One operating system. Six editions of practice.
JustineAI™ is the Agentic Legal OS. The reasoning core — Eve-Legal F5/reasoner — is the same across every edition. What changes is the workflow, the document pipeline, and the jurisdictional taxonomy. If you’re a personal-injury, workers’-comp, medical-malpractice, mass-tort, insurance-bad-faith, or employment-class attorney, you’re on the roster. The PI edition is in market today; the other five are calibrated and queued by wave.
Pick the edition that matches your practice.
Each edition shares the Eve-Legal F5/reasoner compositional fabric and the supervisor + sub-agent pattern. What differs is the calibration of the legal reasoner on Eve-Genesis (Law Edition) for the specific vertical: the workflow shape, the documents the analyzers know to parse, and the jurisdictional taxonomies the reasoner navigates.
- PIIn market
JustineAI™ — Personal Injury Edition
Plaintiff-side personal-injury practice. Justine’s Workspace v1.2 intake with per-field provenance and validator council; nine-step Curation Layer over the medical record; four-pass demand-letter pipeline with ICD-10 / CPT validation and CourtListener citation verification; one-click Demand Package assembly (cover letter + Medical Chronology + Bill Stack); supervisor-over-sub-agents pattern across the nine-status case lifecycle.
Intake → Curation → Demand Package → Settlement, across the 9-status PI workflow.
Read the workflow →
- MTComing next
JustineAI™ — Mass Tort Edition
MDL specialists. One Justine supervisor coordinates thousands of plaintiff sub-agents in a single context — bellwether scoring, settlement-matrix modeling at scale, lien negotiation, plaintiff fact-sheet auto-population. The supervisor + sub-agent pattern is the moat.
One supervisor. Thousands of plaintiff sub-agents. Bellwether scoring + settlement matrix.
Tell us your firm →
- WCComing next
JustineAI™ — Workers’ Comp Edition
Applicant and defense workers’ comp. State-specific filings, AME/PQME analysis, MMI tracking, MTUS/ACOEM treatment-utilization review, permanent-impairment rating modeling. ChironAI™ Occupational Medicine is the upstream feed — cross-portfolio moat.
AME / PQME / MMI / state-specific filings — with ChironAI™ OM as the upstream feed.
Tell us your firm →
- MMOn the roadmap
JustineAI™ — Medical Malpractice Edition
Multi-provider medical chronology across 5,000–50,000 pages per case. Causation analysis grounded in cited standard-of-care deviations. Daubert challenge preparation. Certificate-of-merit drafting. Expert-witness management.
Multi-provider chronology, causation reasoning, Daubert prep, certificate of merit.
Tell us your firm →
- IBOn the roadmap
JustineAI™ — Insurance Bad Faith Edition
Plaintiff-side bad-faith litigation. Policy-language interpretation, claim-file analysis, prior-claim pattern detection across the carrier’s portfolio, claim-handler deposition preparation, Brandt fees calculation.
Policy interpretation, claim-file analysis, Brandt fees, claim-handler depo prep.
Tell us your firm →
- ELOn the roadmap
JustineAI™ — Employment Class Edition
Plaintiff-side employment class action and FLSA collectives. Class certification motion practice, damages modeling at class scale, FLSA fluctuating-workweek calculations, opt-in conversion tracking, EEOC charge orchestration.
Class certification, damages modeling at class scale, FLSA collectives, EEOC orchestration.
Tell us your firm →
Three waves. No dates.
Wave 1 — in market. The PI edition is live today. Self-serve trial for solo and small practices; sales-assisted for mid-size and enterprise. Every capability listed on the PI page is shipped.
Wave 2 — coming next. Mass Tort and Workers’ Comp. We chose these as the first roadmap editions for two reasons: the supervisor + sub-agent pattern that powers PI is the same pattern MT and WC need at scale; and ChironAI™ Occupational Medicine is already in market, which gives the WC edition an upstream-feed cross-portfolio moat from day one.
Wave 3 — on the roadmap. Medical Malpractice, Insurance Bad Faith, Employment Class. These are calibrations away — the document pipeline shape, the jurisdictional rules, the per-vertical motion practice. The reasoning core is the same.
We don’t publish dates because we don’t miss them. When an edition opens, we announce it on the day it’s ready and we reach out to every attorney who told us about their practice — in the order they told us.
The AI is the moat. The OS is the everyday.
Eve-Legal F5/reasoner is the reasoning core that produces the demand letter, reads the medical record set, and writes the strategy memo. JustineAI™ is the operating system that sits above it — case management, deadlines, conflicts, trust accounting, time tracking, e-filing, the client portal, the integrations your firm already runs. Six pillars. Twenty-six practice-operations capabilities. Shared across every edition of the OS — PI today, WC / MM / MT / IB / EL as each wave opens.
- Matter lifecycle. Tasks. Calendars. Time.
Case operations
- Case management
Matters, phases, dashboards, status flows, custom checklists per case type — the file your firm actually works.
- Deadlines + SOL tracking
Statute-of-limitations clocks per matter; court-deadline rules per jurisdiction; automated reminder cadence; nothing falls through.
- Conflict-of-interest check
Every new intake runs through an automated conflict ledger keyed to the firm’s existing clients and adverse parties. Ethics-rule compliance built in, not bolted on.
- Tasks + appointments
Per-matter task lists, calendar integration with Microsoft 365, appointment scheduling with the client portal flow.
- Time tracking + writing-style
Attorney billable-hours tracking with billing reconciliation. Per-attorney writing-style preferences applied to every AI-generated draft so the voice stays the firm’s own.
- Case management
- Trust accounting. Billing. Settlement. Loans.
