Andrey Melkov

[andreymelkovv]

Demonstration demo version Industrial AI

https://www.linkedin.com/feed/update/urn:li:groupPost:19650012-7486427462319386627?utm_source=social_share_send&utm_medium=member_desktop_web&rcm=ACoAAAHgus0BPbIHNk5udi2gApKMW32rDIJKzQU

[andreymelkovv]

Artificial intelligence earns confidence one explanation at a time.

Speed attracts attention.

Trust creates adoption.

[andreymelkovv]

People often talk about AI as if it's a technology story.

In manufacturing, it's increasingly a process story.

One factory spends hours searching documentation.

Another asks an AI assistant and gets the answer in seconds.

One factory discovers a machine failure after production stops.

Another sees it coming days in advance.

One factory relies on manual inspection.

Another has cameras checking every product around the clock.

The difference isn't intelligence.

It's friction.

AI keeps removing small pieces of friction from industrial systems.

And eventually those small differences become a very large gap.

[andreymelkovv]

Are you still considering it?)

[andreymelkovv]

Funny enough, industry's "ChatGPT moment" didn't happen when ChatGPT launched.

It happened when companies stopped treating AI like a science project.

For years, everyone was running pilots, demos, and proof-of-concepts. Most of them never went anywhere.

Turns out the hard part wasn't building the AI.

The hard part was cleaning up years of messy data, integrating systems, and figuring out where AI could actually make a difference.

The most successful use cases aren't flashy.

They're things like predicting machine failures, helping engineers find answers faster, automating inspections, and reducing downtime.

That's probably the most important shift happening right now:

People are asking less "What can AI do?"

And more "What problem can AI solve today?"

[andreymelkovv]

Don't build a chatbot that tries to be your whole company. Start with the 10 things people ask 80% of the time.

Hybrid is best: buttons for clear paths, AI for messy questions.

Connect it to your CRM. Otherwise it's just a fancy FAQ.

Measure: how often does the bot solve it alone? How fast? When does it fail?

Pilot for a month. Watch what breaks. Fix. Add more.

The goal is not to fire support people. The goal is to stop making them answer "what's my order status" 50 times a day.

[andreymelkovv]

You see ads: "how to exit operations". Two million search results.

Delegation is not the same as having a system.

I left my business for a year. Thought it would run itself. Came back to zero.

Why don't owners build processes? Not because it's hard. Because they're scared.

Scared it won't work. Scared employees will quit. Scared someone smarter will join. Scared to see the truth.

But chaos is worse. So yes, a business as a system is possible. Start small. One process at a time. Face the fear.

[andreymelkovv]

A transport company had a problem: truck inspection took 181 minutes. Target was 150. That extra half hour meant only 5 trucks per day instead of 6.

They thought mechanics were slow. Nope.

Mechanics were WAITING.

- Writing in paper logs

- Waiting for a supervisor to walk over

- Waiting for parts room to get the message

So we automated the handoffs.

Now a mechanic uses a mobile device. Finish one step – next step opens automatically. No paper. No running around.

Find a defect? The system tells the supervisor AND the parts room instantly. The warehouse reserves parts before the mechanic finishes the inspection.

Result: 150 minutes. Six trucks a day. No new hires. No new lifts.

The process just… works now.

Moral: don't blame people. Look at where they wait.

[andreymelkovv]

You have a 1‑hour meeting recording. You ask AI: "when did Ivan promise the delivery date?" The AI gives a vague answer because someone summarised the video and lost the timestamp.

Bad approach.

Better approach: a team of three AI agents.

- Navigator – finds the exact 30‑second window where Ivan spoke.

- Eyes – looks at that window and sees "Ivan, slide with 'delivery: May 15'".

- Master – checks if that's enough, then answers: "At 23:45, Ivan said May 15."

Accuracy goes from 64% to 75%. Not magic – just not throwing away information.

How to build it (5 steps):

1. Get subtitles with timestamps (Whisper works).

2. Split into chunks, keep timestamps, put in a database.

3. Teach Navigator to find relevant time windows.

4. Add Eyes only for visual questions (slides, objects, people).

5. Master collects everything and gives a timestamped answer.

Rule #1: never lose timestamps. Rule #2: never analyse the whole video at once.

Works for meetings, lectures, surveillance, anything with video + time.

[andreymelkovv]

We did our first webinar on AI in industry. Technical prep, cost calculation, quality control, document processing.

The audience wasn't huge – but it was the RIGHT people. Technologists. Production heads. Owners. People who actually do the work.

What I liked: talking to people who get it. That's rare and valuable.

What I'll change next time:

1. One hour is a joke. We need 1.5‑2 hours. Deep dives take time.

2. I want to show one complete process from start to finish (blueprint → tech card → price). But then I can't cover everything. Maybe a series. One webinar = one deep story.

3. More live questions. When the audience is silent, I don't know what they need. Next time: ask questions in advance, or bribe people to unmute.

