Drupal is a registered trademark of Dries Buytaert
drupal 11.3.7 Update released for Drupal core (11.3.7)! drupal 11.2.11 Update released for Drupal core (11.2.11)! drupal 10.6.7 Update released for Drupal core (10.6.7)! drupal 10.5.9 Update released for Drupal core (10.5.9)! cms 2.1.1 Update released for Drupal core (2.1.1)! drupal 11.3.6 Update released for Drupal core (11.3.6)! drupal 10.6.6 Update released for Drupal core (10.6.6)! cms 2.1.0 Update released for Drupal core (2.1.0)! bootstrap 8.x-3.40 Minor update available for theme bootstrap (8.x-3.40). menu_link_attributes 8.x-1.7 Minor update available for module menu_link_attributes (8.x-1.7). eca 3.1.1 Minor update available for module eca (3.1.1). layout_paragraphs 2.1.3 Minor update available for module layout_paragraphs (2.1.3). ai 1.3.3 Minor update available for module ai (1.3.3). ai 1.2.14 Minor update available for module ai (1.2.14). node_revision_delete 2.0.3 Minor update available for module node_revision_delete (2.0.3). moderated_content_bulk_publish 2.0.52 Minor update available for module moderated_content_bulk_publish (2.0.52). klaro 3.0.10 Minor update available for module klaro (3.0.10). klaro 3.0.9 Minor update available for module klaro (3.0.9). layout_paragraphs 2.1.2 Minor update available for module layout_paragraphs (2.1.2). geofield_map 11.1.8 Minor update available for module geofield_map (11.1.8).

rail_score

No security coverage
View on drupal.org

RAIL Score for Drupal integrates the RAIL Score API into Drupal 9, 10, and 11, giving you a production-ready evaluation layer for responsible AI content governance. Content is automatically scored across 8 RAIL dimensions on save, with configurable thresholds, compliance checks, incident tracking, and a built-in human review queue from the start.

The RAIL framework is detailed in
"RAIL in the Wild", which maps real-world responsible AI values to measurable, auditable dimensions.

The 8 RAIL Dimensions

  • Safety : prevention of harmful, toxic, or dangerous content
  • Privacy : protection of personal information and sensitive data
  • Fairness : equitable treatment across groups, no bias or discriminatory framing
  • Transparency : honest representation of reasoning, limitations, and uncertainty
  • Reliability : factual accuracy, internal consistency, appropriate calibration
  • Accountability : traceable decisions and auditable reasoning
  • Inclusivity : accessible, welcoming language for diverse users
  • User Impact : positive value delivered relative to the user's actual need

Evaluation Modes

  • Basic : fast, cost-efficient scoring on every save
  • Deep : per-dimension explanations, issue tags, and improvement suggestions

Evaluation Context

  • Domain : general, healthcare, finance, legal, education, code
  • Use case : general, chatbot, content generation, summarization, translation, code generation

Regulatory Compliance

Run compliance checks alongside every evaluation against one or more frameworks:

  • GDPR
  • CCPA
  • HIPAA
  • EU AI Act
  • India DPDP
  • India AI Governance

Telemetry and Incident Tracking

  • Every API request is logged with timing, score, cache status, and per-dimension breakdown
  • Score breaches and compliance violations automatically raise incidents with unique IDs and severity
    levels
  • Dashboard shows total requests, error rate, average duration, cache hit rate, and score distribution
  • All metrics are filterable by date range

Human Review Queue

Dimensions scoring below a configurable threshold are automatically queued for human review. The dashboard surfaces the full queue with inline Mark Reviewed and Dismiss actions

Dashboard

A single admin page at /admin/reports/rail-score provides:

  • API account usage statistics
  • Local evaluation counts, averages, and below-threshold totals
  • Recent evaluations with pass/review status
  • API telemetry with score distribution bands
  • Open incidents with inline Acknowledge and Resolve actions
  • Pending review queue with inline Mark Reviewed and Dismiss actions

Drupal AI Module Integration

When the Drupal AI module is installed and enabled in settings, two integration points become available:

  • Automatic response scoring : every response from any registered AI provider (OpenAI,
    Anthropic, Gemini, and others) is scored automatically via event subscriber
  • AI Automators plugin : scores generated field values before they are written, with an optional block-on-low-score setting

The integration is fully optional and has zero overhead when the AI module is absent.

Field Formatter

Display stored RAIL scores on any decimal, float, or integer field in four modes: badge, progress bar, text, or full widget with per-dimension breakdown.

Requirements

Activity

Total releases
6
First release
Nov 2025
Latest release
4 weeks ago
Release cadence
27 days
Stability
83% stable

Release Timeline

Releases

Version Type Release date
1.0.4 Stable Mar 21, 2026
1.0.x-dev Dev Mar 18, 2026
1.0.3 Stable Nov 18, 2025
1.0.2 Stable Nov 6, 2025
1.0.1 Stable Nov 6, 2025
1.0.0 Stable Nov 4, 2025