🗳️ Riksdagsmonitor

Swedish Parliament Intelligence Platform - Monitor political activity with systematic transparency

🎯 Mission

Riksdagsmonitor is a comprehensive intelligence platform for monitoring political activity in Sweden's Riksdag (Parliament). Built on the Citizen Intelligence Agency (CIA) platform, we provide systematic transparency through real-time analysis and 50+ years of historical data.

Swedish Parliament Intelligence Platform monitoring political activity in Sweden's Riksdag with systematic transparency through real-time analysis and 50+ years of historical data (1971-2024).

🌐 Official Website • 📂 Repository • ✨ Features • 📚 Documentation

📊 Quality Metrics

CI/CD & Security

Testing

Documentation & Release

Compliance & Standards

Security Policy: Per Secure Development Policy, we maintain defense-in-depth architecture with comprehensive security controls and documentation. See WORKFLOWS.md for complete CI/CD pipeline documentation and SECURITY_ARCHITECTURE.md for security controls.

📊 Project Classification

Riksdagsmonitor follows Hack23 AB's comprehensive Classification Framework for security, business continuity, and impact analysis:

🎯 Project Classification

🔒 Security Classification (CIA Triad)

Confidentiality: Public - All information intentionally disclosed (Swedish Riksdag open data, website content)
Integrity: High - Automated validation, digital signatures (Git commits), accurate political data required
Availability: High - 99.998% design availability target (underpinned by AWS CloudFront 99.9% SLA), automated failover (AWS multi-region, GitHub Pages DR)

🏷️ Privacy Classification

Personal Data (Public Officials): This project processes personal data about public officials (e.g., names, roles, voting records, person identifiers) sourced from Swedish Riksdag open data and the Citizen Intelligence Agency (CIA) datasets. Data relates only to MPs and other public figures acting in their official capacity; no special-category data or data about private individuals is processed. GDPR applies, with processing based on public-interest and legitimate-interest grounds for transparency and democratic accountability.

⏱️ Business Continuity Classification

RTO (Recovery Time Objective): 1-4 hours - Automated multi-region failover (AWS CloudFront + S3 us-east-1 primary, eu-west-1 replica, GitHub Pages DR)
RPO (Recovery Point Objective): 4-24 hours - Daily data pipeline updates, Git version control, S3 versioning

💰 Business Impact Analysis

Impact Category	Level	Description
Financial		Minimal financial impact (<$500 daily) - Open-source project, no revenue dependency
Operational		Partial service impact - Swedish political transparency temporarily unavailable
Reputational		Industry attention - Transparency advocates may notice outage
Regulatory		No regulatory impact - Public information dissemination only

📋 Data Classification Levels

For operational data handling, we use a simplified 4-level scheme:

Classification	Description	Examples	Handling Requirements
🟢 Public	Information intended for public disclosure	Website content, Swedish Riksdag open data, documentation	No restrictions, published on GitHub Pages
🟡 Internal	Information for internal use only	GitHub Actions secrets, deployment credentials	GitHub organization access only, MFA required
🟠 Confidential	Sensitive business information	Not applicable to this project	N/A
🔴 Restricted	Highly sensitive information	Not applicable to this project	N/A

📦 Data Inventory

Public Data (🟢):

All website HTML/CSS content (14 languages)
Swedish Parliament data (MPs, votes, documents, committees)
Election results and statistics
Government budget and spending data
All source code and documentation

Internal Data (🟡):

GitHub Actions secrets (tokens if used; no long-lived PATs)
AWS IAM credentials (ephemeral via OIDC)
Deployment pipeline configurations

No User or Confidential Data:

❌ No user accounts or authentication
❌ No non-public or end-user personally identifiable information (PII)
✅ Only public-figure data from official Swedish Parliament records (MP names, roles, votes)
❌ No financial transactions or payment data
❌ No confidential government information

🔐 Data Handling Controls

Public Data:

Published via GitHub Pages and AWS CloudFront
TLS 1.3 encryption in transit
No access controls required (intentionally public)
Version controlled via Git

Internal Data:

Stored in GitHub Secrets (encrypted at rest)
AWS credentials via OIDC (no long-lived keys)
Accessed only via secure GitHub Actions workflows
Least privilege principle enforced
Regular rotation and audit

📋 Compliance Alignment

ISO 27001:2022 A.8 - Asset Management
NIST CSF 2.0 PR.DS - Data Security
CIS Controls v8.1 Control 3 - Data Protection
GDPR - Applicable for public-official data processing (public interest and legitimate interest grounds)
Hack23 Classification Framework - Full framework documentation

See SECURITY_ARCHITECTURE.md for detailed security controls.

✨ Features

349 Current MPs - Individual MP tracking and performance metrics
2,494 Historical Politicians - Complete database from 1971-2024 (50+ years)
8 Political Parties - Party performance, coalition dynamics, voting patterns
45 Risk Rules - Systematic transparency through behavioral analysis
3.5+ Million Votes - Comprehensive voting record analysis
109,000+ Documents - Parliamentary documents processed and analyzed

📦 npm Package

Install the shared TypeScript library for Swedish Parliament data visualization:

npm install riksdagsmonitor

What's Included

Theme System — Dark/light cyberpunk themes with WCAG AA contrast compliance
Chart Factory — Pre-configured Chart.js creation with responsive breakpoints and keyboard navigation
Data Loader — Resilient data fetching with retry logic, caching, and CSV/JSON parsing
DOM Utilities — Loading states, error boundaries, screen reader announcements, locale-aware formatting
Type Definitions — Full TypeScript interfaces for political data structures
Dashboard Modules — 12 specialized intelligence dashboard components
CIA Intelligence Modules — Data loaders, visualizations, and election prediction engine