Financial operations
- Trust accounting (IOLTA)
Interest On Lawyer Trust Accounts handled to the standard your state bar requires. Reconciliation built in. Auditable. The single most-often-cited reason a PI firm replaces its case-management software.
- Billing — Stripe + Square
Dual billing paths. Per-seat subscriptions on Stripe; flat-tier plans on Square. Automated reconciliation. The firm chooses the path that matches its payment flow.
- Settlement schedules + disbursements
Settlement-schedule modeling, disbursement statement preparation, client-side settlement explainer, lien orchestration across Medicare, Medicaid, ERISA, and provider liens.
- Expenses + pre-settlement loans
Per-matter expense tracking. Litigation-funding loan management when the matter is on the financing path.
- Trust accounting (IOLTA)
- E-filing. Pleadings. E-signature. Letter templates.
Court + filing
- E-filing
Court-integrated electronic filing for jurisdictions that support it. The filing receipt routes back to the matter automatically.
- Pleadings drafting
Complaint + answer drafting calibrated to the matter and jurisdiction, distinct from the demand-letter pipeline.
- E-signature via DocuSign
Engagement letters, consent forms, releases, settlement agreements — all signed through the integrated DocuSign envelope flow.
- Custom letter templates
Firm-branded letterheads and letter templates beyond the demand-letter pipeline — status letters, lien letters, treatment letters, the firm’s standard library.
- E-filing
- Client portal. SMS. Phone intake. Email + fax.
Client + communication
- Client portal
Clients access their case status, sign documents, upload records, and message the firm. Reduces phone-and-email status updates to zero.
- SMS messaging (ACS)
Outbound SMS for case-status updates, appointment reminders, document requests — opt-in, STOP-compliant, transmitted via Azure Communication Services.
- Conversational phone intake
ElevenLabs-powered conversational AI answers the firm’s intake line, takes the structured intake conversation, and hands the dossier to Justine ready for attorney review.
- Email + fax
Email-in for matter correspondence; automated fax send/receive for the records workflows that still require it.
- Satisfaction campaigns
Post-matter client-satisfaction outreach, anchored to the matter close-out and tracked in the firm dashboard.
- Client portal
- Case Advisor. Predictive analytics. Search. Reports.
Intelligence + analytics
- Case Advisor agent
A standalone AI surface — the attorney asks Justine "what should I do next on this matter" and gets a structured strategic answer grounded in the case file.
- Predictive analytics
Case-outcome prediction grounded in the firm’s historical matters and the venue’s comparable verdicts — distinct from in-matter valuation modeling.
- Full-text search
Search every matter, every document, every reasoning step — bounded by tenant + role.
- Reports + analytics dashboard
Firm-level reporting on attorney productivity, matter inventory, settlement velocity, lead conversion, and the metrics the practice administrator runs the firm on.
- Quick Analyze + Spotlight
A one-off matter-analysis surface for intake triage; a cmd-K command palette for power users.
- Case Advisor agent
- Microsoft 365. Filevine. Cloud storage. DocuSign. ElevenLabs.
Integrations
- Microsoft 365
Single sign-on via Microsoft Entra ID. Outlook calendar + email integration. OneDrive document sync. Teams meeting integration. The identity boundary your firm already runs on.
- Filevine bidirectional sync
For firms running Filevine today: matter data, contacts, documents, and activity sync bidirectionally so the migration is incremental, not all-or-nothing.
- Cloud storage — Dropbox + Box + OneDrive
Document libraries from existing cloud providers attach to matters without copy-and-paste; the canonical record stays where the firm already keeps it.
- DocuSign + ElevenLabs + Telnyx
E-signature via DocuSign. Conversational phone intake via ElevenLabs. Telephony via Telnyx. Each integration documented in the subprocessor list with materiality classification.
- Microsoft 365
A compositional fabric — not a stack.
Every JustineAI™ edition is powered by Eve-Legal™ Fusion v5 — a Microsoft Phi-3 classifier, a Microsoft Phi-4-derived Small Reasoning Model fine-tuned on Eve-Genesis (Law Edition), and one to three commercially available frontier models composed dynamically per request, with Meta Llama 4 Scout occupying the long-context slot.
We don’t compete with frontier labs. We compose frontier models into our reasoning systems rather than competing with them. Where a jurisdiction or client prohibits a specific provider, that provider is swapped without rebuilding the agent.
Justine supervises stage-specialized sub-agents (intake, medical, valuation, strategy) across the case lifecycle. The supervisor + sub-agent pattern is what makes Mass Tort at scale possible — one Justine supervisor coordinating thousands of plaintiff sub-agents in a single reasoning context.
No customer data is used for training. Eve-Genesis (Law Edition) is 100% synthetic by construction.
Sub-200ms routing across workload type, modality, reasoning intensity, and context-length needs.
Why: Lightweight 3.8B-parameter classifier. The first responder of the stack — decides which downstream models compose for the matter at hand.
LoRA-fine-tuned on Eve-Genesis (Law Edition). The domain-specialized workhorse for the bulk of legal reasoning.
Why: 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.
Best-in-class long-form structured reasoning. Used when the matter is high-stakes and nuance matters.
Why: Frontier slot one. Strong at demand-letter narrative, complex damages reasoning, and matters requiring careful disambiguation of authority.
Frontier general reasoning. Complementary to Opus for cross-validation and ensemble routing.
Why: Frontier slot two. Provider diversity — when a client or jurisdiction prohibits a specific provider, this slot absorbs the constraint without rebuilding the agent.
10M-token single-context reasoning across the entire case file in one thought. The moat.
Why: 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.
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.