ORC-DEC-01Tier IOrchestration Topology

Routing (Classification-Dispatch)

Classify the input first, then dispatch to a specialist prompt or agent, rather than asking one generalist to handle every case.

Runtime: DecideAgentOps: Design & ScopeSee on the matrix →
ROUTING — CLASSIFICATION DISPATCH User Query Classifierintent detection Lane A · Refundsspecialist prompt Lane B · ProductRAG agent Lane C · ComplaintHITL route Default · EscalatehumanSpecialist quality per lane beats a generalist mean.
In Plain English

This page is the complete instruction page for one pattern called "Routing (Classification-Dispatch)." It explains the problem this pattern solves, the idea behind the solution, when you should (and should not) use it, and what happens afterward, both the good effects and the costs.

This matters because building AI agents is not just about making them clever. It is also about making them safe and predictable. Following a well-tested pattern like this one helps avoid common mistakes, and shows you exactly which safety rules and regulations it connects to, listed under "Standards Mesh" on this page.

Context

Queries arrive in mixed forms: refund request, product question, complaint, escalation. A single prompt tuned for all cases is worse than several prompts tuned for one each.

Problem

Generalist prompts regress to the mean across all cases.

Forces

  • Coverage of cases vs specialisation
  • Routing accuracy vs cascade errors

Solution

Classify the input by a cheap model or deterministic rules. Route to a specialist chain, agent, or prompt. Include a default lane for unclassified cases and a human-escalation lane for low-confidence classifications.

Placement

Where this pattern acts in the two lifecycles

Runtime Cognitive
01Perceive
02Reason / Plan
03Decide
04Act
05Observe
06Reflect / Learn
07Terminate

03 Decide. Tool / route / next-action selection. 7 of 61 catalogue patterns act at this stage.

AgentOps Lifecycle
01Design & Scope
02Build & Integrate
03Evaluate & Red-Team
04Deploy
05Operate & Monitor
06Iterate & Adapt
07Decommission

01 Design & Scope. Use-case assessment, autonomy tier, risk bounding. 11 of 61 catalogue patterns act at this stage.

Stages and counts from the catalogue data. The Runtime lens is the loop the agent runs each turn; the AgentOps lens is the lifecycle the team runs the agent through. See the Matrix for every pattern at each stage.

Applicability

  • Customer support
  • Inbox triage
  • Multi-intent assistants

Anti-Patterns

  • Classifier hidden in the generalist prompt
  • No default or escalation lane

Consequences

  • +Specialist quality per lane
  • +Easier to improve one lane at a time
  • −Classifier errors cascade
  • −Lane proliferation