Deployment Options

Our AI-powered document intelligence platform can be deployed in three configurations — Cloud, Hybrid, and Full On-Premises — to meet your firm's data-security and compliance requirements.

The Hybrid modelRECOMMENDED is ideal for engineering and infrastructure organisations. It keeps all source data within your network, while leveraging secure Australian cloud compute for AI processing.

This approach delivers full performance and full compliance — without the cost of full on-prem hardware.

DEPLOYMENT

Choose Your Configuration

Three deployment models designed to balance security, performance, and cost. Each configuration meets different compliance and infrastructure requirements.

FeatureCloud
HybridRECOMMENDED
Full On-Premises
Where documents liveAll files and processing in the cloudFiles stay on your servers; only transient text snippets processed in cloudAll data and compute remain on your servers
Security ownershipCloud providerShared — you keep custody of all data; cloud handles transient compute100% client-managed
PerformanceHigh, bandwidth-dependentHigh — local file access + cloud GPU computeModerate (limited to local CPU/GPU)
Setup & costLowMedium (light local agent + cloud embedding)High (hardware + maintenance)
MaintenanceProvider-managedAuto-updates in cloud; minimal local supportFully client-managed
Compliance
(ISO, NATA, AU data-residency)
May require extra controlsFully compliantFully compliant
AI model updatesAutomaticAutomaticManual

HYBRID ARCHITECTURE

How the Hybrid Model Works

1Local Connector – Secure Bridge

A lightweight service installed on your own server or VM:

  • Reads and parses approved files locally (PDF, Word, CAD, drawings)
  • Extracts text and metadata for embedding
  • Sends only small text fragments (hundreds of words) over encrypted outbound HTTPS to Azure for embedding
  • Receives numeric vectors, discards text, and stores nothing readable
  • Fetches original text locally when users search, ensuring data never leaves your network
No inbound ports
Fully auditable
No full documents uploaded

2Cloud Embedding & Vector Storage

  • Uses secure cloud infrastructure (e.g., Azure Australia East) for transient embedding — text is processed in memory only
  • Produces numeric vectors stored in a secure, region-locked vector database
  • Stores only minimal metadata (doc ID, page #, project code)
  • No readable content or files retained in the cloud

Your Data Stays Local

Project files never leave your network

Mathematical Representations Only

Only vectors are sent to secure cloud model

No Raw Content Exposed

No text, drawings, or metadata are exposed

Full AI Capability

Without managing expensive GPU hardware

3Query & Retrieval

01

User submits a search in the web app

Hosted securely in the cloud

02

Query is embedded and matched against vectors

AI processing finds relevant content

03

Connector retrieves matching snippets locally

Full source traceability and context

04

Your data stays secure

No full documents or sensitive data leave your network

DATA SECURITY

Metadata Handling

TypeExampleStored In
Non-sensitivedoc_id, page_number, keywords☁️ Cloud vector DB
Sensitivefile path, author, client name, project title🏢 Local metadata index
Vectorsnumeric embeddings [0.254, -0.088, …]☁️ Cloud
Original filesPDFs, Word, DWG🏢 Local storage

Result: The cloud knows what's relevant, but only your system can reconstruct the text.

TECHNICAL OVERVIEW

Data Flow & Security

User
Cloud Frontend
(Azure App Service)
Cloud Backend / Vector DB
(AI Embedding Service)
Local Connector
(Client VM)
Local File Server / SharePoint
(Your Network)
All transfers encrypted (TLS 1.2+)
Cloud endpoints stateless — no text stored
Region-locked to Australian data centres
Local logs record every file processed
No external party can access your file system

Ready to Learn More?

Schedule a call to discuss how the Hybrid deployment model can work for your firm.

Book a Demo