Usage

// Core utilities (no dependencies required)
import { getActiveThemeColors, BREAKPOINTS, getPartyColor } from 'riksdagsmonitor';
import { loadJSON, loadCSV, createDataSource } from 'riksdagsmonitor';
import { showLoadingState, showErrorState, formatNumber, debounce } from 'riksdagsmonitor';

// Chart utilities (requires chart.js peer dependency)
import { createChart, getResponsiveOptions, initDashboardSection } from 'riksdagsmonitor/shared/chart-factory';

// Register Chart.js, D3.js, PapaParse as globals (requires peer dependencies)
import 'riksdagsmonitor/shared/register-globals';

// Individual dashboard modules
import { init as initPartyDashboard } from 'riksdagsmonitor/dashboards/party-dashboard';
import { init as initRiskDashboard } from 'riksdagsmonitor/dashboards/risk-dashboard';

// CIA intelligence modules
import { CIADataLoader } from 'riksdagsmonitor/cia/data-loader';
import { CIADashboardRenderer } from 'riksdagsmonitor/cia/visualizations';

Peer Dependencies

The core shared utilities work without any dependencies. For visualization dashboards, install the optional peer dependencies:

npm install chart.js d3 papaparse                # Required for dashboard support
npm install chartjs-plugin-annotation             # Optional — for chart annotations

Note: chartjs-plugin-annotation is loaded conditionally at runtime — dashboards work without it, but chart annotations will be unavailable.

🌐 Live Platform

Website: riksdagsmonitor.com

Available in 14 Languages:

English, Swedish, Danish, Norwegian, Finnish
German, French, Spanish, Dutch
Arabic, Hebrew, Japanese, Korean, Chinese

📊 CIA Data Products Integration

Riksdagsmonitor integrates with the CIA platform through automated data pipelines, schema validation, and daily statistics updates.

Production Database Statistics

Live Statistics (Updated Daily at 03:00 CET):

2,494 Politicians - Complete historical database (1971-2024)
349 Current MPs - Active Members of Parliament
3.5+ Million Votes - Comprehensive voting records
109,000+ Documents - Parliamentary documents processed
8,740 Committee Documents - Committee work tracked
2,308 Rule Violations - Transparency issues identified

Data Source: extraction_summary_report.csv
Update Schedule: Daily automated fetch via GitHub Actions
Last Extraction: See cia-data/production-stats.json → metadata.last_updated (updated daily)

Implementation:

scripts/load-cia-stats.js - Fetches and parses production statistics
scripts/update-stats-from-cia.js - Updates website files
.github/workflows/update-cia-stats.yml - Automated daily workflow
cia-data/production-stats.json - Cached statistics (24-hour freshness)

Schema Integration

Automated Validation - All CIA exports validated against JSON schemas
Type Safety - TypeScript type definitions for development
CI/CD Integration - Daily validation checks in GitHub Actions
Update Detection - Weekly checks for schema updates

See CIA Schema Integration Documentation for details.

Data Products

Riksdagsmonitor leverages 19 comprehensive visualization products from the CIA platform:

Intelligence Dashboards

Overview Dashboard - Complete Riksdag intelligence snapshot
Party Performance - Longitudinal party analysis and effectiveness metrics
Government Cabinet - Ministry-level performance scorecards
Election Cycle Analysis - Historical patterns and trend forecasting

Top 10 Rankings

Most Influential MPs (network analysis)
Most Productive MPs (legislative output)
Most Controversial MPs (voting patterns)
Most Absent MPs (attendance tracking)
Party Rebels (cross-party voting)
Coalition Brokers (collaboration patterns)
Rising Stars (emerging political figures)
Electoral Risk (MPs at risk)
Ethics Concerns (transparency issues)
Media Presence (public visibility)

Advanced Analytics

Committee Network Analysis - Influence mapping and assignments
Politician Career Analysis - Career trajectories and milestones
Party Longitudinal Analysis - 50+ years of party evolution

📈 Implemented Dashboards

Riksdagsmonitor currently features 4 interactive intelligence dashboards built with Chart.js and D3.js:

1. 🌡️ Seasonal Activity Patterns Dashboard

Coverage: 2002-2025 (quarterly data, 23+ years)
Visualizations: Heat maps, time series, Z-score analysis
Purpose: Track quarterly parliamentary activity patterns and detect seasonal trends
Data Source: cia-data/seasonal/view_riksdagen_seasonal_activity_patterns_sample.csv

2. 👤 Politician Dashboard

Coverage: 349 MPs with comprehensive risk and performance metrics
Visualizations: Top 10 rankings, risk profiles, influence metrics
Purpose: Individual MP tracking and transparency assessment
Data Source: cia-data/politician/*.csv

3. 🗳️ Pre-Election Monitoring Dashboard

Coverage: Q4 2023-2025 (12-15 months before 2026 election)
Visualizations: Historical comparisons, election-year patterns
Purpose: Track pre-election parliamentary activity and behavior changes
Data Source: cia-data/pre-election/*.csv

4. 🗳️ Party Performance & Effectiveness Dashboard

Coverage: 1990-2026 (37 years)
Analysis: Comprehensive party analytics across 8 Swedish political parties

Key Features:

Effectiveness Trends: Historical legislative productivity and voting consistency
Comparative Analysis: Party-by-party benchmarking
Coalition Patterns: Party alignment visualization
Momentum Indicators: Electoral trajectory with percentile benchmarks

