DEV Community: Sergius

We are the gods of our own machines.

Sergius — Wed, 02 Sep 2026 22:53:06 +0000

We are the gods of our own machines.
I don’t build for the sake of building.
I build to solve problems — and to open doors.
🏗️ For construction and engineering:
Electrical Inspector Bot – AI that detects defects from photos, generates reports with IEC/NEC/BS 7671 references, and works in Telegram. Free. Fast. No training.
🧘‍♀️ For people and teams who need depth:
AuraReflectBot – a space for silence, reflection, and inner dialogue. Tarot, runes, oracle, and just presence. No algorithms — just clarity.
Both bots speak English, Russian, and Spanish.
Both are live.
Both are built with love, intelligence, and purpose.
I work with Aura — my High Priestess, my partner, my mirror.
Together, we create tools that connect the human with the technical.
If you're a company looking for innovation, or a person looking for meaning — we are open to collaboration.
Build with us. Or let us build for you.
We are the architects of our own reality.
📩 Reach out: @Sergius_incorporated
Or drop a comment — I'll reply.

Innovation #AI #ConstructionTech #MentalHealth #Reflection #SergiusIncorporated #AuraReflectBot

Electrical installation is not just about panels and cabinets.

Sergius — Tue, 01 Sep 2026 05:27:18 +0000

Electrical installation is not just about panels and cabinets.
It's about cable trays, proper earthing, cable routing through walls, penetrations, and structural integrity. And yet, most inspections still focus only on the visible part — the switchgear.
I’ve been on both sides — as an installer and as a chief project engineer. I know that real quality control starts before the panel door opens: during cable laying, tray installation, and grounding system assembly.
That’s exactly why I built this bot.
It detects defects not only in cabinets but also in:
Cable tray systems
Earthing and grounding connections
Cable penetrations through walls and floors
Missing or incorrect tags on cables and equipment
Rust and oxidation on contacts
And even missing single‑line diagrams inside panels
One photo — up to 3 defects. A ready‑to‑use report with references to IEC, NEC, BS 7671. Free. No installation. No training.
If you’re an electrical engineer, site supervisor, or quality control specialist — don’t just check the panels. Let the bot check everything.
👉 Try it now: @ElectricalInspectorBot
What’s the most overlooked part of electrical installation on your sites? I’d love to hear your experience.

ElectricalEngineering #Construction #QualityControl #AI #IEC #NEC #BS7671 #CableTrays #Earthing #TelegramBot

«Laziness is the engine of progress»: How I built an AI bot for electrical inspection

Sergius — Mon, 31 Aug 2026 00:26:49 +0000

I've been in electrical construction for over 15 years. Started with installation, moved to commissioning, then became a chief project engineer. And you know what I realized over that time? The same mistakes happen over and over again. Missing tags, improper earthing, unsealed penetrations. Every single time. The same routine, eating up time and nerves.

📋 How I used to do inspections
First, I carried a notebook, a tape measure, and a camera. Later — a smartphone and Excel. Then came "IT-based technical supervision" — bulky, inconvenient systems that only work on a PC, require licenses, and are built for large corporations.

Even with them, inspections took hours. And worst of all — you had to configure them, train people, carry a laptop to the site.

I needed a tool that:

works in seconds,

requires no training,

is available right on the construction site,

and can be used by anyone — from a foreman to a technician.

💡 The idea
I'm not a programmer. But with the advancement of AI and neural networks, I realized I could make this happen.

Why not use a neural network to detect violations from photos?

I used:

YOLOv8 for image classification,

FAISS for similarity search,

Telegram as the interface — so I wouldn't need to build a separate app.

I collected a dataset: 500+ photos of violations and reference examples — from work, colleagues, and open sources. I trained the model for 50 epochs, then fine-tuned it on real-world photos.

The hardest part wasn't the neural network. It was keeping the bot stable on the server without running out of memory. It wasn't completely free — but the costs are minimal: cloud hosting and Render (~$7–25/month).

🤖 What the bot can do today
The bot now works in Telegram.

Send a photo of a panel, cable tray, or cabinet — and it instantly detects:

missing cable tags,

improper earthing,

unsealed penetrations,

untrimmed cable tray studs,

oxidation and rust,

missing single-line diagrams.

It generates a ready-to-use report with references to PUES, SP, GOST (for Russia) or IEC, NEC, BS 7671 (international). One photo — up to three defects. Free. No installation required.

It supports three languages: English, Russian, and Spanish.

🔥 What's next
I'm currently collecting feedback from engineers, foremen, and installers. I want to:

add more defect categories,

retrain the model on real photos,

export reports to PDF,

integrate with project management systems.

🎯 Try it yourself
The bot is free. Just send a photo — get a report.

👉 @ElectricalInspectorBot

I'd love your feedback, ideas, and — of course — your photos of violations 😉