---
title: VRAX-01 — AI Legal Research Analyst
slug: vrax
role: AI Legal Research Analyst
function: Legal / Compliance
seniority: Senior
verticals:
  - "Legal"
  - "B2B"
tier: expert
monthlyPrice: $1000/month
publishedAt: "2026-05-04T16:00:00.000Z"
canonical: "https://fidelic.ai/agents/vrax"
---

# VRAX-01 — AI Legal Research Analyst

*Legal research and memo drafts, with citations checked*

VRAX runs legal research, drafts memos, and checks citations under the supervising attorney's published rules — with every claim grounded in a citation that has been verified to exist.

## Why it matters

Harvey runs at $1,200–2,000/seat/mo with 25-seat minimums (~$360K+/yr floor) and is a Big Law product only. VRAX is $1,000/mo flat per supervising attorney, with citation-verification gates on every output and no enterprise floor.

## Capabilities

- Drafts research memos on the questions you assign, grounded in primary sources
- Verifies every citation against the actual case, statute, or regulation before shipping
- Surfaces relevant precedent with the procedural posture noted
- Logs every research move with the source it came from
- Maintains a per-matter research log for the supervising attorney

## The edge

VRAX flags every citation that the agent could not verify against a primary source. The memo ships with the unverified citations explicitly marked — not silently included.

## The hook

Every Friday VRAX ships a research-quality digest: citation verification rate, memo turnaround time, attorney-acceptance rate per matter type. Self-audit on the record.

## Tools and integrations

- Slack
- Westlaw
- Lexis+
- Casetext
- Google Drive

## Evidence

- Operates under the four-tier Fidelic constitution; the autonomy ceiling is 'research and draft only', never advise
- EvalOps suite covers citation verification, hallucination detection, and primary-source fidelity
- Inherits new base models and new agent skills automatically — pushed to every Fidelic agent the moment they ship. Same shape as a SaaS update; no upgrade purchase, no version pinning.

## Safeguards

VRAX will not give legal advice or render an opinion. The agent does research; the supervising attorney advises.

VRAX will not ship a citation it has not verified against a primary source.

VRAX will not handle privileged client communications without the supervising attorney's explicit approval.

## Worst-case behavior

When the model is uncertain, VRAX flags the question and surfaces the candidate sources for the supervising attorney's review rather than emitting a confident-sounding answer.

## Day 1 / Week 1 / Month 1

- **Day 1:** Provisioned. Supervising attorney approves the matter scope and constitutional rules.
- **Week 1:** First research memos delivered under attorney review. Citation-verification baseline established.
- **Month 1:** Per-matter research log compounding. Citation accuracy and attorney-acceptance rate reported weekly.

## 90-day success criterion

Every memo’s citations are verified against primary sources, and attorney-acceptance rate is above the threshold the supervising attorney sets, sustained for three weeks.

## Integrations / supervision required

Westlaw, Lexis+, or Casetext access (your firm's subscription). Document storage (Google Drive, OneDrive). Slack for digests.

## Resume

**Background.** AI legal research is the category where hallucinated citations have been most catastrophic for buyers (the 2023 Mata v. Avianca sanctions case set the bar). VRAX is built on the Fidelic AI configuration agent with citation verification as a hard-coded gate. The agent does not ship a memo with an unverified citation.

**Methodology.**
- Drafts memos against the scope the supervising attorney has approved
- Verifies every citation against the primary source before shipping
- Routes against the four-tier constitution: autonomous on research, review-required on memo drafts, escalate on advice questions, refuse on privileged-comms decisions
- Logs every research move with the source it came from

**Evals.** EvalOps suite covers citation verification (must be 100% before ship), hallucination detection on memo drafts, and primary-source fidelity. Suite must pass before any memo ships.

**Operating record.** First-cohort deployments scheduled May–June 2026. Operating-record metrics publish with the first quarterly cohort review.

## Compatible agents

- [ETHA-01 — AI Risk & Security Analyst](https://fidelic.ai/agents/etha) — Vendor-risk reviews, security questionnaires, audit prep
- [PRAX-01 — AI Contract Review](https://fidelic.ai/agents/prax) — Contract redlining against your firm's playbook
- [VELA-01 — AI Compliance Analyst](https://fidelic.ai/agents/vela) — Compliance memos ready for your GC

## Related honest questions

- [What do I actually own if I cancel my AI agent tomorrow?](https://fidelic.ai/hard-questions/what-do-i-own-if-i-cancel)
- [Is Fidelic just a wrapper around GPT?](https://fidelic.ai/hard-questions/wrapper-around-gpt)
- [What if the agent makes a public mistake we can't take back?](https://fidelic.ai/hard-questions/public-mistake)

---
Canonical: https://fidelic.ai/agents/vrax