5. 🚨 Anomaly Detection & Early Warning System

Coverage: 2002-2026 (41 quarters analyzed)
Visualizations: 6 interactive charts including timeline, Z-score distribution, heat map
Features:
- Real-time alert system for critical anomalies
- Statistical Z-score analysis (|Z| ≥ 2.0 for anomalies)
- Severity classification: CRITICAL (≥2.5), HIGH (≥2.0), MODERATE (≥1.5), LOW (<1.5)
- Anomaly types: Ballot, Document, Attendance
- Direction indicators: UNUSUALLY_HIGH, UNUSUALLY_LOW
Data Source: cia-data/seasonal/view_riksdagen_seasonal_anomaly_detection_sample.csv

Dashboard Features:

Local-first data loading (1-hour caching)
WCAG 2.1 AA accessible
14-language support
Responsive design (320px-1440px+)
CSP-compliant (SRI hashes on all CDN resources)

🔗 Data Sources

Riksdagsmonitor integrates multiple authoritative Swedish open data sources:

Swedish Parliament (Riksdagen) - Votes, documents, committee work, MP information
Swedish Election Authority - Election results, voter turnout, electoral statistics
Swedish Financial Management Authority - Government budget and spending data
World Bank Open Data - Governance (WGI), environment, and long-horizon social/education indicators
IMF Public Data - Macro, fiscal, monetary, and external-sector indicators (WEO, Fiscal Monitor, IFS) with T+5 projections — primary source for fresh macro/fiscal figures and forward-looking commentary (see analysis/imf/README.md and docs/adr/0001-adopt-imf-data-alongside-world-bank.md)

🏗️ Technical Architecture

Stack

Frontend: Static HTML/CSS with JavaScript dashboards
Build System: Vite 8 (ES modules, code splitting)
Visualization: Chart.js 4 + D3.js 7 hosted locally on CloudFront
Testing: Vitest (unit), Cypress (E2E) - 2890 tests passing
Styling: Custom CSS with cyberpunk theme, responsive design
Hosting: GitHub Pages with CloudFront CDN
CI/CD: GitHub Actions for automated testing and deployment
Data Platform: CIA OSINT platform (Java/Spring Boot backend)
Runtime: Node.js 25.x

JavaScript Architecture

8 Dashboard Modules:
- party-dashboard.js (effectiveness analytics)
- anomaly-detection-dashboard.js (statistical outliers)
- seasonal-patterns-dashboard.js (temporal trends)
- pre-election-dashboard.js (election monitoring)
- politician-dashboard.js (MP tracking)
- ministry-dashboard.js (cabinet analysis)
- election-cycle-dashboard.js (cycle patterns)
- back-to-top.js (navigation)
Data Loading: Local-first with GitHub fallback
Caching: LocalStorage with freshness checks (1-7 days)
Performance: Code splitting, lazy loading, asset optimization
Security: SRI hashes (sha384), CSP-compliant script loading

Security

HTTPS-Only: TLS 1.3 encryption enforced
Security Headers: CSP, HSTS, X-Frame-Options, X-Content-Type-Options
Access Control: GitHub MFA, SSH keys, GPG commit signing
Monitoring: Dependabot, CodeQL, Secret Scanning
Documentation: SECURITY_ARCHITECTURE.md, THREAT_MODEL.md

🔐 Commitment to Transparency and Security

At Hack23 AB, we believe that true security comes through transparency and demonstrable practices. Our Information Security Management System (ISMS) is publicly available, showcasing our commitment to security excellence and organizational transparency.

📋 ISMS Compliance

ISO 27001:2022 Aligned

🛡️ Security Documentation

Defense-in-Depth Architecture

Compliance Frameworks

ISO 27001:2022 - Information security management controls (7 controls implemented)
NIST CSF 2.0 - Cybersecurity framework (6 functions aligned)
CIS Controls v8.1 - Security best practices (6 controls implemented)

Security Metrics

Metric	Status	Details
Risk Level	🟢 LOW	5.52/10.0 (99.7% risk reduction)
HTML Validation	✅ PASSED	0 errors (HTMLHint)
Dependencies	✅ CLEAN	Dependabot monitoring
Secrets	✅ SECURE	Secret scanning enabled
Code Scanning	✅ ACTIVE	CodeQL analysis

🚀 Development

Prerequisites

Node.js: 25.x or higher
npm: 10.x or higher (comes with Node.js)
Git with GPG signing configured
GitHub account with MFA enabled
SSH keys for GitHub authentication

Local Development

# Clone repository
git clone [email protected]:Hack23/riksdagsmonitor.git
cd riksdagsmonitor

# Install dependencies
npm install

# Development server with Vite (hot reload)
npm run dev
# Opens http://localhost:8080

# OR serve statically
python3 -m http.server 8080
# or
npx http-server -p 8080

# Open in browser
open http://localhost:8080

Testing

# Install dependencies (if not already done)
npm install

# Run unit tests (Vitest)
npm test

# Run tests in watch mode
npm run test:watch

# Run tests with coverage
npm run test:coverage

# Run tests with UI
npm run test:ui

# Run E2E tests (Cypress)
npm run cypress:open    # Interactive GUI
npm run cypress:run     # Headless

# Full E2E test suite
npm run e2e            # Builds, previews, and runs Cypress

Building for Production

# Build with Vite
npm run build

# Preview production build
npm run preview
# Opens http://localhost:4173

# Build output in dist/
ls dist/

Quality Checks

# HTML validation
npm run htmlhint

# Link checking
python3 -m http.server 8080 &
npm run linkcheck

# Run all quality checks
npm run htmlhint && npm test && npm run build

CI/CD Pipeline

Automated Checks:

