How It Works Trust Center FAQ Blog About Try Sandbox Start a Pilot
Founding Firm Program — limited spots
Modern Law / Private AI

Would you tell your clients where their data actually goes?

With Rendex, you can. A private cloud AI system built on Azure confidential compute — a dedicated H100 inside a sealed enclave. Every answer cites the exact document and page. No outbound egress required after setup.

Private Cloud $299–$599/attorney/month
Book a Demo View Trust Center
120B
Model
131K
Context Window
Zero
Outbound Egress
8
Service Stack
x86
Standard Architecture
SOC 2 Aligned
SSO — Microsoft Entra ID
Matter Isolation + Ethical Walls
Ready to run AI inside a sealed enclave?

Start with a 30-day pilot. One practice group, three workflows, hardware-attested isolation from day one.

Start a Pilot
How It Works
Three steps. Zero exposure.
From document upload to cited answer — everything runs inside a dedicated confidential compute enclave. No shared tenancy. No outbound egress required after setup.
1

Your enclave comes online

We provision a dedicated Azure confidential VM with your own NVIDIA H100 GPU. AMD SEV-SNP attestation verifies the enclave on every boot. We configure SSO via Microsoft Entra ID and hand your IT team the attestation report. No hardware to install. No changes to your infrastructure. Operational in days.

Drag and drop documents to ingest
2

Upload your documents

Drag in contracts, briefs, filings — PDF, DOCX, TXT. Rendex indexes everything inside the enclave. Scanned PDFs get OCR'd in the same boundary. Organize by matter with automatic access controls. Every document stays inside the perimeter.

Ask in plain English and see streaming answer
3

Ask questions, get cited answers

Type in plain English. Rendex searches your entire document repository using hybrid retrieval — combining semantic AI search with keyword matching. Every answer cites the exact document, section, and page. Every query is logged for audit.

Click a citation to open the source document
Platform
Private AI built for security and compliance review.
🔒

Complete data sovereignty

Document processing, retrieval, and inference run inside your environment. No outbound egress required after setup. No third-party APIs, no training on your data. Verify with firewall rules or packet capture.

⚡

No vendor lock-in

Built on open-source models and standard hardware. No proprietary formats, no data hostage. Your documents remain yours — export everything, anytime.

⚖

Built for legal workflows

Matter-level permissions, ethical walls, page-level citations, audit trails, and guided workflows that match how firms actually work.

What You Can Ask
One interface. Ask for what you need.
Comparisons, clause tables, guided workflows, precedent search — ask in plain English and get cited answers. No separate tools to learn.

Comparisons

“What changed between the March and June drafts of the MSA?” — cited to both versions

Clause Tables

“Build a clause matrix across these 40 contracts (assignment, indemnity, termination)” — outputs a table with every cell cited to document + page. Export as CSV (with citations).

Guided Workflows

Depo Prep, Litigation Chronology, Precedent Memo — structured outputs with citations, exportable as HTML

Precedent Search

“Do we have prior work product on restrictive covenants in Texas?” — filtered by matter

Bulk Ingest

Scale to 100K+ documents with batched processing, progress tracking, and pause/resume. Built for data rooms and discovery.

Due Diligence

M&A and custom checklists. Scan matter documents, verify items, export to CSV or DOCX for deal teams.

Compare & Memo

Side-by-side document comparison with significance filters. Draft memos with citations; export to DOCX.

Machine Vision OCR

Scanned PDFs are automatically detected and re-processed through an on-device vision-language model. Quality scored, no cloud OCR, no data leaves the enclave.

