Your team burns
30 hours a week
on work I automate

Senior AI Automation Engineer. I build n8n workflows, RAG search over your own documents and multi-agent systems that run around the clock without babysitting. Ten products run on my own servers and stayed available more than 99.5% of the last 30 days. Your team stops shuffling data and starts doing work only they can.

Free task estimate See live cases

Describe one process. Within one business day I tell you whether it can be automated, what it takes and what it costs. No pitch, no commitment.

10 applications in production
Ukraine · Europe · Remote
Ihor Kostyniuk, Senior AI Automation Engineer Ihor Kostyniuk, Senior AI Automation Engineer
Ihor Kostyniuk
Senior AI Automation Engineer · LLM agents, MCP, RAG, Voice AI
10
Apps in production
2.5y+
Experience
1
business day to reply
WHAT I DO

Services that actually move the needle

What you get, how it runs and what it costs. The projects behind it are in the next section.

Workflow Automation

Your systems exchange data on their own. Built on n8n, running on your server or mine, with monitoring wired in: a broken flow raises an alert instead of going quiet.

  • n8n on your server or on mine
  • 400+ ready integrations, the rest over API
  • Uptime monitoring and failure alerts
from $150

AI Agents & RAG

An agent that answers from your documents, not from the internet. Search over your own knowledge base, calls to your own tools, answers checked by a judge model before they reach anyone.

  • Qdrant or pgvector over your knowledge base
  • Tool calling and custom MCP servers
  • Several providers with automatic fallback
from $300

Hiring & ATS

Screening stops being a manual step. Vacancies and candidates arrive on their own, CVs are parsed, fit is scored, the technical interview is generated.

  • Job collection across 17 boards
  • CV parsing and fit scoring
  • EU AI Act: DPIA, DSAR, human in the loop, bias monitoring
from $150

SaaS & Custom Apps

The whole product: web, Android, desktop and the server under them. Multi-tenant with data isolation, auth, billing, over-the-air updates.

  • Next.js + Supabase, RLS on every table
  • Native Android (Kotlin) and desktop (Tauri)
  • Docker, monitoring, nightly backups
from $500
REAL PROJECTS

Cases that speak for themselves

Every number below comes from my CV, which is open in full.

Check it against the CV
Client · since 2026

Generative video pipeline

Consolidated production into 6 reusable pipeline skeletons and grew it from 3 to 12 client channels. Renders run for hours per job: checkpointed state so any stage resumes after a crash, retry with backoff, circuit breakers around each provider. Then handed rendering over to the clients (bundled installer, deploy keys, one-click update), so they run it on their own hardware.

3→12
Channels
$22-30
Per film
~235
Scenes each
Client · since 2024

AI support across 7 channels

WhatsApp, Telegram, Viber, Instagram, Facebook, web and email all reach one agent. RAG is separate per tenant. Cleared Meta App Review for production messaging permissions. The site widget speaks the host page's language, is screen-reader accessible, and writes a visitor who leaves a phone number straight into the CRM.

7
Channels
Meta
App Review
RAG
Per tenant
Client · recruiting

Recruiting CRM under the EU AI Act

Multi-tenant CRM: 33 migrations, RLS on every table, a subdomain per workspace, around 20 AI tasks including CV parsing, few-shot-calibrated ATS scoring and outreach generation, fed by a 17-source scraping pipeline. Compliance built in: DPIA and DPA templates, self-serve DSAR export and erasure, human score overrides with an audit trail, a bias-monitoring dashboard.

17
Job sources
~20
AI tasks
86+
Security tests
Client · 2025–2026

Documents and operations

Audited four business functions (procurement, accounting, legal, recruitment), turned the bottlenecks into implementation specs, then built the systems those specs described. Contracts and reports are assembled from templates with docxtemplater and Gotenberg: drafting became filling a form. Plus the operations app the teams work from: scheduling, run monitoring, work hours and spend in one view.

4
Functions audited
SmartSuite
System of record
Docker
Under all of it
Own product · in production

Monitoring that watches itself

One view over 9 servers and 36 watchdogs. A dead-man switch raises an alert when the monitor itself dies, and a native Android app delivers push alerts. The same approach is in the Managed package: when a client's flow goes quiet, I know before the client does.

9
Servers
36
Watchdogs
Android
Push client
Own product · in production

Content pipeline with one-tap approval

LinkedIn, Instagram, Telegram and Threads from one pipeline. Every post is fact-checked against 18 sources and cross-checked by two models, and goes out only after one tap in Telegram. Routing across providers with automatic fallback keeps the daily cost near zero. The same can be built for your personal brand.

4
Channels
18
Fact-check sources
2
Models cross-check
RECOMMENDATIONS

What the people who worked with me wrote

Three recommendations from LinkedIn, quoted word for word. They stay in the language they were written in.