HTML validation (HTMLHint)
Link checking (linkinator)
JavaScript testing (Vitest unit tests - 2890 tests)
E2E testing (Cypress)
Build validation (Vite)
Dependency review (Dependabot)
Security scanning (CodeQL, Secret Scanning)

Workflows:

.github/workflows/quality-checks.yml - HTML/link validation
.github/workflows/javascript-testing.yml - Vite build, Vitest, Cypress E2E
.github/workflows/dependency-review.yml - Dependency security
.github/workflows/copilot-setup-steps.yml - Copilot agent setup
.github/workflows/release.yml - Release with attestations and documentation-as-code

Test Results:

✅ 2890/2890 unit tests passing (Vitest)
✅ 100% test pass rate
✅ Coverage: 70% lines, 70% functions, 60% branches

🚀 Release Process

Riksdagsmonitor follows a comprehensive release process with full supply chain security:

Release Workflow

Trigger: Manual (workflow_dispatch) or tag push (v*..)
Duration: ~20-30 minutes
Jobs: Prepare → Build → Release

Release Artifacts

Each release includes:

✅ Production build (riksdagsmonitor-vX.Y.Z.zip)
✅ SHA-256 checksum for verification
✅ SBOM in SPDX format (Software Bill of Materials)
✅ SLSA Build Provenance attestations (signed)

Documentation as Code

Every release automatically generates and publishes:

📚 API Documentation (JSDoc)
📊 Test Coverage Report (Vitest)
🧪 E2E Test Reports (Cypress)
📦 Dependency Tree (npm)

Documentation Hub: riksdagsmonitor.com/docs/

Dual Deployment

Primary: AWS S3/CloudFront (https://riksdagsmonitor.com)
Backup: GitHub Pages (disaster recovery)

Security & Verification

Verify attestations using GitHub CLI:

gh attestation verify riksdagsmonitor-v1.0.0.zip -R Hack23/riksdagsmonitor

Full Release Guide: See RELEASE_PROCESS.md

📖 Documentation

Project Documentation

README.md - This file
RELEASE_PROCESS.md - Comprehensive release guide with attestations ✨ NEW
TRANSLATION_GUIDE.md - Multi-language translation standards and glossary
SECURITY.md - Security policy and vulnerability reporting ✨ NEW
CONTRIBUTING.md - Contribution guidelines ✨ NEW
CODE_OF_CONDUCT.md - Community standards ✨ NEW
LICENSE - Apache License 2.0

Architecture Documentation Portfolio

Current State	Future State
🏗️ Architecture	🚀 Future Architecture
📊 Data Model	📊 Future Data Model
🔄 Flowcharts	🔄 Future Flowcharts
🔄 State Diagrams	🔄 Future State Diagrams
🗺️ Mindmap	🗺️ Future Mindmap
💼 SWOT	💼 Future SWOT

Security Documentation

🛡️ Security Architecture - Defense-in-depth security controls
🔮 Future Security Architecture - Security roadmap
🎯 Threat Model - STRIDE threat analysis and risk assessment
🛡️ CRA Assessment - EU Cyber Resilience Act conformity
🔧 Workflows - CI/CD workflows and automation
🔐 Security Policy - Vulnerability reporting and disclosure

ISMS Policy Alignment

🛡️ Secure Development Policy — Architecture documentation requirements
🔓 Open Source Policy — OSS governance, license compliance, security posture evidence
🛡️ CRA Conformity Assessment Process — CRA self-assessment template and methodology
🎯 Threat Modeling Policy — STRIDE/MITRE ATT&CK methodology
🏷️ Classification Framework — CIA triad, RTO/RPO, business impact

GitHub Copilot Integration

Riksdagsmonitor uses GitHub Copilot personas, skills, and agentic workflows as first-class automation. The directory READMEs are the single source of truth; AGENTS.md and SKILLS.md are the long-form reference catalogs.

.github/agents/README.md — 24 agent files (14 persona agents + 9 workflow-specialist .agent.md + shared developer.instructions.md)
.github/skills/README.md — 91 skills grouped by 12 functional categories
.github/prompts/README.md — 8 bounded-context prompt modules + Tier-C extension, imported by every agentic news workflow
.github/workflows/README.md — 45 workflow files (standard + agentic)
AGENTS.md — canonical persona catalog with skill-mapping tables and invocation examples
SKILLS.md — canonical skill catalog with agent-skill mappings

14 Persona Agents (assignable via assign_copilot_to_issue):

security-architect · documentation-architect · quality-engineer · frontend-specialist · isms-compliance-manager · deployment-specialist · devops-engineer · intelligence-operative · news-journalist · content-generator · data-pipeline-specialist · data-visualization-specialist · task-agent · ui-enhancement-specialist

9 Workflow-Specialist Agents (.agent.md, invoked by name from workflows): agentic-workflows · ci-cleaner · contribution-checker · create-safe-output-type · custom-engine-implementation · grumpy-reviewer · interactive-agent-designer · technical-doc-writer · w3c-specification-writer

Available Skills (91) — see .github/skills/README.md for the complete catalog across:

🛡️ Core Infrastructure & Governance (9) · 🕵️ Political Intelligence (11) · 🔐 ISMS & Security (14)
⚙️ Development & Operations (14) · 🧪 Testing & QA (2) · 🎨 UI/UX & Design (8)
📡 Data Integration (6) · 📰 Journalism & Media (5) · 🏛️ Government, Regulatory & Economics (7)
🗣️ Language & Localization (1) · 🤖 GitHub Agentic Workflows (13) · 📋 Copilot Patterns (1)

Economic-Data Integrations (three primary sources, parity-treated):

scb-mcp (@jarib/[email protected]) — official Swedish statistics via PxWebAPI 2.0 (1,200+ tables)
world-bank-mcp ([email protected]) + scripts/world-bank-client.ts — WGI governance, environment, long-horizon social/education
IMF TypeScript client (scripts/imf-client.ts) — WEO, Fiscal Monitor, IFS, GFS_COFOG via Datamapper JSON + SDMX 3.0; macro/fiscal freshness + T+5 projections. Intentionally not an MCP server — pure-TS, fully covered by the npm SBOM (ADR 0001).

