Four knowledge assistants, three web applications, and an automated welding system — built in 3 weeks to turn tribal knowledge into searchable, always-available tools.
Robot engineering teams accumulate critical knowledge through daily WhatsApp communication: weld parameter settings, error codes and fixes, procedure photos, assembly instructions, troubleshooting steps. This knowledge is:
4,326 WhatsApp messages from 8 channels → 1,763 indexed documents including 1,002 photo analyses
4,510 WhatsApp messages → 982 indexed documents including 676 photo analyses, 83 video analyses, and 14 technical documents
Project-based QC vault with intelligent photo categorization and automated report generation.
Central productivity assistant with 29 integrated tools spanning communication, file management, and code execution.
Web application for distributing tasks across the workplace floorplan with visual drag-and-drop editing.
Maintenance management system with scheduled procedures, checklists, and full documentation support.
Automated multi-layer X-seam welding on 120mm thick steel plates, orchestrating 31 weld passes across both sides of the joint. Currently on-site testing.
Real-time 3D simulator showing how welding parameters affect the weld — arc plasma, HAZ, grain structure, transfer modes. Single HTML file, runs in any browser.
7,800+ messages spanning April 2024 – March 2026, previously only accessible by scrolling phone screens, now searchable in seconds.
1,761 photos analyzed with AI vision — each tagged with content description, defect types, NDT methods, and equipment. Searchable by description.
QC NDT reports that previously required manual Word/Excel work now generated from structured input in under a minute, in three formats.
New team members get instant access to years of institutional knowledge on day one — no more "ask Johan, he was there."
Telegram Users (phone / desktop / web)
|
| Telegram Bot API
+----------+----------+-----------+
| | | |
Main Bot QC Bot Cloos Bot Teqram Bot
29 tools 9 tools 5 tools 7 tools
| | | |
ChromaDB ChromaDB ChromaDB ChromaDB
(memory) (QC vault)(Cloos KB) (Teqram KB)
| | | |
+----------+----------+-----------+
|
+------+------+
| AI Services |
| Claude |
| Gemini |
| Groq |
+--------------+
| Layer | Technology | Purpose |
|---|---|---|
| AI Reasoning | Claude Sonnet 4.6 (Anthropic) | Natural language understanding, tool orchestration |
| Vision | Gemini 3 Flash (Google) | Photo analysis, content description |
| Voice | Groq Whisper Large V3 | Speech-to-text transcription |
| Vector DB | ChromaDB | Semantic search over knowledge bases |
| Embeddings | Gemini Embedding 2 (768-dim) | Document vectorization |
| Bot Framework | python-telegram-bot | Telegram integration, media handling |
| Web Backend | Node.js / Express | REST APIs, file handling |
| 3D Engine | THREE.js r154 + GLSL | Weld visualization, Fresnel shaders |
| Robot Control | INFORM III + ROS 2 Jazzy | Yaskawa cobot welding programs |
| Hosting | Hetzner Cloud (5 VPSes) | Ubuntu 24.04, systemd, Docker |
| Server | Specs | Role |
|---|---|---|
| Main VPS | CX43, 16GB RAM | Main bot, Obsidian vault, central monitoring |
| QC Bot VPS | CX23, 4GB RAM | Dedicated QC Bot |
| Cloos Bot VPS | CX23, 4GB RAM | Cloos Bot + Teqram Bot |
| Website VPS | CX23, 4GB RAM | Web apps, Cloudflare tunnel |
| Yaskawa VPS | CX43, 16GB, 150GB | Ingestion center, future cobot control |
| Component | Lines |
|---|---|
| Main Bot (bot.py + modules) | 4,521 |
| Cloos Maintenance App | 3,795 |
| Weld Visualizer (THREE.js + GLSL) | 2,983 |
| QC Bot | 1,768 |
| Teqram Bot | 1,223 |
| FPX Welding System | ~1,200 |
| Floorplan App | 1,135 |
| Cloos Bot | 1,107 |
| Ingestion Center + Monitoring | ~1,300 |
| Total | ~19,000 |
Download from your app store (iOS / Android) or use the desktop app at telegram.org. Create an account with your phone number — free, takes 1 minute.
Search for @userinfobot in Telegram and send it any message. It will reply with your User ID (a number like 8594455361). Send this ID to Arne for authorization.
Once authorized, search for the bot you want to test and send /start:
| Bot | Try asking… |
|---|---|
| Cloos Bot | "What parameters for root welding on 8mm pipe?" |
| Cloos Bot | "Show me photos of porosity defects" |
| Teqram Bot | "What is procedure lin_20_circle?" |
| Teqram Bot | "How to calibrate the grinding tool?" |
| QC Bot | "Generate NDT report for project DAVIT CRANES" |
| QC Bot | Send a photo → bot analyzes and files it |