Independent AI engineer · open to freelance · Kyiv

AI that earns its keep.

AI agents, smart search (RAG), and automation — live in production, not slideware. Try it.

Opens Echofy — my live SaaS, running in production.

01 — Flagship

The proof, live.

Live · production SaaS

Echofy

An AI employee for Instagram shops.

A production multi-tenant SaaS I designed and shipped solo. It reads a shop's Instagram DMs and answers product questions, qualifies buyers, and handles support 24/7 — in the customer's own language, across text, images and voice.

Projected It's built to take the ~80% of DMs that are the same repeat product questions off a shop owner's plate — they only step in for the rest.

It's live and running in production right now. Don't take my word for it — try it yourself.

Open the live demo
echofy / architecture
apiFastAPI + Celery task queue
dataPostgres, row-level multi-tenancy
ingestInstagram DM webhooks
brainMultimodal RAG over each shop's catalog
langAuto-detect: Ukrainian · Russian · English
verifyOwnership invariant, formally verified
deployDockerized · VPS behind Caddy

Proven property: a shop can never be left without an owner — checked by symbolic execution (CrossHair, Z3-backed) over all code paths, not sampled cases.

In plain terms: it reads photos and voice notes, replies in each customer's own language, and keeps every shop's data walled off from the rest.

02 — How I ship

I use AI to build AI.

Echofy is a full production SaaS I shipped solo. That's only possible because I turn the same agentic techniques I build for clients inward — onto my own engineering. It's how I ship solo, at the pace of a team. This is the working method behind the build.

01

My own agent process

Custom skills and subagents I built to run production development end to end — solo.

custom skills · subagents
02

Wired into real systems

MCP servers connect my agents straight to the tools, data and APIs a real build touches — not a sandbox.

MCP servers
03

Orchestration at the frontier

I work with Claude Code's newest layer — Dynamic Workflows: plan a job, fan it across parallel subagents, self-verify, merge.

Dynamic Workflows
04

Pushing the harness further

Between client builds I push my own agent harness — longer-lived sessions, durable cross-session memory, recursive LLM architectures. Experiments that feed straight back into how I ship.

context · memory · recursive LLMs
03 — What I offer

Practical AI, built properly.

Scope is agreed up front, with a first version live in 1–2 weeks. We start small and paid, and keep going only if it earns its place.

/ 01

AI Knowledge Assistant

Finds and delivers answers across a team's documents and systems. Covers data and process analysis, a custom RAG architecture, a web or messenger interface, and team onboarding.

See related work →
/ 02

AI Sales Chatbot

A 24/7 sales agent that answers product questions, qualifies leads, books meetings, logs to a CRM, and hands off to a human when needed.

Optional: Stripe payments · custom integrations

See related work →
/ 03

Custom AI Workflows

Automates repetitive work like document sorting, email and form processing, and reporting. Covers process analysis, building the workflow, integrations with existing tools, and documentation/handoff.

See related work →
04 — Lab

Built to prove it.

Builds I've taken end to end to push the stack and pressure-test ideas. Every one actually runs.

Automation Case study →
Workflow Autopilot

An autonomous Telegram bot that sorts ~10,000 telecom equipment photos a month with a two-stage AI pipeline — 1.5 hours of manual work down to a 2-minute review.

Python · Gemini · Telethon
Agents & Bots Case study →
Automated Sales

A conversational sales agent that answers course questions from a RAG knowledge base, qualifies leads in real time, and closes with in-chat Stripe checkout — the whole funnel in one chat.

FastAPI · Gemini · Stripe
Agents & Bots Case study →
Smart Ticketing

An autonomous LangGraph agent that classifies tickets, answers from a RAG knowledge base behind a 3-layer quality gate, and escalates honestly — built to resolve the repetitive ~78% automatically.

LangGraph · LlamaIndex · Gemini
RAG & Search Case study →
Instant Search

Hybrid semantic + keyword retrieval with cross-encoder reranking over 109 HR docs — cited answers in seconds, in any language. 0.82 Answer Relevancy on Ragas.

Qdrant · BM25 · FlashRank
Agents & Bots Case study →
Billing Rescue

Rescued a live subscription-billing Telegram bot for a content creator: root-caused a duplicated scheduler granting 60-day subscriptions instead of 30, fixed it under TDD, and killed an expiry job throwing ~880 errors a day.

FastAPI · aiogram · React
Automation Case study →
Listing Pipeline

Automated a property agency's listing workflow: catches private-seller ads, filters out agents, and posts formatted listings to a shared sheet and Telegram channel. Soak-tested: 48 hours, 96 cycles, zero errors.

Python · Sheets API · Telegram
Automation Case study →
Anomaly Detector

Three detection layers for month-end close: hard accounting rules, Benford and round-number heuristics, per-client learned models. QuickBooks Online integration, sandbox-tested. 434 tests passing.

Python · QuickBooks · Benford + ML
05 — Expertise

What I work with.

01

Agentic AI Development

Multi-agent systems that plan, delegate to subagents, call tools, and verify their own work.

02

Advanced RAG Systems

Hybrid retrieval and reranking that answers with the source attached.

03

Workflow Automation

Repetitive back-office work wired end to end.

04

Backend & API

The FastAPI services and data layer underneath it all.

05

LLM Eval & Tracing

Measuring answer quality and watching every call in production.

06

Prompt Engineering

Prompts tuned and tested against real cases, not guessed.

01

Orchestration

How agents plan, hold state, call tools, and connect to real systems.

LangGraph · LangChain · PydanticAI · MCP · DSPy
02

Retrieval

Finding the right facts in a sea of documents.

LlamaIndex · Qdrant · BM25 · FlashRank
03

Evaluation

Proving the answers are good — and watching them in production.

Langfuse · Ragas · DeepEval · Promptfoo
04

Serving

Running models and background jobs fast, at scale.

vLLM · Celery · Docker
05

Foundation

The dependable backend everything sits on.

Python · FastAPI · Postgres
06 — About

Who's behind it.

Roman Hurakov — independent AI engineer

I'm Roman — an AI engineer who ships real systems, not toys. Echofy is a full production SaaS I built alone, from webhooks to formal verification to deployment. Now I help businesses put the same kind of AI to work — fast, and done properly.

— Roman Hurakov
07 — Let's talk

Let's put AI to work.

Bring me a problem worth automating. I'll scope it, build it end to end, and ship something that holds up in production.