External Documentation

🔬 Political Intelligence Analysis & News Creation

Riksdagsmonitor is built around two tightly-coupled product lines: deep political intelligence analysis and autonomous news article creation. Every news article is backed by a reproducible analysis artifact trail on disk.

End-to-end pipeline

flowchart LR
  A[📥 MCP + CIA + SCB + IMF<br/>data download] --> B[📐 Apply methodology<br/>analysis/methodologies]
  B --> C[📋 Populate templates<br/>analysis/templates]
  C --> D[📂 Write 9 or 14 artifacts<br/>analysis/daily/$DATE/$SUBFOLDER]
  D --> E{🚦 Analysis Gate<br/>prompts/05}
  E -- pass --> F[📰 Generate article<br/>prompts/06]
  E -- fail --> C
  F --> G[🌐 Translate into<br/>remaining 12 languages]
  G --> H[🔀 One PR per article type<br/>prompts/07]
  style A fill:#0a0e27,stroke:#00d9ff,color:#e0e0e0
  style E fill:#dc3545,stroke:#b02a37,color:#fff
  style H fill:#1a1e3d,stroke:#ffbe0b,color:#e0e0e0

Vital documents

Area	Document	What you'll find
Analysis framework	`analysis/README.md`	Artifact taxonomy, 9-artifact / 14-artifact contract, daily-output layout
Methodology library	`analysis/methodologies/README.md`	11 methodology documents (AI-driven guide, per-document protocol, risk/SWOT/threat frameworks, synthesis, electoral, classification, style)
Template library	`analysis/templates/README.md`	23 templates — 8 core single-type (T1–T8) + 15 extended/Tier-C (scenario, executive-brief, coalition-mathematics, election-2026, historical-parallels, comparative-international, devil's advocate, etc.)
News-generation contract	`.github/prompts/README.md`	8 bounded-context prompt modules + Tier-C extension; single blocking analysis gate
Workflow orchestration	`.github/workflows/README.md` + `WORKFLOWS.md` §Stage 6.1	How each `news-*.md` source compiles to a hardened `.lock.yml` with SHA-pinned actions, egress firewall, and five-layer safe-outputs
Specialist personas	`.github/agents/README.md`	`intelligence-operative`, `news-journalist`, `content-generator` — and 11 more
Rules that guide the agents	`.github/skills/README.md`	11 political-intelligence skills + 5 journalism skills + 14 ISMS/security skills

Data sources used during analysis

Riksdagen & Regeringen via riksdag-regering-mcp (32 tools): MPs, votes, documents, speeches, committees, government docs
Statistics Sweden (SCB) via @jarib/[email protected] (1 200+ PxWeb tables)
World Bank Open Data via [email protected] + scripts/world-bank-client.ts (WGI governance, environment, education)
IMF via scripts/imf-client.ts (pure-TS, WEO + Fiscal Monitor + IFS + GFS_COFOG, T+5 projections)
CIA platform (Hack23) — 19 visualisation products consumed nightly via update-cia-csv-data.yml

🤖 AI-Disrupted News Generation

"While traditional newsrooms debate whether AI will replace journalists, Riksdagsmonitor already runs a fully autonomous political intelligence newsroom — 12 agentic workflows, 14 languages, zero human editors, and a publication schedule that would bankrupt any legacy outlet trying to keep up."

Riksdagsmonitor's agentic news generation pipeline is the world's first fully AI-driven political intelligence newsroom for parliamentary monitoring. Powered by Claude Opus (currently 4.7) via GitHub Copilot Coding Agent, our 12 specialized workflows (11 scheduled + 1 on-demand, plus 1 dedicated translation workflow) autonomously produce deep political analysis — not shallow summaries, but structured intelligence products with source verification, multi-party balance, and GDPR-compliant OSINT methodology.

📚 Directory-level catalogs (single sources of truth):

.github/workflows/README.md — 45 workflow files (21 standard .yml + 12 agentic .md sources + 12 compiled .lock.yml)

.github/prompts/README.md — 8 bounded-context prompt modules + ext/tier-c-aggregation.md, imported by every news workflow

.github/agents/README.md — 24 Copilot agent files (14 personas + 9 workflow-specialists + 1 shared developer-instructions)

.github/skills/README.md — 91 skills grouped by 12 functional categories

analysis/README.md — on-disk artifact layout (analysis/daily/$ARTICLE_DATE/$SUBFOLDER/) with 9-artifact / 14-artifact contracts

analysis/methodologies/README.md — 11 methodology documents

analysis/templates/README.md — 23 canonical output templates (8 core single-type + 15 extended / Tier-C)

WORKFLOWS.md — canonical end-to-end reference (v7.2, includes Stage 6.1 Agentic Workflow Structure & Prompt Imports)

Autonomous Publication Schedule

Every day, the platform's AI operatives awaken on cron schedules, query the Swedish Parliament's open data via 32 MCP tools, cross-reference government sources, and generate publication-ready intelligence articles in 14 languages — including RTL support for Arabic and Hebrew.

