Judge Layer (Rubrics & Severity)
Prompts that fail or bypass the Gate escalate to Stage 2: The Judge. Axon sends the prompt to a fast, cost-effective reasoning model which rates the request against four independent categorical axes. These axes are passed into a deterministic lookup table that resolves the target tier.
The 4 Independent Rubric Axes
Unlike naive routers that assign arbitrary numerical scores (e.g. “severity 73/100”), Axon requires the Judge to classify the prompt along four distinct, qualitative dimensions:
Measures how far an incorrect response propagates through downstream system behavior. This is judged by systemic consequence, not simply the number of files touched.
True if an incorrect response causes real-world harm that code changes alone cannot undo: destructive data loss, financial transactions, external communications, or security/auth vulnerabilities.
The number of interdependent steps or sequential thinking required to fulfill the task correctly, evaluated independently of risk or reversibility.
Clear: Sufficient context exists to begin processing.
Unclear: Missing critical requirements (e.g. “Fix reconnect bug” vs. “Fix reconnect bug where hosts lose leaderboard view”).
If Irreversibility: True, the prompt is immediately assigned to the Frontier tier, overriding all other axes. Axon never optimizes cost or latency at the expense of irreversible real-world risk.
Deterministic Tier Mapping
The categorical axis results from the Judge are mapped directly to a model tier via a deterministic lookup table:
| Irreversible | Blast Radius | Reasoning Depth | Ambiguity | Resolved Tier |
|---|---|---|---|---|
true | any | any | any | Frontier (Veto) |
false | High | High | any | Frontier |
false | High | Medium / Low | Unclear | Frontier |
false | High | Medium / Low | Clear | Balanced |
false | Medium | High | any | Frontier |
false | Medium | Medium / Low | any | Balanced |
false | Low | High | any | Balanced |
false | Low | Medium | Unclear | Balanced |
false | Low | Low | Clear | Fast |
Judge Model Decoupling & DI
The Judge model is configured separately from the tiers. Axon decouples the classification engine using Dependency Injection:
- The classification module (
rubric.ts) never imports provider SDKs or tier configurations directly. It receives an injectedRateFn. - This enforces modular testing: you can test Judge rubric logic in isolation with mock ratings without making network requests.
- Developer Configured: The end-user of your application never chooses or sees the Judge model. If omitted from your config, Axon safely defaults to the Fast-tier model.
// Explicit Judge Configuration
const axon = new Axon({
tiers: { ... },
judge: {
model: "gemini-1.5-flash",
apiKey: process.env.GEMINI_API_KEY!,
// provider: "google" // optional: inferred automatically
},
fallbackTier: "balanced",
});