Platform
Included in every deployment
Matter summarization — one-click, cached per matter
Machine vision OCR — scanned PDFs auto-detected and re-extracted by on-device vision-language model
Document comparison — side-by-side, significance scoring
Draft memo — citations, DOCX export, refine
DMS sync — iManage, NetDocuments, Worldox, and local folder watch. Workspace-to-matter mapping with scheduled sync (hourly to daily)
Full audit trail — queries, logins, exports; CSV for admins
Folder watch auto-ingest — drop files into a network folder, indexed automatically into the target matter
3-tier document library — Personal, Workspace, and Firm-level catalogs with promotion between tiers
Sandbox demo mode — read-only evaluation environment for prospect demos, no setup required
Two-model strategy — Fast model for everyday queries, Deep Analysis toggle for complex legal reasoning
Circuit breaker and concurrency controls — automatic throttling protects GPU resources during peak usage
Why Rendex
Your firm wants AI. Compliance says no.
Rendex is designed to support security and compliance review.
Cloud AI raises ethics and confidentiality concerns. Rendex was built for this reality.

Hardware-Attested Privacy

A dedicated H100 inside an Azure confidential VM. AMD SEV-SNP encrypts memory at the hardware level. Attestation verifies the enclave on every boot. Not a promise — a cryptographic proof.

Zero Vendor Access

Not even Rendex can see inside the enclave. Not Microsoft. Not us. The attestation report is yours to verify. Remote support is customer-initiated only — no standing access, no inbound tunnels.

Every Answer Cited

Click any citation to see the exact source text. Answers are citation-backed, and unsupported responses are flagged or refused.

Ethical Walls & Matter Isolation

Matter-level permissions enforced at the query level. SSO via Microsoft Entra ID. Every access logged.

Private Cloud AI — Hardware-attested privacy
Azure confidential compute.
Sealed by hardware. Verified by attestation.

Every firm runs on a dedicated NVIDIA H100 inside an Azure confidential VM — sealed by AMD SEV-SNP memory encryption, verified by hardware attestation, operational in days. Not even Microsoft can read your data inside the enclave. Same citations. Same matter isolation. Same audit trail. Founded by Matthew Giordano for firms where data sovereignty isn't optional — it's the requirement.

30-Day Pilot — accepting applications
Infrastructure
Built for law. Auditable by anyone.
Every component is self-hosted, inspectable, and replaceable. The legal-specific layer on top is what makes it Rendex.
Built for law
Legal-aware parsing
Section-boundary chunking, definitions detection, QC scan for missing standard clauses.
RAG pipeline
Hybrid Qdrant + OpenSearch retrieval, citation grounding, optional cross-encoder rerank.
Legal workflows
Draft generation + risk scan, tabular review, playbook runner, clause-level compare.
Governance
Per-document ACLs, query-time ethical walls, append-only audit log, multi-tenant scoping, SSO via Entra ID.
Zero egress
Content never leaves the enclave — traces and errors strip prompts and hash user ids.
This is what you’re paying for.
Auditable stack
Models & serving
GPT-OSS 120B MoE on vLLM; BAAI/bge-base-en-v1.5 on HuggingFace TEI
Storage & search
Qdrant, OpenSearch, PostgreSQL, Valkey
Ingest
Apache Tika, Marker (PDF→markdown)
Observability
Langfuse (metadata-only LLM traces), GlitchTip (Sentry-compatible), Prometheus + Grafana
Runtime
Node/Express, Nginx, Docker Compose
Every component is open source, self-hosted, and independently inspectable.

The stack is inspectable. The way it’s put together for law is not.

Full deployment and security details in the Trust Center →
Build vs Buy
BigLaw firms build their own AI.
You shouldn't have to.
Large firms hire 3–5 AI engineers, spend $800K–$1.5M per year, and take 6–12 months to deploy. Mid-size firms deserve the same capability without the same overhead.
What a large firm builds internally
3–5 engineers hired$800K–$1.5M/year in salary alone
6–12 months to deployA working system — if the project doesn't stall
Ongoing maintenanceModel updates, security patching, infrastructure management
Built for one firmNo cross-firm improvements
Key-person riskIf the lead engineer leaves, the project stalls
What Rendex deploys for you
Pre-configured confidential enclaveDeployed in days, not months
Same hybrid search, citations, and matter isolationEverything a large firm builds — ready from day one
Quarterly updatesNew models, new features, security patches — we handle it
Every improvement benefits every firmCross-platform improvements with every release
No AI team to recruit, manage, or retainOne enclave. One price. No headcount.
Why Rendex
Built for firms that can't risk public AI.
Litigation teams handle privileged documents, sensitive testimony, and confidential strategy. Public AI tools are a liability. Rendex is the infrastructure that lets you use AI without the exposure.
Litigation-first workflows

Chronology, deposition prep, document Q&A with citations. Not general-purpose chat.