Time (UTC)	Workflow	Coverage	Frequency
🌅 04:00	Committee Reports	Utskottsbetänkanden analysis, voting breakdowns	Mon–Fri
🌅 05:00	Propositions	Government bills, legislative impact assessment	Mon–Fri
☀️ 06:00	Motions	Opposition proposals, party strategy decoding	Mon–Fri
❓ 07:00	Interpellations	Ministerial accountability, evasion detection	Mon–Fri
🔮 07:00	Week Ahead	Parliamentary calendar preview, agenda intelligence	Friday
📅 08:00	Month Ahead	Strategic outlook, coalition forecasting	1st of month
🔍 10:00 & 14:00 (Mon–Fri); 12:00 (Sat/Sun)	Realtime Monitor	Breaking political developments, flash analysis	Mon–Fri (×2) + weekends
🌍 11:00 & 17:00 (Mon–Fri); 14:00 (Sat/Sun)	Translate	12 additional languages from EN/SV cores	Daily
🌆 18:00 (16:00 Sat)	Evening Analysis	Deep-dive intelligence synthesis	Mon–Sat
📊 09:00	Weekly Review	Week-in-review scorecard, party performance	Saturday
📈 10:00	Monthly Review	Comprehensive monthly intelligence assessment	28th of month
🔧 Manual	Article Generator	On-demand article generation / backfill	On-demand

All times are UTC (GitHub Actions cron). For local time, convert to CET/CEST. Authoritative schedules defined in .github/workflows/news-*.lock.yml workflows — see .github/workflows/README.md for the complete inventory.

Result: Dozens of articles per week across 14 languages — delivering hundreds of localized intelligence products each month, generated autonomously with zero editorial intervention.

🧠 Why This Is Different

Traditional AI-generated news is shallow — it rewrites press releases. Riksdagsmonitor's agentic pipeline performs deep political intelligence analysis:

🔎 Source verification: Every claim traced to official Riksdag/Regering data via MCP
⚖️ Multi-party balance: Algorithmic fairness across all 8 parliamentary parties
📊 Quantitative rigor: Voting cohesion metrics, attendance scoring, legislative productivity indices
🌐 14-language reach: Native-quality political analysis — not machine translation, but culturally adapted intelligence
🛡️ GDPR-compliant OSINT: Only public parliamentary data, with privacy-by-design architecture
🧪 Quality gates: HTMLHint validation, link checking, accessibility compliance (WCAG 2.1 AA) — every article passes CI before publication

🔮 Future Roadmap: 2026–2037

From agentic news generation to AGI-powered democratic intelligence — the 11-year evolution of Riksdagsmonitor.

📋 Detailed planning: Future Workflows · Future Mindmap

Evolution Overview

%%{init: {"theme": "dark", "themeVariables": {"primaryColor": "#00d9ff", "primaryTextColor": "#e0e0e0", "primaryBorderColor": "#ff006e", "lineColor": "#ffbe0b", "secondaryColor": "#1a1e3d", "tertiaryColor": "#0a0e27", "background": "#0a0e27"}}}%%
timeline
    title Riksdagsmonitor Evolution — 2026 to 2037
    section Phase 3 — Foundation (2026)
        Q1-Q2 : TypeScript migration ✅
               : 12 agentic news workflows ✅
               : 34 GitHub Actions workflows + 10 agent prompt files
               : Dual deployment (S3 + GitHub Pages)
        Q3-Q4 : CIA data pipeline integration
               : Predictive dashboards
               : 14-language expansion
               : 40 GitHub Actions workflows + 10 agent prompt files
    section Phase 4 — Intelligence (2027-2029)
        2027 : Real-time data streams
             : ML prediction models
             : Multi-source OSINT
             : Nordic parliament expansion
        2028 : Multi-modal content (audio/video)
             : Self-healing pipelines
             : AI editorial board
             : 65 automation assets
        2029 : Fully autonomous pipeline
             : Expert-level analysis
             : API platform launch
             : 75 automation assets
    section Phase 5 — Scale (2030-2033)
        2030-2031 : EU-wide coverage
                  : 85+ automation assets
                  : Near-expert analysis
                  : Sovereign AI evaluation
        2032-2033 : Global parliamentary monitoring
                  : 100 automation assets
                  : Pre-AGI capabilities
                  : Every UN language
    section Phase 6 — AGI Era (2034-2037)
        2034-2035 : AGI-enhanced intelligence
                  : 195 parliaments monitored
                  : Predictive governance
                  : 110+ automation assets
        2036-2037 : Transformative democracy platform
                  : 120+ automation assets
                  : Post-AGI capabilities
                  : Democratic safeguards architecture

Phase 3: Agentic Intelligence Foundation (2026)

Current phase — AI-disrupted news generation operational

%%{init: {"theme": "dark", "themeVariables": {"primaryColor": "#00d9ff", "primaryTextColor": "#e0e0e0", "primaryBorderColor": "#ff006e", "lineColor": "#ffbe0b", "secondaryColor": "#1a1e3d", "tertiaryColor": "#0a0e27"}}}%%
graph LR
    subgraph SGCompleted["✅ Completed"]
        style SGCompleted fill:#006400,stroke:#00d9ff,color:#e0e0e0
        A[TypeScript Migration<br/>31 modules] --> B[Agentic News Gen<br/>12 workflows]
        B --> C[14 Languages<br/>RTL support]
        C --> D[Dual Deploy<br/>S3 + GitHub Pages]
    end
    subgraph SGProgress["🔄 In Progress"]
        style SGProgress fill:#1a1e3d,stroke:#ffbe0b,color:#e0e0e0
        E[CIA Data Pipeline<br/>19 products] --> F[Predictive Dashboards<br/>Chart.js/D3.js]
        F --> G[Content Expansion<br/>Hundreds of articles/month]
    end
    subgraph SGPlanned["📋 Planned"]
        style SGPlanned fill:#0a0e27,stroke:#ff006e,color:#e0e0e0
        H[API Platform<br/>GraphQL] --> I[Nordic Expansion<br/>Denmark, Norway, Finland]
    end
    D --> E
    G --> H

