Codex Legal Engine.

The Problem

An architectural response to a structural problem.

A jurist using LLM for legal analysis faces a structural problem: the model doesn't distinguish established from debated, positive law from minority doctrine. It produces fluent, confident, potentially false responses. Codex is an architectural response.

The Architecture

Four sequential steps.

1. Externalized Calibration. Model: Claude Haiku. 6 probes (R1–R3 rigor, P1–P3 scope/depth), 3 cursors. Calibrator never touches legal data.

2. Layer Selection. Epistemic Regimes: Four layers.

• Litigation
• Advisory
• Exploratory
• Monitoring

Each defines what the model may say and with what certainty.

3. Labeled Analysis. Model: Claude Sonnet or Opus. Epistemic Levels: Five labels.

• [ESTABLISHED]
• [MAJORITY POSITION]
• [ARGUED CONNECTION]
• [DEBATED]
• [PROSPECTIVE]

4. Active Verification. Protocol: CoVe (Consensus Verification).

• Existence
• Content
• Contradiction

Transversality Matrix

The law never arrives alone.

17 adjacent domains with 0–3 scoring.

Direct Access to Case Law

The model checks the sources itself.

7 MCP tools connected to Judilibre API (Cour de cassation):

• 4 search engines
• Full text access
• Pourvoi verification
• Taxonomy lookup

Seven Posture Rules

How the model is required to behave.

1. Presumption of expertise
2. Systematic gap signaling
3. Maximum informational density
4. Positional neutrality
5. Anti-acquiescence
6. Traceability
7. Stylistic sobriety

Installation and Cost

Deployed by Claude, run for the price of a subscription.

Claude-as-installer pattern:

• Claude Pro: €18/month
• Make: €9/month
• API: ~€10/month
• Total: ~€28/month

Quick Reference

The system in four numbers.

• 4 architecture steps
• 5 epistemic labeling levels
• 7 MCP Judilibre tools
• ~€28 per month