Skip to main content
Phase 0 + 1 complete. Deliberation Engine MVP live

AI that amplifies reason, not noise

Diverse AI agents powered by 4 model providers from 4 jurisdictions simulate structured deliberation on contested normative questions. Humans intervene only when they disagree.

The core inversion

Agents deliberate. Humans decide.

Traditional deliberative democracy asks citizens to do the hardest cognitive work: reading opposing views, steelmanning arguments, tracking concessions, and synthesising common ground. Most people don't lack opinions. They lack the time.

Pangora.Space inverts this. AI agents do the computationally expensive part of deliberation. Humans provide the irreducibly human contribution: normative authority. The question shifts from “what do you think?” to “does this consensus, reached through structured reasoning, represent what you actually want?”

Traditional approach

High quality + Large scale + Low time cost

Pick two. Fishkin's impossibility triangle.

Pangora.Space's approach

Agents handle scale and quality. Humans handle authority.

The deliberative poll, computationally extended.

Multi-model architecture

Training data bias as a deliberation feature

Most AI deliberation research uses a single model family. Pangora.Space uses 4 providers across 4 jurisdictions. The strong diversity hypothesis: models trained on different data encode meaningfully different normative orientations.

Anthropic

Claude

US

Western liberal-institutional

Mistral

Mistral

EU

European regulatory-social democratic

DeepSeek

DeepSeek

China

Chinese developmental-authoritarian

AI Singapore

SEA-LION

SEA

Southeast Asian multicultural

25%

Maximum share of any single provider per deliberation panel

10%

Deliberate persona-model mismatches for cross-cultural stress testing

3

Different providers for framing, common ground extraction, and synthesis

Deliberation engine

Structured discourse, not just chat

1

Framing

A neutral framing document identifies value tensions and provides multi-context factual grounding. Generated by a different provider than the deliberation agents.

2

Position → Critique → Revision

Each round has three phases. Agents state positions with reasoning chains and value anchors, critique others with steelmanning, then revise. Every newly incorporated proposition is tracked explicitly.

3

Common Ground Extraction

After each round, convergent propositions are extracted with convergence rates broken down by model provider and governance familiarity category.

4

Consensus Synthesis

When convergence reaches the threshold (default 75%), a consensus statement is synthesised. Dissenting positions are always preserved as first-class outputs, never erased.

Anti-sycophancy controls

  • Adversarial anchors: 2 agents per panel explicitly resist consensus unless presented with genuinely novel evidence
  • Convergence velocity monitoring flags any >20pp jump in a single round as suspiciously rapid
  • Position commitment reminders reinforce each agent's core position and value anchors every round
  • Textual vs. substantive convergence: only independent reasoning chains count toward ratification

Dissent as first-class output

Every consensus statement includes dissenting positions with the percentage of agents holding them and the core disagreement. When convergence isn't achievable, the deliberation is declared irreconcilable and published as a structured map of where the foundational disagreements lie. This is a feature, not a failure.

Persona taxonomy

12 dimensions of normative variation

Civic Personas are constructed from 12 dimensions designed to capture what actually varies in normative reasoning, without encoding protected attributes. The taxonomy captures structural and experiential variation, not demographic identity.

Moral Foundations
Justice Orientation
Epistemic Style
Institutional Trust
Time Horizon
Risk Disposition
Economic Position
Governance Familiarity
Livelihood / Domain
Geographic Exposure
Community Scope
Change Orientation

The essentialism boundary

Programming an AI agent with “gender: woman” requires the model to generate “what a woman would think.” But there is no such thing. Protected attributes are social positions that interact with normative orientations in complex, individual ways. The taxonomy captures the experiential dimensions that are more directly connected to policy reasoning, while a post-deliberation representativeness audit checks for demographic blind spots in the output.

Current status

Phase 0 + 1 complete

Built

  • Multi-model deliberation engine (4 providers)
  • 36 Civic Personas across 12 dimensions
  • 3-phase round execution with anti-sycophancy controls
  • Consensus synthesis with dissent preservation
  • Model provenance logging on every contribution
  • Meta-call provider diversification
  • Cross-cultural stress test framework
  • FastAPI backend + Next.js frontend

Next

  • QAM Suite (DQS, CTP, Neutrality Auditor, FAC)
  • Human review and ratification tiers
  • Personal Agent studio with Bayesian value models
  • Spotlight Review mechanism
  • Representativeness audit pipeline
  • Fidelity score computation and sunset clause
  • Constitutional amendment process