AM
Alex Merchenko
Head of Sales & Business Consultant · Sales Strategy & Audits
Client

“We had Ihor build a lead qualification bot for our agency. Before that, our sales guys were jumping on every call, half of them going nowhere.”

“The bot now handles first contact. Asks the right questions, scores the lead, routes the serious ones. By the time a salesperson picks up, the conversation is already half done.”

“Lead qualification time dropped around 60%. That tracks with what we saw. The team stopped burning afternoons on dead-end calls and actually started closing.”

“Delivered clean, no drama after launch. Would recommend for any sales team that’s tired of chasing unqualified inbound.”

May 2026 · LinkedIn
~60%
less time qualifying a lead
The client’s own figure, from the recommendation above
OV
Oleksandr Vashchyshyn
AI Engineer
Team lead

“I was Ihor’s team lead and watched him working across several internal projects. Document generation, ATS pipelines, workflow integrations. He handled all of it.”

“What I noticed pretty quickly was that he didn’t need handholding. You’d give him a task and he’d come back with it done, plus a few things you hadn’t thought to ask for.”

“Infrastructure side was solid too. Docker, self-hosted setup, monitoring. Stuff just worked. And when something went wrong, he usually knew about it before anyone else did.”

“Good automation engineer, easy to work with. Would recommend him for any team doing serious AI automation work.”

May 2026 · LinkedIn
PS
Parsla Sietina
Business Analyst · Process improvement & analytics
Colleague

“As a colleague he demonstrated a strong analytical mindset, exceptional problem-solving skills, and a genuine willingness to help others. No matter how complex the challenge was, he approached it with patience, curiosity, and determination to fully understand the root cause before finding the right solution.”

“He has a great ability to break down complicated processes, think critically under pressure, and come up with practical solutions to issues that initially seemed impossible to resolve. He was always approachable, collaborative, and ready to support colleagues whenever needed.”

May 2026 · LinkedIn
Check them on LinkedIn
WAYS TO WORK

Start with an audit call, then pick what fits

Each package includes the one before it, except the one-off audit call. Monthly, no long contracts.

Audit call

You are stuck and not sure what to automate first.

$35 / hour
  • A call about your tasks
  • Notes and a plan in PDF after the call
  • 7 days of questions on the plan
What's included
Included
  • Five short questions before the call, so the call goes to your task
  • The call on whatever platform works well for you
  • PDF: what to automate first, with which tools, what to do yourself and what to hand off
  • Follow-up questions in chat for 7 days
Not included
  • Hands-on work in your accounts
  • Development

Paid before the call.

Book a call

Chat support

You build it yourself and want someone to ask.

$100 / month
  • Questions in Telegram: text, screenshot, voice
  • Replies on weekdays within one business day
  • Help with tools, flows, prompts and errors
What's included
Included
  • Advice on tools and how to structure an automation
  • Review of your flows and prompts
  • Error triage from a screenshot or a log
Not included
  • Hands-on work in your accounts
  • Calls
  • Development

If an answer takes more than 30 minutes of work, it is a task: I quote it separately.

Start support

Managed

Recommended

You want the automations to work without you looking after them.

$200 / month
  • Everything in Chat support
  • Up to 5 hours of work a month
  • I hear about a failure before you do
What's included
Included
  • Fixes, improvements and small new flows in your tools
  • A 60-minute call once a month
  • Key flows check in on schedule, and silence raises an alert on my side
  • A short report at the end of the month
Not included
  • Large projects: that is a custom build

Over 5 hours: $35 an hour, after we agree. Unused hours do not roll over.

Hand it over

Business

For teams whose revenue depends on the automations.

$400 / month
  • Everything in Managed
  • Up to 8 hours of work a month
  • Server support and team training
What's included
Included
  • Two calls a month
  • First in the queue
  • Server support included: updates, backups, alerts
  • Documentation for what is built
  • Training your team on calls
Not included
  • Large projects: that is a custom build

Over 8 hours: $35 an hour, after we agree. I take no more than two teams at a time.

Discuss for a team

Your own server

$100
one-time

When a project outgrows free plans or has to live on your own server.

  • A VPS on your own account with the provider
  • Setup: HTTPS, firewall, automatic updates, backups, monitoring
  • Moving one project over: n8n, a bot or a web app
Server support

Updates, backups, downtime alerts and a fix when it breaks. Up to 1 hour of work a month. Already included in Business.

$50
/ month

You pay the provider for the server itself, directly.

Set up a server

Custom build

Fixed quote

A tool built for your task: a bot, an integration, a web app, an AI assistant.

  • Estimated after an audit call or a brief
  • A fixed price with rounds of changes named upfront
  • 50% before the start, 50% on delivery
Discuss a project

Prices in US dollars. Pay by card in hryvnia (the payment service fee is included in the amount) or by bank transfer.

