Skip to main content

Model Routing

Playbooks · LLM overview · ① Capability matrix →

Implementation guides for the LLM Blueprint. Plane ① on Agents may pin model_profile on the route row. The LLM gateway resolves that to a registry-approved endpoint. Principles: G.A.I.N LLM.

THE CLAIM

The model does not choose which model runs. Task-aware routing, abstention, and the capability matrix live on the gateway, not in the agent prompt.

Three playbooks

#PlaybookOne-line purpose
Capability matrixApproved endpoints per profile, task, data class, and region
Gateway task routingPlan vs synthesize vs classify; failover, cost caps, abstain
Canary promotionEval-gated model swap, rollback, and change records

  1. Capability matrix: version the approved pool before writing routing code
  2. Gateway task routing: filter, score, pick or abstain on every inference call
  3. Canary promotion: eval gates and rollback before a new endpoint becomes stable

Bridge reading: G.A.I.N LLM · Inference handoff · Route contract reference · Eval Reasoning plane.

What this plane decides

DecidesDoes not decide
Which approved model endpoint for this callWhich workflow or manifest (Plane ①)
Cost, latency, region, data-class constraintsWhich tool to propose (Plane ②)
Canary vs stable route for a task tierPEP verdict on side effects

Who should read what

RoleStart withThen
AI platformCapability matrix, Gateway task routingCanary promotion, G.A.I.N LLM
Domain squadCapability matrixRoute model_profile in Route contract reference
GovernanceCanary promotionModel approval, eval sign-off
SRE / FinOpsGateway task routingCost caps, SLOs, failover

① Capability matrix →