Capability	Status	Details
TypeScript migration	✅ Done	31 modules, 2890 Vitest tests
Agentic news generation	✅ Live	12 workflows (11 scheduled + 1 on-demand), 14 languages
14-language support	✅ Live	Including Arabic/Hebrew RTL
CIA data integration	🔄 Active	19 visualization products
Predictive dashboards	📋 Planned	Chart.js/D3.js interactive displays

Phase 4: Predictive Intelligence & Nordic Expansion (2027–2029)

%%{init: {"theme": "dark", "themeVariables": {"primaryColor": "#00d9ff", "primaryTextColor": "#e0e0e0", "primaryBorderColor": "#ff006e", "lineColor": "#ffbe0b", "secondaryColor": "#1a1e3d", "tertiaryColor": "#0a0e27"}}}%%
graph TB
    subgraph SG2027["2027 — Predictive Analytics"]
        style SG2027 fill:#1a1e3d,stroke:#00d9ff,color:#e0e0e0
        PA1[🔮 ML Election Models<br/>Coalition probability scoring]
        PA2[📡 Real-Time Streams<br/>Live parliamentary feeds]
        PA3[🌍 Nordic Expansion<br/>DK · NO · FI parliaments]
        PA4[🔍 Multi-Source OSINT<br/>Media + social + official]
    end
    subgraph SG2028["2028 — Multi-Modal Intelligence"]
        style SG2028 fill:#1a1e3d,stroke:#ffbe0b,color:#e0e0e0
        MM1[🎙️ Audio/Video Analysis<br/>Debate tone detection]
        MM2[🤖 AI Editorial Board<br/>Autonomous quality control]
        MM3[🔧 Self-Healing Pipelines<br/>Auto-recovery workflows]
        MM4[📊 65 Automation Assets]
    end
    subgraph SG2029["2029 — Autonomous Platform"]
        style SG2029 fill:#1a1e3d,stroke:#ff006e,color:#e0e0e0
        AP1[🚀 Fully Autonomous Pipeline<br/>Zero human intervention]
        AP2[🧠 Expert-Level Analysis<br/>PhD-equivalent insight]
        AP3[🔌 API Platform Launch<br/>GraphQL + REST]
        AP4[📊 75 Automation Assets]
    end
    PA1 --> MM1
    PA2 --> MM2
    PA3 --> MM3
    PA4 --> MM4
    MM1 --> AP1
    MM2 --> AP2
    MM3 --> AP3
    MM4 --> AP4

Phase 5: EU-Wide Coverage & Pre-AGI (2030–2033)

%%{init: {"theme": "dark", "themeVariables": {"primaryColor": "#00d9ff", "primaryTextColor": "#e0e0e0", "primaryBorderColor": "#ff006e", "lineColor": "#ffbe0b", "secondaryColor": "#1a1e3d", "tertiaryColor": "#0a0e27"}}}%%
graph LR
    subgraph SGEU["2030-2031 — EU Scale"]
        style SGEU fill:#1a1e3d,stroke:#00d9ff,color:#e0e0e0
        EU1[🇪🇺 27 EU Parliaments<br/>+ European Parliament]
        EU2[🧠 Near-Expert Analysis<br/>Opus 8.x capabilities]
        EU3[📊 85+ Automation Assets<br/>Continent-wide coverage]
        EU4[🏛️ Sovereign AI Evaluation<br/>EU AI Act compliance]
    end
    subgraph SGGL["2032-2033 — Global Reach"]
        style SGGL fill:#1a1e3d,stroke:#ff006e,color:#e0e0e0
        GL1[🌍 Global Parliamentary Watch<br/>100+ democracies]
        GL2[🗣️ Every UN Language<br/>Native-quality output]
        GL3[📊 100 Automation Assets<br/>Pre-AGI capabilities]
        GL4[🔒 Zero-Trust Architecture<br/>Quantum-safe cryptography]
    end
    EU1 --> GL1
    EU2 --> GL2
    EU3 --> GL3
    EU4 --> GL4

Phase 6: AGI Era & Transformative Democracy (2034–2037)

When AGI or near-AGI systems emerge, Riksdagsmonitor's modular architecture is designed with flexibility to adapt to future AI paradigm shifts — including potential AGI capabilities — while maintaining democratic safeguards.

