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

# Employee Onboarding Gate

<Note>
  Human onboarding is role-based. The AI-reviewed platform readiness gate proves platform lifecycle readiness, while first human cohorts still require role assignment, scoped access checks, persistence proof, and clear active-hardening caveats.
</Note>

***

## Current readiness status

```text theme={"dark"}
AI-reviewed platform readiness gate: PASSED
Human Lucia-quality approval: NOT PASSED / NOT CLAIMED
Human onboarding: ROLE-BASED / CONTROLLED
Owner/admin oversight: IMPLEMENTED
Tester lane: IMPLEMENTED
Evaluator workbench: IMPLEMENTED / ACTIVE HARDENING
Registry Diagnostics: OWNER/ADMIN DIAGNOSTIC SURFACE
Behavioral Observatory: OWNER/ADMIN LABEL SURFACE
```

***

## Required before onboarding

Human employees/evaluators should not be onboarded until:

1. AI-reviewed platform readiness gate is passed.
2. Clerk auth works for the cohort.
3. Clerk public metadata has the correct `eval_labs_role`.
4. The Clerk session token includes the role claim required by Supabase RLS.
5. The user's visible surfaces match [Eval Labs Roles and Access Matrix](/eval-labs/how-eval-labs-works/eval-labs-roles-and-access-matrix).
6. Real runs persist to Supabase and reload from the correct scoped view.
7. Owner/admin can inspect shared persisted evidence through Team Review or Global Analysis where oversight applies.
8. Human review process is clearly distinguished from AI-reviewed platform testing.
9. Behavioral Observatory persistence and access boundaries are verified before assigning saved-label work to employees.
10. Any active-hardening caveats are named before work begins.

Status as of this Canon update:

* Steps 1-4 are implemented.
* Steps 5-7 must be verified for the specific role/cohort.
* Steps 8-10 are onboarding responsibilities.

***

## Tester boundary

Tester is the entry-level prompt-testing role.

Testers can use:

* Custom Prompt Test
* Auto-generated Prompt Test

Testers cannot use Verification Check, Verification Results, Controlled Batch Runner, Team Review, Global Analysis, Registry Diagnostics, Behavioral Observatory, or owner/admin tools.

***

## Evaluator boundary

Evaluator is the full evaluator workbench role.

Evaluators can use evaluator-safe test surfaces and their own run/review/history routes.

Evaluators cannot use Team Review or Global Analysis. Those are owner/admin oversight surfaces.

Evaluator workspace polish remains active hardening; do not describe the evaluator UX as fully final while that work continues.

***

## Do not overclaim

Do not describe Eval Labs as broadly production-mature or open-access.

Do not describe Lucia as human-approved from AI-reviewed gate results.

Correct language:

```text theme={"dark"}
The platform readiness gate passed.
Human Lucia-quality approval remains pending.
Human onboarding is role-based and controlled.
Evaluator workspace polish remains active hardening.
```