So – if you work in industry or with AI – what would actually help you?

- Case studies?

- Live demo?

- ROI math?

- Our screw‑ups (there are many)?

Tell me. Because the next one is happening.

[andreymelkovv]

So your AI assistant confidently tells a client "the invoice is issued" but never actually created it in the system. Classic hallucination. Not magic. Just bad engineering.

Here's what neuroscience says: the brain predicts, does something, sees what happened, compares, fixes. LLMs don't do that. They just generate text.

We need three things AI is missing:

1. **Real actions** – not "I'll write that I sent an invoice" but actually calling the API to create it, then checking it exists.

2. **Hierarchy** – the brain stores goals and rules at the top, messy details at the bottom. AI loses important stuff in the middle of a long chat. So store structure (deadline, budget, agreements) separately from chat noise.

3. **Memory that writes back** – not just reading old docs (RAG). The AI needs to remember what went wrong last time, then at night "sleep" on it and turn mistakes into rules.

Also – **invariants**. Hard rules that cannot be broken. Like: no invoice without bank details. No discount above 10% without manager approval. Check these AFTER every action but BEFORE replying to the customer.

Five steps to make it work:

1. Turn each deal into a structured card (15‑30 fields)

2. List allowed actions (only these, nothing else)

3. Write down 10 invariants

4. Log everything

5. Nightly processing

Result: AI that double‑checks reality. Fewer lies. More trust. And you don't need a PhD in neuroscience – just a bit of structure.

[andreymelkovv]

Headline: "95% of companies got no value from AI"

Panic. "See? AI is useless."

But the study said: 95% of companies never scaled past pilot. They tried a little, didn't commit, gave up.

That's not AI's fault. That's bad implementation.

Also, Andrej Karpathy: chatbots beat the average human. But not the expert human. Your best lawyer is still better than ChatGPT. For now.

So AI isn't a flop. It's just not magic. It's a tool. Some people use it well. Most don't.

If you want it to work: clean your data, train your people, start small, and don't expect miracles.

Also, don't believe hype. Either the "AI will kill us all" hype or the "AI does nothing" hype. Reality is in the middle.

[andreymelkovv]

Your corporate AI chatbot was smart on day one. Now it's dumb. It quotes old policies. It makes up facts.

Why? Because its brain (the knowledge base) never changed. The world changed, but the AI didn't.

You think: "Let's make it save its own good answers." Good idea. But if you save everything, you also save its mistakes. Then it learns from its own lies.

We built a filter. Before any answer gets saved, three checks:

1. Can you prove it with a real document?

2. Is the link real?

3. Is this new information (not a duplicate)?

Result: The AI learns slowly but never gets dumber. It adds only good stuff.

Cost: slower processing. But for a knowledge base that updates overnight? Worth it.

[andreymelkovv]

You want to use ChatGPT. But you need a foreign card. Also a VPN. Also the VPN breaks every Tuesday.

There's a Russian service. You pay in rubles. No VPN. They give you access to ChatGPT, Midjourney, DeepSeek, all of them.

Also they have a drag‑and‑drop automation thing (n8n). You can connect email → AI → Telegram in 5 minutes. Costs about 22 rubles a day when you use it.

Data stays in Russia. No foreign servers.

Is it magic? No. It's just a middleman that solves the payment and access mess. Works fine.

[andreymelkovv]

2009. Everyone was panicking. We started a company.

First client: a factory that had been trying to implement 1C for two years. Nothing worked. People hated the system.

We came in. Four months. We didn't add anything fancy – just cleaned up the mess. Found €200k just sitting there in bad logistics, double entries, unaccounted stock.

Then a sausage company. Farm to fork. That took 1.5 years.

After that we thought: we need a logo with meaning. So we used runes. ᛏ for determination, ᚨ for communication, ᛒ for growth.

We still have that logo. Because the principles still work: find the chaos, clean it, grow.

[andreymelkovv]

30 people. Scanned documents. Typing numbers. All day. Every day. People quit every 6 months.

We put an AI on a local server (no cloud because state secrets). It reads scans. It types into 1C. 98% accuracy. 10 seconds per doc.

Now 7‑8 people check the AI's work and handle weird cases. The rest moved to real accounting. Month‑end doesn't require panic anymore.

Also saved 900k rubles a year on outsourcing.

The accountants? They're happy. Because they stopped being typing monkeys.

[andreymelkovv]

A room full of people typing numbers from PDFs into a database. By 5pm, everyone's eyes blur. Mistakes happen. Mistakes on million‑ruble contracts = fines + lawyers.

We built an AI that reads the PDFs. It finds the INN, the OGRN, the cadastral number, the date, the amount. In 30 seconds.

Accuracy 90%. Errors down 80%. The humans now check the AI's work instead of typing everything.

They don't hate their job anymore. The company doesn't get sued anymore.

That's a win.