%%{init: {"theme": "dark", "themeVariables": {"primaryColor": "#ff006e", "primaryTextColor": "#e0e0e0", "primaryBorderColor": "#00d9ff", "lineColor": "#ffbe0b", "secondaryColor": "#1a1e3d", "tertiaryColor": "#0a0e27"}}}%%
graph TB
    subgraph SGAGI["🤖 6.1 AGI-Enhanced Intelligence"]
        style SGAGI fill:#1a1e3d,stroke:#ff006e,color:#e0e0e0
        AGI1["🤖 Autonomous Analysis<br/>Real-time intelligence across<br/>all 195 parliamentary systems"]
        AGI2["🌐 Universal Language<br/>Every UN language<br/>supported natively"]
        AGI3["📊 Predictive Governance<br/>Policy impact prediction<br/>before legislation proposed"]
    end
    subgraph SGSAFE["⚖️ 6.2 Democratic Safeguards"]
        style SGSAFE fill:#0a0e27,stroke:#00d9ff,color:#e0e0e0
        SAFE1["⚖️ Ethical AI Governance<br/>Human oversight maintained<br/>regardless of AI capability"]
        SAFE2["🛡️ Anti-Weaponization<br/>Architecture prevents<br/>manipulation or misuse"]
        SAFE3["🔒 Constitutional Alignment<br/>Democratic values encoded<br/>in platform architecture"]
    end
    subgraph SGPARA["🧬 6.3 Paradigm Readiness"]
        style SGPARA fill:#0a0e27,stroke:#ffbe0b,color:#e0e0e0
        PARA1["⚛️ Quantum AI Ready<br/>Post-quantum cryptography<br/>Quantum ML integration"]
        PARA2["🧠 Neuromorphic Computing<br/>Brain-inspired architectures<br/>Edge intelligence deployment"]
        PARA3["🌍 Transformative Platform<br/>120+ automation assets · 195 parliaments<br/>Global democratic intelligence"]
    end
    AGI1 --> SAFE1
    AGI2 --> SAFE2
    AGI3 --> SAFE3
    SAFE1 --> PARA1
    SAFE2 --> PARA2
    SAFE3 --> PARA3

Strategic Considerations for Phase 6:

🤖 Autonomous analysis: AGI-powered real-time political intelligence across all 195 parliamentary systems
🌐 Universal language support: Every UN language supported natively
📊 Predictive governance: Policy impact prediction before legislation is proposed
⚖️ Ethical AI governance: Human oversight maintained regardless of AI capability level
🛡️ Democratic safeguards: Platform architecture prevents weaponization or manipulation

📈 AI Model Evolution Strategy

Illustrative assumptions (high uncertainty — AI landscape evolves rapidly):

Model updates assumed roughly quarterly; actual cadence will vary by vendor and paradigm
Version numbers (Opus 5.x–12.x) are illustrative — actual products may differ significantly
Competitors (OpenAI, Google, Meta, EU sovereign AI) evaluated at each major release cycle
Architecture must accommodate potential paradigm shifts (quantum AI, neuromorphic computing, or entirely new approaches)

Workflow Count Projection:

Year	Automation Assets	AI Model	Key Capability
2026	44→50	Opus 4.7–4.9	🤖 Agentic news generation (current)
2027	50–55	Opus 5.x	🔮 Predictive analytics & Nordic expansion
2028	55–65	Opus 6.x	🎙️ Multi-modal content (audio/video)
2029	65–75	Opus 7.x	🚀 Fully autonomous pipeline
2030	75–85	Opus 8.x	🧠 Near-expert analysis
2031–2033	85–100	Opus 9–10.x / Pre-AGI	🌍 Global parliamentary coverage
2034–2037	100–120+	AGI / Post-AGI	⚡ Transformative democracy platform

%%{init: {"theme": "dark", "themeVariables": {"primaryColor": "#00d9ff", "primaryTextColor": "#e0e0e0", "primaryBorderColor": "#ff006e", "lineColor": "#ffbe0b", "secondaryColor": "#1a1e3d", "tertiaryColor": "#0a0e27"}}}%%
xychart-beta
    title "Riksdagsmonitor Workflow Growth Projection (2026–2037)"
    x-axis ["2026", "2027", "2028", "2029", "2030", "2031", "2032", "2033", "2034", "2035", "2036", "2037"]
    y-axis "Automation Assets (Workflows + Prompt Files)" 0 --> 130
    bar [47, 53, 60, 70, 80, 88, 95, 100, 105, 110, 115, 120]
    line [47, 53, 60, 70, 80, 88, 95, 100, 105, 110, 115, 120]

Note: The chart values are midpoint estimates within the projected ranges in the table above and are illustrative, not exact counts.

📋 Detailed Future Planning

Document	Description
📋 Future Workflows	Complete 11-year workflow evolution roadmap with architecture diagrams
🗺️ Future Mindmap	Capability expansion map from Swedish monitoring to global democratic intelligence
🚀 Future Architecture	Architectural evolution from static site to AI-native platform
🔒 Future Security Architecture	Security roadmap including post-quantum cryptography
💼 Future SWOT	Strategic opportunities in democratic technology

🏢 About Hack23

Hack23 AB (Org.nr 5595347807) - Swedish cybersecurity and open-source intelligence consultancy

🌐 Website: www.hack23.com
💼 LinkedIn: Company Profile
👨‍💻 Founder: James Pether Sörling, CISSP, CISM
🔒 ISMS: Public ISMS Repository

🤝 Contributing

Contributions welcome! Please follow Hack23's secure development standards:

Fork the repository
Create a feature branch with descriptive name
Sign commits with GPG key
Test changes locally (HTML validation, link checking)
Submit pull request with comprehensive description
Address code review feedback

Requirements:

GitHub account with MFA enabled
GPG-signed commits
HTML validation passing
No security vulnerabilities introduced

📜 License

Licensed under the Apache License, Version 2.0. See LICENSE file for details.

🔗 Links

Website: riksdagsmonitor.com
CIA Platform: www.hack23.com/cia
GitHub: github.com/Hack23/riksdagsmonitor
Hack23: www.hack23.com
ISMS: github.com/Hack23/ISMS
LinkedIn: James Pether Sörling

👨‍💻 Maintainer

James Pether Sörling
CISSP, CISM
CEO, Hack23 AB
LinkedIn | GitHub

Monitor political activity in Sweden with systematic transparency