Skip to main content
Liorry Herisnor
Runtime state: Running in productionProduct Delivery

Model Routing Decision

Decide which tier handles a task — including the no-model tier, which is the most valuable rule in the policy.

Runtime state: Applied on every task in my own delivery workflow, including the no-model tier. It is a working practice rather than a deployed service.

Business objective
Stop overpaying on trivial work and underpowering hard work at the same time, which is what happens when one model handles everything.
Trigger
Any task about to be given to an assistant.
Inputs
  • The task and its class
  • Sensitivity classification of the data involved
  • Current spend against the tracked budget
  • Provider availability
Outputs
  • A routing decision, or a decision to use no model at all
  • Recorded spend attributed to the task class
  • A fallback route if the primary tier is unavailable

The first question is not which model

It is whether a model at all.

A large share of what I was originally sending to an assistant were factual questions about the system — which service owns this table, what does this flag default to, how many of these exist. A query, a search or a script answers those faster, for free, and exactly correctly. A model answers them approximately correctly, which is worse in every respect.

The no-model tier is the most valuable rule in this policy.

The workflow

Task to routing decision

Two gates before a tier is even considered.

  1. Approval gate

    Sensitivity classification

    Decision point: Does this involve secrets or production data? If so, it does not enter a prompt at all — regardless of tier.

  2. Approval gate

    Is this a deterministic fact?

    Decision point: Can a query, a search or a script answer this exactly? If yes, route to no model. Faster, free, and not capable of being wrong.

  3. Automated software

    Classify the task

    Extraction, summarization, mechanical transformation, architecture, security review, or production incident.

  4. Automated software

    Select the tier

    Decision point: Extraction and summarization — inexpensive. Architecture and security — strong. Production incident — premium reasoning, where cost is not a consideration.

  5. Automated software

    Check rate and budget

    Decision point: Within limits? If not, defer or downgrade — except for incidents, which are never downgraded.

  6. AI / LLM

    Execute on the selected tier

    Under an explicit token, tool-call and runtime ceiling.

  7. Monitoring / feedback

    Record spend against the task class

    Attributed spend is what turns the routing policy from a guess into something evidence can correct.

  8. Automated software

    Fallback if the tier is unavailable

    Decision point: Defined alternative per tier. Availability problems degrade the tier, never the approval boundary.

  • Automated software
  • AI / LLM
  • Approval gate
  • Monitoring / feedback

The tiers

TierTask classWhy
No modelDeterministic facts, counts, lookups, mechanical checksExactly correct, instant, free. A model can only make this worse.
InexpensiveExtraction, summarization, mechanical transformationThe task is well-specified and the output is easy to verify.
StrongArchitecture, security review, non-obvious designBeing wrong is expensive and the failure is hard to spot.
Premium reasoningProduction incidentsThe one class where cost does not enter the decision.

Decision points

  • Does this involve sensitive data? If yes, no prompt — before any tier is considered.
  • Can this be answered deterministically? The most valuable question in the policy.
  • What class of task is this?
  • Are we within rate and budget? Incidents are exempt from downgrade.
  • Is the tier available? Fall back on capability, never on approval rules.

Responsibilities

AI / LLM

  • Nothing. Routing is decided before a model is involved, and no model chooses its own tier.

Deterministic

  • Sensitivity classification.
  • The deterministic-fact test.
  • Task classification and tier selection.
  • Rate and budget checks.
  • Spend attribution.
  • Fallback selection.

Human approval points

  1. Setting the routing policy and revising it from tracked spend.
  2. Overriding a route for a specific task, which is recorded.
  3. Adjusting budget ceilings per task class.

Failure handling

FailureResponse
Task mis-routed to too weak a tierOutput quality is visibly poor; retry at a higher tier and record the correction.
Task mis-routed to too strong a tierWasted spend, caught by attribution rather than at the time.
Budget ceiling reachedDefer or downgrade — except incidents, which are never downgraded.
Primary tier unavailableDefined fallback per tier. The approval boundary never changes.
Sensitive data in a taskBlocked before context assembly. Not a routing decision at all.

Monitoring

Spend per task class, retry rate by tier, mis-routing corrections, budget exhaustion, and fallback activation. Rising corrections at a tier means the classification rules need work, not that the tier is wrong.

More workflow designs

Back to the library