Skip to main content
This page records dated Eval Labs release and validation checkpoints. For current platform truth, see Current System State.

​
April 2026 milestone

Eval Labs became usable for active Lucia development after the custom prompt, review, tester identity, environment, browser-origin authorization, and persistence work landed.

​
April 2026 product changes

​
Custom prompt launcher

Commit:
Added:
  • fork landing page
  • custom 1–10 prompt launcher
  • saved custom suites
  • custom run history
  • runSource: custom
  • shared Review Queue reuse

​
Review completion and navigation

Commit:
Added:
  • final prompt button changes from Save & Next to Save
  • completion action area
  • top-left brand home navigation
  • clickable breadcrumbs
  • dist/ removed from Git tracking

​
Tester identity exports

Commit:
Added:
  • TesterIdentity
  • prompt-level savedBy
  • top-level exportedBy
  • reviewer identity in CSV/Markdown exports
  • Clerk identity normalization

​
Durable run-item identity

Commit:
Changed persistence to reconcile a run item by its logical position within the run instead of relying on a newly generated record identifier.

​
Durable row identity reconciliation

Commit:
Fixed durable-record collisions by reusing the existing record identity for the same logical run-item slot.

​
April 2026 environment-hardening checkpoint

​
Netlify

At this checkpoint, the deployed Eval Labs client was configured to target the Lucia Engine Development environment.

​
Render dev Engine

At this checkpoint, the Development Engine’s browser-origin policy was updated to admit the canonical Eval Labs production origin. The exact allowlist and environment control names remain private operational configuration.

​
April 2026 validation outcome

At this checkpoint, validation established:
  • the deployed Eval Labs site called the intended Development Engine
  • Engine returned 200
  • a custom prompt run succeeded
  • Supabase persistence succeeded
  • no cross-origin policy error was observed
  • no durable run-item conflict was observed in the validated bundle
  • exported identity metadata worked
This is historical checkpoint evidence, not current deployment proof. The later Development-target correction was live-verified on 2026-07-10; current proof is maintained in Current System State.

​
May 2026 readiness-gate status

At this checkpoint, custom prompt suites were the primary tool for behavior-family refinement. The gate did not constitute human Lucia-quality approval.

​
May 2026 review-layer milestone

Eval Labs gained a full layered review architecture:
  • adjudication-ready review schema
  • guided Employee Review fields
  • suggested review layer
  • Human Guidance Evaluation
  • Quick Review UX for non-expert reviewers
  • review state controls and routing
  • adjudication queue filters
  • canon-candidate workflow
  • JSON, CSV, and Markdown export parity for structured review evidence
  • lifecycle finalization
  • durable prompt-level review persistence
  • dirty/completion state preservation
  • semantic stepped rating sliders
  • native-feeling confidence bar visual design
Doctrine established at the May 2026 checkpoint:
This should be treated as a major product and Canon milestone, not a cosmetic UI change.

​
May 2026 product-surface and access milestone

Eval Labs was refined into a more complete internal product surface:
  • top app shell owned page identity
  • in-page blog-style mastheads were removed from the app
  • Custom, Auto-generated, and Controlled Batch Runner surfaces were split
  • /lucia/auto-generated became the canonical normal generated tester route
  • /lucia/automated was retained as a legacy alias
  • /analysis became the canonical Global Analysis route
  • /experiments was retained as a legacy alias
  • Single Run Analysis was added at /analysis/runs/:sessionId
  • Run rows were standardized with two-zone layout and Copy dropdown patterns
  • Copy Session ID / Copy Deep Link controls were added across key surfaces
  • Global Analysis loading was fixed to show immediately
  • role-gated owner/admin/evaluator behavior was added as the initial product gate
Historical access limitation at this milestone:
Current role and durable-authorization posture is documented in Current System State and Eval Labs Roles and Access Matrix.

​
May 2026 AI-reviewed platform readiness gate

Final gate result:
Supabase verification result:
Browser-local verification found a compact index for all 60 owned sessions, no retained full item-level payloads, and no visible other-owner or ownerless sessions in the tested context. At the May 2026 gate, this evidence established:
  • run creation
  • Lucia response capture
  • review generation
  • review persistence
  • run finalization
  • Run History truth
  • Global Analysis truth
  • Supabase/UI count agreement
  • compact browser-local continuity state
  • controlled batch lifecycle
  • no visible cross-owner local leak in the tested owner context
The May 2026 gate did not establish:
  • Lucia is human-approved
  • Lucia is ready for real operator use
  • employee rollout is complete
  • human evaluators agree with AI scoring
  • backend authorization rules are complete security proof by themselves
Read next: AI-Reviewed Platform Readiness Gate.