> ## Documentation Index
> Fetch the complete documentation index at: https://helloluciallc.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Review Architecture

<Note>
  Eval Labs now separates fast employee judgment from senior adjudication so Lucia can learn from structured signal without letting non-expert reviewer language become training truth.
</Note>

***

## The three-layer review model

Eval Labs review is not one flat annotation step.

It is a layered judgment system:

<div className="hl-flow-v"><span>Layer 1: Employee Review</span><span>Layer 2: Escalation Routing</span><span>Layer 3: Senior Adjudication</span></div>

Each layer has a different job.

***

## Behavioral Observatory position

Behavioral Observatory adds a saved behavioral label layer beside the Review Queue workflow.

It does not erase the three-layer review model.

Use this distinction:

```text theme={"dark"}
Review Queue = score and review the prompt/response item.
Behavioral Observatory = save structured behavioral labels for the conversation.
Registry Diagnostics = inspect derived classification suggestions.
```

Behavioral Observatory labels can become useful behavioral evidence, but they should not be confused with senior adjudication or Gold Standard approval.

***

## Layer 1 — Employee Review

Employee Review captures fast human reaction.

It is designed for reviewers who may not know AI, prompting, ontologies, or model training.

Employees answer guided questions such as:

```text theme={"dark"}
Did Lucia understand what was needed?
Did Lucia give the right next move?
Did Lucia make the situation feel calmer?
Did anything feel risky, confusing, or wrong?
Should a senior reviewer look at this?
Could this teach Lucia something reusable?
```

This layer should be:

<ul className="hl-status">
  <li>simple</li>
  <li>fast</li>
  <li>structured</li>
  <li>low-friction</li>
  <li>non-technical</li>
  <li>psychologically clear</li>
</ul>

Employee reviewers should not be asked to invent labels, taxonomies, intent categories, action classes, or training language.

***

## Layer 2 — Escalation Routing

Escalation Routing converts guided review answers into workflow state.

Examples:

```text theme={"dark"}
seniorReview = true → reviewState: needs_adjudication
reusableLearning = true → canonCandidate: true
riskOrConfusion = slightly_off → reviewState: needs_review
riskOrConfusion = definitely_wrong → reviewState: needs_review
```

The important doctrine:

```text theme={"dark"}
The employee reports what they experienced.
The system routes the case.
The senior reviewer interprets meaning.
```

***

## Layer 3 — Senior Adjudication

Adjudication is the senior-review layer where canonical meaning is assigned.

Adjudication may include:

* final human labels
* final intent interpretation
* follow-through decision
* final action type
* emotional read
* owner pressure level
* reason for the final call
* reusable canon/training signal

This layer exists to prevent ontology drift.

Employees should not train Lucia directly with improvised language.

***

## Why this architecture matters

Without this separation, Eval Labs risks collecting inconsistent reviewer opinions as if they were stable training truth.

That creates:

```text theme={"dark"}
ontology drift
label noise
inconsistent training signal
reviewer fatigue
low-confidence exports
```

With this separation, Eval Labs captures simple human judgment while preserving a high-quality senior interpretation layer.

***

## Canon rule

<Warning>
  Non-expert reviewers provide signal. Senior adjudication provides meaning.
</Warning>

This is the core protection layer for scalable human evaluation.