflow, or specialist team
  • Escalates when confidence is low or the routing consequence is sensitive
NeedDuckie component
Interpret customer languageAutonomous triage classifier agent
Restrict tags to allowed valuesWorkflow branch logic and categories
Calculate priority and SLARouting workflow
Write tags and assignmentHelpdesk app tools or custom tools
Track confidence and routing pathAttributes and analytics
Review low-confidence casesSlack escalation agent

​
Flow

​
Suggested Taxonomy

Start small. A useful first taxonomy usually has broad intent, product area, urgency, and route dimensions.
DimensionExample values
Intentaccess issue, billing question, bug report, how-to question, feature request, cancellation, complaint, account change
Product areaaccount, authentication, billing, dashboard, integration, notifications, API, mobile, data import
Urgencylow, normal, high, critical
Sentimentneutral, confused, frustrated, angry, positive
Customer segmententerprise, business, self-serve, trial, partner
Routetier 1, billing support, technical support, account management, engineering triage, trust and safety
Missing informationno account match, unclear product area, missing screenshot, missing order ID, missing reproduction steps
Avoid overfitting the first taxonomy. If reviewers cannot consistently explain the difference between two tags, start with one broader tag and split it after you have run data.

​
Classifier Output Contract

Have the classifier return structured output. The routing workflow can then validate values and apply rules. 
{
  "primary_intent": "access issue",
  "secondary_topics": ["authentication", "workspace permissions"],
  "product_area": "account",
  "urgency": "high",
  "sentiment": "frustrated",
  "missing_information": [],
  "recommended_route": "technical support",
  "confidence": 0.86,
  "reasoning_summary": "Requester can log in but cannot access a workspace after a permission change."
}

​
Routing Rules

Keep routing rules deterministic after classification.
RuleExample action
Low confidenceSend to Slack triage review before writing assignment.
Known incident matchTag as incident-related and route to incident macro or response workflow.
Priority customer and high urgencyAssign to priority queue and set elevated SLA.
Billing intentRoute to billing support unless account risk or refund approval is required.
Bug report with reproduction detailsRoute to technical support or engineering triage.
Bug report without reproduction detailsAsk for missing details before routing to engineering.
Angry sentiment and repeated contactAdd management-review attribute or route to senior support.

​
Helpdesk Writeback

Common writebacks include:
  • Tags
  • Category or custom fields
  • Priority
  • SLA policy
  • Queue or group
  • Assignee
  • Internal summary note
  • Missing-information request
  • Link to the Duckie run
Start with internal notes and shadow tags. Turn on assignment and priority writebacks only after replay testing and human review show that the routing rules are reliable.

Categories

Define the allowed classification categories.

Attributes

Track confidence, urgency, SLA risk, and route.

Autonomous Agents

Configure the triage classifier agent.

Workflows

Apply deterministic routing and writeback logic.