ASSET WIZARD

From nameplate to queryable knowledge in minutes.

The Asset Wizard turns a process that usually takes days — identify equipment, find documentation, organize knowledge — into a guided, AI-assisted experience. No empty forms. The system anticipates, suggests, and validates at every step.

Request a Demo View Technology
16
Technical domains
~50
Models per manufacturer
44
Queries per search angle
<10s
Nameplate scan
PIPELINE

From nameplate to RAG answer.

Every step feeds the next. Zero manual configuration.

📷
Scan
Photo → identification
🏭
Configure
Domain, manufacturer, model
🔍
Corpus
30–80 PDFs found
🧠
Knowledge Graph
Structured extraction
💬
RAG Chat
Answers with sources
FEATURE 01 — VISION

Nameplate Scanner with Computer Vision

Why type when you can photograph?

Take a photo of your equipment's nameplate. Claude Vision extracts the manufacturer, model, serial number, and year of manufacture automatically. In seconds, with zero manual entry.

Zero transcription errors — read directly from the source
Works on any nameplate: aviation, CNC, automotive, marine, military
Add an asset in 10 seconds instead of hunting for references
📷
screenshot: nameplate scan
FEATURE 02 — DOMAINS

16 Preconfigured Technical Domains

Every industry has its own manufacturers, terminology, and standards.

Aviation, CNC Machining, Automotive, Robotics, Marine, Medical Devices, Energy, and more. The moment you select a domain, the system adapts manufacturers, models, subsystems, and search angles. An aviation technician never sees CNC manufacturers.

Instant relevance — everything adapts to your industrial context
No noise — each domain has its own reference set
Extensible with a custom field for any unlisted domain
🏭
screenshot: domain selection
FEATURE 03 — MANUFACTURERS

Intelligent Manufacturer Detection

24 to 36 manufacturers generated dynamically per domain.

An LLM call generates the list of relevant manufacturers — global leaders, mid-tier players, and niche specialists. Each manufacturer is classified by tier with a visual badge. A free-text field lets you enter any unlisted manufacturer.

Exhaustive coverage — the LLM knows thousands of manufacturers per industry
Major / mid / niche badges for quick identification
Never blocked — custom field always available
🔧
screenshot: manufacturer list with badges
FEATURE 04 — MODELS

LLM-Enriched Model Selection

36 to 50 models per manufacturer, organized by category.

The LLM generates a complete model list grouped by category, tagged entry/prosumer/pro. Both current and legacy models still in service are included — because many machines in the field are 10, 20, 30 years old.

Legacy models included — your 1998 Fanuc is covered
Organized by category — not 50 models in a flat list
Full adaptability via custom field
📋
screenshot: model list by category
FEATURE 05 — SUBSYSTEMS

Subsystem Toggle Controls

The system knows what your machine is made of.

For each piece of equipment, the LLM identifies 8 to 12 subsystems. Each chip is clickable to enable or disable. Only activated subsystems are used for documentation search — less noise, more relevance.

Fine-grained customization — disable a removed subsystem in one click
Targeted search — each active subsystem generates specific queries
Visual counter "8/12 active" shows coverage at a glance
⚙️
screenshot: subsystem chips
FEATURE 06 — CORPUS

Corpus Builder — 5 Search Angles

Your equipment's documentation, found automatically.

The Corpus Builder launches 44 queries per angle — Maintenance, Operation, Training, Parts, and All — covering manufacturer, model, subsystems, and technical terminology. 30 to 80 PDFs found and ranked in 5 to 15 minutes.

44 queries cover all publicly available documentation
Every PDF gets a trust score — low-quality documents are filtered out
Zero effort — what would take 2–3 days happens in minutes
🔍
screenshot: corpus builder in action
FEATURE 07 — KNOWLEDGE GRAPH

Knowledge Graph Pipeline — 3 Presets

Transform PDFs into queryable knowledge.

The KG Pipeline extracts knowledge from each document into structured Knowledge Units. Three presets: Economy (fast), Optimal (balanced), Max Quality (multi-pass with validation). Each KU contains a fact, its source, and confidence metadata.

Full traceability — every RAG answer traces back to the source PDF and exact page
Budget flexibility — Economy to test, Max Quality for critical production
Continuous enrichment with your internal documents
🧠
screenshot: KG pipeline presets
FEATURE 08 — UPLOAD

Internal Document Upload

Your proprietary manuals enrich the Knowledge Graph.

Drag & drop zone for PDF, Word, Excel, images, CSV, TXT. Associate each document at the fleet level, per model, or per specific machine. Internal documents contain the information that public documentation doesn't have.

10x precision with your proprietary data
Smart association — by model or by specific unit
Multi-format — Word, Excel, images, PDF, plain text
📁
screenshot: drag & drop upload zone
FEATURE 09 — RAG CHAT

RAG Chat with Context Selector

Ask questions about the right equipment.

The RAG Chat includes an asset selector. Context — manufacturer, model, callsign, subsystems — is injected into every question. Switch equipment in one click. Every answer cites its source PDF with the exact page.

Contextual precision — same question, different answers per equipment
Instant context switching between your machines
Traceable citations back to the source document
💬
screenshot: RAG chat with citations
FEATURE 10 — COVERAGE

Coverage Report — GO / NO GO

Know if your documentation is complete.

Score out of 100 with a GO / CAUTION / NO GO verdict. Five criteria evaluated: assets added, sufficient corpus, internal documents, subsystems covered, KG generated. Detailed breakdown per asset with clear actions for gaps.

No surprises — know what's missing before going to production
Actionable — every failed criterion has a clear next step
Per-asset detail — which equipment is covered, which isn't
screenshot: GO / NO GO report

An assistant, not a form.

The Wizard anticipates what you need at every step.

🔗

Contextual Anticipation

Every step uses previous choices to preconfigure the next. Domain determines manufacturers. Manufacturer determines models. Model determines subsystems. Nothing is generic.

Background LLM Calls

Language model calls run in parallel while you interact. You never see an empty screen or a loading spinner blocking your workflow.

🔓

Never Blocked

At every step, a free-text field lets you bypass the suggested list. The LLM adapts to any input — listed or not.

👁️

Continuous Visual Feedback

Chips that change opacity, real-time progress bars, status badges, counters. Every action produces an immediate visual response.

🛡️

Intelligent Data Protection

Asset deletion requires password confirmation in a secure modal. Destructive actions are deliberately slowed down. Your data is safe.

🌐

Multilingual Native

The LLM understands French, English, and German. The Knowledge Graph is multilingual. Ask in any language, get grounded answers.

GET STARTED

Ready to see it with your documentation?

Try the live demo with 35,606 Knowledge Units, or request a demo with your own technical documents.

Try Live Demo Request Demo