The architectureEve-Legal F5/reasoner

A compositional fabric for legal reasoning.

JustineAI™ doesn’t run on a single foundation model. It runs on Eve-Legal F5/reasoner — a compositional fabric of cooperating reasoning models, deployed on Eve-Grid™ (Microsoft Azure). Plug-and-play. Provider-diverse. Domain-specialized. Designed so the constraints of one model never become the limits of your firm.

Five cooperating models

The compositional fabric.

Five cooperating reasoning models compose per request. The classifier routes; the legal SRM carries the domain workload; one to three frontier slots add nuance and cross-validation; the long-context slot reads the entire case file in a single thought. Five is the representative configuration — not a fixed schema.

ClassifierMicrosoft Phi-3

Sub-200ms routing across workload type, modality, reasoning intensity, and context-length needs.

Why this model occupies this slot — Lightweight 3.8B-parameter classifier. The first responder of the stack — decides which downstream models compose for the matter at hand.

Legal reasonerMicrosoft Phi-4

LoRA-fine-tuned on Eve-Genesis (Law Edition). The domain-specialized workhorse for the bulk of legal reasoning.

Why this model occupies this slot — Carries the majority of legal workloads at near-Phi-4 cost and latency. Trained to reason like a senior litigator across canonical jurisdictional rules and procedural taxonomies.

Frontier reasoningAnthropic Claude Opus 4.7

Best-in-class long-form structured reasoning. Used when the matter is high-stakes and nuance matters.

Why this model occupies this slot — Frontier slot one. Strong at demand-letter narrative, complex damages reasoning, and matters requiring careful disambiguation of authority.

Frontier reasoningOpenAI GPT-5.4

Frontier general reasoning. Complementary to Opus for cross-validation and ensemble routing.

Why this model occupies this slot — Frontier slot two. Provider diversity — when a client or jurisdiction prohibits a specific provider, this slot absorbs the constraint without rebuilding the agent.

Longitudinal contextMeta Llama 4 Scout

10M-token single-context reasoning across the entire case file in one thought. The moat.

Why this model occupies this slot — The single largest open-weight context window publicly available. Workflow patterns this enables — full case-file review, multi-deposition synthesis, citation grounding across years of correspondence — are one-shot queries for Scout.

The synthetic-data substrate

Eve-Genesis (Law Edition)

The Phi-4-derived legal SRM is fine-tuned on Eve-Genesis (Law Edition) — a proprietary synthetic reasoning corpus calibrated to legal workflows. The dataset is 100% synthetic by construction. Your firm’s matter data is never used to train models.

The supervisor pattern

Justine over stage-specialized sub-agents

Justine supervises stage-specialized sub-agents (intake, medical, valuation, strategy) across the case lifecycle. The sub-agents are NOT separately branded — Justine is the only Digital Employee with a name. This is the architectural moat for Mass Tort: one supervisor coordinating thousands of plaintiff sub-agents in a single reasoning context.

Where it runs

Eve-Grid™ — built on Microsoft Azure.

JustineAI™ runs on Eve-Grid™ — MindHYVE.ai™’s proprietary cloud architecture anchored to Microsoft Azure. The marketing site is on Azure Static Web Apps; the PI application is on Azure Container Apps, Functions, Cosmos DB, Storage, and Key Vault. Customer-managed keys available on enterprise plans.

  • Tenant isolation

    Your data, your tenant.

    Each firm’s matters live in an isolated Cosmos DB partition with per-firm encryption keys. The supervisor pattern enforces tenant boundaries at the orchestration layer — sub-agents cannot reach across firms.

  • US data residency

    US regions by default.

    The PI application runs in US Azure regions. Matter data stays in the customer’s region of record. International deployment is configurable but never automatic.

  • Inherited attestations

    Azure-foundation security.

    The Microsoft Azure platform layer holds ISO 27001, ISO 27018, SOC 1/2/3, PCI DSS, and HITRUST attestations. JustineAI™ inherits these at the platform layer; our own attestation roadmap is on the Trust page.

Security posture

Designed for legal procurement from day one.

  • Identity — Entra ID.

    Authentication via Microsoft Entra ID. Authorization via Azure RBAC. SAML and OIDC SSO available for enterprise plans. Per-user, per-matter, per-action authorization decisions logged.

  • Encryption — end to end.

    TLS 1.2+ in transit. Azure-managed keys at rest by default; customer-managed keys (Azure Key Vault) on enterprise. No data is stored outside the customer’s Azure region of record.

  • Audit — tamper-evident.

    Every reasoning step, every output, every user action logged to Azure Monitor. Logs are retained for the agreed contractual period and exportable for litigation discovery, malpractice insurance, and ethics review.

  • Networking — private.

    Service-to-service traffic stays inside the Azure backbone via private endpoints. No backend services have public ingress in production. Web Application Firewall policies and CSP headers enforced on every public surface.

Read the full Trust posture →
Go deeper

Six pages on the architecture.

Ready when you are

See JustineAI™ in your practice.

For PI principals, managing partners, and litigation operators evaluating reasoning-grade AI for their firm. Self-serve trial available for solo and small practices; sales-assisted for mid-size and enterprise.

Talk to our team →Start a free trial →