Work beyond the package hours is $35 an hour, only after we agree. Subscriptions are monthly: cancel any time before the next month starts. Three months paid upfront: 10% off.

Terms of service (public offer)

LIVE PRODUCTS

Try the apps I built

Three you can open and use right now. Six more come with a written breakdown, and some live only as Android or desktop apps.

One CV, twenty-one layouts. This is the house style.

The same data in a dark layout. Pick what the vacancy expects.

The page a recruiter opens. Email and phone are blurred on the screenshot.

Experience, kept current as the CV is edited, so the link never goes stale.

Skills as the recruiter sees them, not as a PDF attachment.

Koss Flow CV

FREE

cv.kossflow.com

AI resume builder for candidates. Reads your PDF, rewrites the resume for a specific posting and gives you a public link.

  • PDF/DOCX import fills the profile
  • Match score 0-100 against the posting
  • Public CV at cv.kossflow.com/u/<slug>
Try free →

Accounts in three currencies, one running total.

A month of spending, grouped by day and category.

Sole-trader tax quarter and savings goals on one screen.

Category limits with what is left, not just what is spent.

Chat that answers over your own numbers, not a generic model.

Kosht

FREE / $2+

kosht.kossflow.com

Personal finance that survives four currencies and a sole-trader tax year. Web and Android, one account.

  • Monobank sync, AI categorization
  • Household sharing, multiple currencies, Drive backup
  • Sole-trader tax calculator, four regimes
Try free →

Library and tools: merge, split, scan, edit.

Reading mode: nothing but the page, by day and by night.

Hand signature placed, dragged and resized on the page.

Seventeen tools grouped by job: scan, images, edit the document.

Papir

FREE

papir.kossflow.com

A PDF app that changes documents, not just displays them. Desktop for Windows and its own Android version.

  • Merge, split, reorder and export pages
  • Forms, hand signature, OCR for scans
  • Runs locally, no account, nothing leaves the machine
Download →
Six more projects, shown rather than opened
Chat, Meet, Courses, SMM, Ops, Fit: screenshots, the problem and how it is used. No public sign-up, so no button that pretends otherwise.
Open the showcase

One Koss Flow account across the web apps, single sign-on via auth.kossflow.com

TECH STACK

The stack, grouped by what it does

Not a wall of logos. What each part is for, and what I use for it.

Agents
Tool calling · custom MCP servers · multi-agent orchestration · memory and context · human-in-the-loop gates · retry, circuit breakers and fallback
Models
Claude · GPT · Gemini · Groq · per-tenant provider routing with automatic fallback · evals, LLM-as-judge and regression harness
Knowledge
RAG and agentic RAG · Qdrant · pgvector · embeddings and semantic search · Docling and OCR for scans
Voice
LiveKit · Whisper and Deepgram with a fallback chain · ElevenLabs · Vapi · zero-shot voice cloning · speaker-attributed transcription
Product
Next.js · React · TypeScript strict · Kotlin and Jetpack Compose · Tauri · FastAPI · Supabase · PostgreSQL with RLS
Runs it
Docker Compose · Caddy · self-hosted VPS · n8n in queue mode · uptime monitoring and error tracking · nightly backups · EU AI Act and GDPR obligations
ABOUT
Ihor Kostyniuk Ihor Kostyniuk
Ihor Kostyniuk
Senior AI Automation Engineer · LLM agents, MCP, RAG, Voice AI

I own the whole system, from the screen to the server

Started in marine engineering, where a system either works or someone gets hurt. That obsession stuck. In AI automation the bar is the same: staying up is the baseline, not a brag.

Two and a half years shipping production LLM systems on self-hosted infrastructure. I write the orchestration layer myself instead of adopting a framework: tool-calling loops, custom MCP servers, multi-provider routing with automatic fallback, checkpointed pipelines that resume after a crash, human-in-the-loop gates. End to end means the web app, the native Android app and the server under them.

English C1 Ukrainian C2 Russian Native Remote-first Odesa, Ukraine
Certifications
OpenClaw: Autonomous AI Agents
Udemy · Mar 2026
AI Voice Agents: Vapi + ElevenLabs + n8n
Udemy · Dec 2025
LLM Apps & AI-Agents with n8n & APIs
Udemy · Sep 2025
Automation #withMake
Web3nity · Jan 2025
LinkedIn
koss-flow
Telegram
@koss_flow
GET IN TOUCH

Tell me what's slowing you down

Describe the problem, even a rough idea. I'll tell you if it's automatable and roughly what it takes. No pitch, no commitment. I reply within one business day.

Your name and contact are used only to reply. Details in the privacy policy.

Email
koss.flow@gmail.com
Telegram
@koss_flow