Hardware-sealed by default

Every workflow runs inside an Azure confidential H100 enclave. No third-party APIs. Not even Microsoft can read your data.

Operational control

Matter isolation, ethical walls, append-only audit trail. Built for security and compliance review.

Pilot Program
Pilot program built for
real law-firm deployment.
License Rendex from $299 per attorney per month on Private Cloud Standard ($599 on Dedicated). We provision a dedicated confidential compute enclave on Azure — no hardware ships, no servers to install. Start with one practice group and real documents.
Confidential at the hardware level.

Every workflow runs inside a hardware-attested NVIDIA H100 TEE with AMD SEV-SNP memory encryption on Azure. Data and model weights are never exposed in plaintext — not to Microsoft, not to Rendex, not to any operator. Zero outbound egress after setup. No standing vendor access.

Start a Pilot View Trust Center

We respond within 2 business days.

Private Cloud. Two Tiers.

Every tier runs OpenAI's open-weight model inside a hardware-attested boundary. Designed for teams of 10 or more attorneys. Most firms start with 10 and scale as they grow.

Private Cloud — Standard
$299/ attorney / month
Designed for teams of 10 or more · billed annually
Most firms start with 10 attorneys. Scale up as you grow.
  • ✓gpt-oss-20B — o3-mini class reasoning
  • ✓Azure Confidential H100 — shared enclave
  • ✓AMD SEV-SNP hardware encryption
  • ✓Cryptographic isolation between firms
  • ✓Legal-aware document ingest + hybrid RAG
  • ✓Citation enforcement on every answer
  • ✓Chronology, depo prep, document Q&A
  • ✓Clause tables, due diligence, compare & memo
  • ✓Matter-level permissions + ethical walls
  • ✓SSO via Microsoft Entra ID
  • ✓Append-only audit trail
  • ✓Same-day deployment
Request Demo

Not even Microsoft can see your data · most firms start with 10 attorneys

Most Popular
Private Cloud — Dedicated
$599/ attorney / month
Designed for teams of 10 or more · dedicated H100 instance
Most firms start with 10 attorneys. Scale up as you grow.
  • ✓gpt-oss-120B — o4-mini class reasoning
  • ✓Dedicated Azure Confidential H100 — your firm only
  • ✓Full CPU + GPU trusted execution environment
  • ✓Hardware attestation reports on demand
  • ✓All Standard features included
  • ✓Priority inference — no queue
  • ✓Compliance attestation dashboard
  • ✓Matter-level permissions + ethical walls
  • ✓SSO via Microsoft Entra ID
  • ✓Append-only audit trail
  • ✓Same-day deployment
Request Demo

Cryptographic proof of data protection · most firms start with 10 attorneys

Private Cloud Standard is $299/attorney/month. Private Cloud Dedicated is $599/attorney/month. Both tiers are designed for teams of 10 or more attorneys and billed annually. Most firms start with 10 attorneys and scale as their practice grows. Contact us to discuss your firm's requirements.

Enterprise pricing available for 50+ attorneys and multi-site deployments. Contact us

Not ready to commit? Try the sandbox — no signup required →

Private cloud AI for law firms. Hardware-attested privacy. We never see your data.

Product
How It Works Trust Center Pilot Program FAQ Try Sandbox
Resources
Blog Start a Pilot Proof Pack
Company
About Start a Pilot info@rendex.inc
© 2026 Rendex Systems. Deployed. Not hosted.
Not affiliated with any online trading platforms or investment schemes.
Privacy Terms info@rendex.inc

Rendex provides technical tooling, not legal advice. Attorneys remain responsible for review, verification, and professional judgment.