I build AI systems that actually do things.

I designed and built a custom CRM and business management platform for a robotics and technology school. The system centralizes customers, students, groups, payments, salaries, rent, and operational expenses.

Instead of functioning only as a contact database, the CRM acts as a business control panel. It automatically calculates revenue, operating expenses, teacher salaries, rental costs, profit, and profitability by individual student group.

Group-level economics makes it possible to identify which classes are profitable and which require changes in occupancy, pricing, scheduling, or costs — turning fragmented operational data into a single interface for day-to-day business decisions.

It keeps evolving with the business: each payment is now tied to a specific group, revenue is recognised as lessons are actually delivered, rent is tracked per studio, teacher rates can be set per teacher and per studio, and groups can meet on several days a week.

A salesperson's own Telegram, inside the CRM deal card.

AmoTg — amoCRM ↔ Telegram integration

Small sales teams often talk to clients from personal Telegram accounts, so those conversations never reach the CRM — and standard connectors only work with bots. I built AmoTg: it connects a real Telegram account to amoCRM through the MTProto protocol and the amoCRM Chats API. Every private conversation appears in the deal card, and managers can reply or write first without leaving the CRM.

It started as an internal tool for a school and grew into a product line: a sales landing page with lead capture; a portable deployment kit for client installations, either on the client's own server or hosted on mine with a separate container, network and encryption key per client; and a multi-tenant version for the amoMarket marketplace with an in-CRM widget, OAuth, billing and a support bot, now in marketplace review.

The hard part is reliability and trust. Telegram delivers each event only once, so messages in both directions go through an outbox and are retried instead of being lost. Webhooks are signature-checked, Telegram sessions and CRM tokens are encrypted at rest, and the first message from a new contact brings the recent conversation history into the deal card.

AI that reads the whole deal before it says anything.

Client archetype classifier and call transcription for amoCRM

In production for a B2B client

For a B2B sales team I built two integrations for amoCRM. The first reads everything attached to a deal — chats including Telegram, emails, documents, notes and call transcripts — and classifies the client on two axes from the company's own ICP methodology: which customer segment the company belongs to and what role the person plays in the purchase.

Precision matters more than coverage. A value is written only when two independent model runs agree with at least 70% confidence; otherwise the system keeps collecting evidence. Each decision comes with a note listing the facts behind it, and a manager's manual edit locks the field for good. The pipelines it may touch are enforced in code, and mail access is strictly read-only.

The second integration transcribes every completed call: a placeholder note appears in the deal at once, the recording is transcribed on the server, and the note is replaced with the dialogue split into manager and client lines. The two services share nothing but CRM notes, so either can change or fail without breaking the other, and all processing stays in the client's country.

Python · amoCRM API · Webhooks · GigaChat · faster-whisper · IMAP · SQLite · Docker

The agent drafts. A human presses Send.

Margo — SMM and inbox agent

Margo is a persistent AI agent that runs a school's content workflow through Telegram. I send an idea as text or a voice note; she writes the post in my style, generates images and carousels, and prepares versions for LinkedIn, Instagram, Telegram, TikTok and X. Nothing is published without explicit approval of each post.

Her second job is the admin inbox. When a parent writes to the school's Telegram account, a small daemon waits for the conversation to settle, wakes the agent through a signed webhook, and she leaves a reply as a Telegram draft that syncs to my phone.

The approval rule is enforced in code, not in the prompt: the agent's Telegram toolset has no send function at all. Voice notes are transcribed locally, and the agent runs in its own isolated container with its own credentials.

Hermes Agent · GPT · MCP · Telethon · Whisper · Webhooks

Automating the customer journey from first message to payment.

Currently in development

I am developing an AI-powered administrative automation system for a robotics and technology school. The goal is to remove repetitive administrative work throughout the customer journey.

The system handles common customer questions, guides prospective customers through the enrollment funnel, helps them reach trial lesson registration, sends payment reminders, collects payment confirmations, and organizes the relevant documents for accounting.

The objective is not to create another chatbot. It is an end-to-end operational workflow where AI can perform actions across the business process while escalating situations to a human when necessary.

A school website where no enquiry gets lost.

Public website, enrollment form, student questionnaire

I built and launched the public website for a robotics and technology school: a fast static landing page with an enrollment form, served from my own infrastructure. A submitted form reaches a small backend that notifies the team in Telegram within seconds, and the visitor lands on a dedicated thank-you page that works as a URL-based conversion goal for ad and analytics platforms.

A separate questionnaire collects student details before the first lesson. Every submission is written to disk before any notification is sent, so nothing is lost if Telegram is unavailable; each gets a readable ID, and spam is filtered with a honeypot field and a per-IP rate limit.

The bot token never reaches the browser, and the recipients are allowlisted in the backend code, so even a modified config cannot redirect applications elsewhere.

HTML/CSS · Node.js · Python · nginx · Caddy · Telegram Bot API · Web analytics

One agent for everyday operations.

I deployed a persistent AI assistant that helps coordinate recurring tasks in everyday life. Instead of using separate tools for every small workflow, the agent provides one conversational layer between me and external services and information.

The project focuses on an important part of agentic systems: moving from isolated prompts to persistent agents capable of tracking context and working with external tools.

Hermes Agent · GPT · APIs · OAuth

Revision as a game, not a test.

Kahoot-style live classroom quiz

For my AI course I wanted students to review each lesson through play. I built a real-time quiz: the host screen shows a PIN and a QR code, students join from any device, answer against the clock, and finish with a leaderboard and a podium.

Designed from both the teacher's and the student's side: points depend on speed, answer options are shuffled, and every game is saved on the server with a results page and CSV export, so the teacher can review how each student did. It ran on the course server through a secure tunnel, without opening inbound ports.

Node.js · Express · Socket.IO · Web Audio · Docker · Cloudflare Tunnel

I designed and operated the technical infrastructure for an AI application development course with 18 students. I provisioned and configured the server and created an isolated containerized environment for every participant, where they could build and deploy applications without interfering with anyone else's work.

I also taught students how to access a remote server, work inside their environment, deploy applications, and operate their own services. The objective was to move beyond local prototypes and teach how software actually reaches a running server.

For the next cohort of 16 students I rebuilt the setup around personal AI agents. Each student gets an isolated container with their own SSH key and resource limits, a pre-installed Hermes agent they configure themselves — personality, rules and projects — and a live quiz at every lesson. Containers reach the internet but not each other, the host or the cloud's internal network.

Linux · VPS · Docker · Containers · Hermes Agent · AI Development Tools

I couldn't find the learning tool I wanted, so I built it.

Falar — Personal European Portuguese learning app

The project started from a practical problem: many mainstream language-learning products focus primarily on Brazilian Portuguese, while I needed a learning experience closer to the language used around me in Portugal.

I created a dedicated application around my own learning workflow and continue iterating on it through real daily usage. The project combines my experience in education, product design, software development, and AI-assisted learning.

It now has English and Russian interfaces, installs as an offline app, syncs progress across devices and uses self-hosted, cookie-free analytics.

Owning the infrastructure behind the tools I use.

Most of the systems on this page run on a server I operate myself: more than twenty containers — four AI agents, the school CRM, websites, hosted client integrations and analytics — behind a single reverse proxy with automatic TLS and security headers.

Each agent gets its own container, storage, credentials and bot, with memory limits per service. Data is backed up nightly with encryption to a separate volume with daily and weekly retention; SSH is key-only and brute-force attempts are banned automatically.

I also run private network services for my family: a VPN with client isolation and a two-server private network that routes traffic by destination.