Oliwier Data · Portfolio

How would you like to view this site?

Your device can run the interactive 3D version. The content is the same either way — pick whichever suits you.

You can switch at any time with the 3D switch at the top of the page.

Oliwier Data

From idea to real product

I build production web applications, AI agents grounded in company data, and the infrastructure they run on.

Oliwier Data, Full-Stack Developer & AI Engineer

Rzeszów, Poland · Remote · Open to full-stack & AI engineering freelance projects

Artur Express

Platform and conversion funnel for a logistics carrier

One person takes a product from idea to a live deployment: the application, the AI agents and automation around it, and the infrastructure underneath.

n8n automation workflows running in production
20+
AI agents & RAG systems shipped — OpenAI, Claude, Gemini
10+
repositories: commercial, product and own projects, most under NDA
30+
users supported on the production infrastructure I maintain
100+

Three engineering pillars

InfrastructureAgents & automationApplication
  1. Full-Stack Web Engineering

    Fast, modern web applications, internal systems and conversion platforms — built end to end, from the database to a polished frontend.

    Where it runs

    • 30+ production and commercial repositories
    • Clients in logistics, hospitality and healthcare-adjacent sectors

    Tools

    • Next.js 16
    • React
    • TypeScript
    • Prisma ORM
    • PostgreSQL
    • SQL
    • Tailwind CSS
    • Three.js / WebGL
    • Playwright
    • REST APIs
    • Node.js
  2. AI Engineering

    RAG Systems, Voice Agents & Process Automation

    AI agents grounded in a company's own data (RAG), reached by chat or by voice, and multi-step automation pipelines that replace manual work across a team.

    20+ workflows in production

    • Lead intake, qualification and routing
    • AP invoice processing with OCR and Sheets
    • Zendesk ticket triage and categorisation
    • Data sync, automated reporting and error handlers with alerting

    Tools

    • OpenAI API
    • Claude API
    • Gemini API
    • RAG architecturechatbots and assistants grounded in client documentation, with conversation memory and tool calling
    • Vapi & ElevenLabsvoice agents: a spoken question goes through the same retrieval, memory and tool calling
    • n8nLangChain-powered agent nodes and custom workflows
    • Python
    • REST API integrations
    • OCR
    • Google Sheets API
    • Zendesk
  3. DevOps, Infrastructure & Self-Hosting

    Containerisation, virtualisation and automated deployments that keep the applications and AI agents I build stable and secure in production.

    In production

    • Infrastructure for 100+ users, maintained day to day
    • Every app and agent above ships as a container through a pipeline
    • Self-hosted services published through Cloudflare Tunnel, with no inbound ports open
    • Encrypted backups, with restores rehearsed

    Tools

    • Docker & Docker Composemulti-container architecture in production
    • CI/CD pipelinesautomated builds, end-to-end test gates and deployments
    • Cloudflare Tunnel & Nginxservices published through a tunnel and a reverse proxy, with no inbound ports open
    • Proxmox VEserver virtualisation, virtual machines and clusters
    • Linux & Windows Serveradministration, service upkeep, TCP/IP, DHCP, DNS, diagnostics
  1. Artur Express

    Full-Stack Web Engineering. Platform and conversion funnel for a logistics carrier.

    Results

    Lighthouse, measured on the live site
    • 98 of 100: Performance
    • 100 of 100: Accessibility
    • 100 of 100: Best practices
    • 100 of 100: SEO
    • 0.8 s LCP
    • 0.004 CLS
    • 62 pages
    • 42 content types
    • 19 Playwright end-to-end tests, run before every deploy

    Challenge

    A US trucking carrier needed its website rebuilt as a lead engine: every visitor path should end in a captured, routable enquiry — and the pages had to load fast.

    What I built

    End-to-end UX/UI design and build in Next.js, TypeScript and Tailwind CSS: a multi-path conversion funnel with lead capture, pay calculators, a news system and a JWT-secured admin CMS on PostgreSQL + Prisma — shipped as Docker images through a CI/CD pipeline that runs the Playwright suite before every deploy, and published through a Cloudflare Tunnel with no inbound ports open.

    Built with

    • Next.js 16
    • React 19
    • TypeScript
    • Tailwind CSS
    • PostgreSQL
    • Prisma
    • Playwright
    • Docker
    • CI/CD
    • Cloudflare Tunnel
  2. Enterprise RAG & AI Agents

    AI Engineering. Assistants that answer from a company's own documentation.

    10+ production deployments

    Google DriveChatEmbeddingsPostgres memorypgvector storeRAG agentVoice callAnswerGoogle DriveChatVoice callEmbeddingspgvector storeRAG agentPostgres memoryAnswer

    Results

    • Answers grounded in the client's own documents, not model guesswork
    • Conversation memory and tool calling in every agent
    • One agent behind chat and voice: Vapi carries the call, ElevenLabs the speech
    • Self-hostable end to end: n8n, pgvector and Postgres in Docker

    Challenge

    Teams lose hours answering questions that are already written down — in documentation nobody has time to search, and that a generic chatbot knows nothing about.

    What I built

    AI assistants and chatbots powered by clients' internal documentation, built on the OpenAI, Claude and Gemini APIs with n8n's LangChain agent nodes: conversation memory, retrieval over RAG knowledge bases and integration with external tools. The same agent also takes a voice channel, built on Vapi and ElevenLabs: a spoken question runs through the same retrieval, memory and tools, and the answer is spoken back.

    Built with

    • OpenAI API
    • Claude API
    • Gemini API
    • n8n
    • LangChain agent nodes
    • Vapi
    • ElevenLabs
    • pgvector
    • PostgreSQL
    • Docker
  3. Production Automation Pipelines

    AI Engineering & Automation. Business processes that run themselves, with a human where it matters.

    20+ workflows in production

    Follow one throughPick what arrives and watch a workflow I run in production handle it.

    A supplier emails a scanned PDF invoice to accounts payable.

    1. Gmail intakeThe message is picked up and the attachment pulled out.
    2. OCRA scanned PDF is read into text; a digital one skips this step.
    3. LLM extractionSupplier, amounts, dates and line items become structured fields.
    4. Duplicate & PO checkThe invoice is compared with earlier ones and matched to its purchase order and vendor.
    5. Approval in SlackA person sees the extracted fields in an editable form and approves or corrects them.
    6. Sheets registerThe approved invoice is written to the register.
    7. OutcomeFiled and approved by a person; any failure alerts the ops channel instead of passing silently.

    A visitor submits the enquiry form on a client's website.

    1. Signed webhookThe site sends the lead with an HMAC-SHA256 signature.
    2. Signature checkA request that does not verify is rejected before anything else runs.
    3. File and de-duplicateThe lead is stored and matched by email, so the same person is never filed twice.
    4. Score 0–100The lead is scored on what it says and how complete it is.
    5. RouteHot goes to Slack and email, warm to Slack, cold is filed.
    6. OutcomeEvery lead is stored and the right person hears about the good ones at once.

    A customer opens a new ticket in Zendesk.

    1. New ticketZendesk hands the ticket to the workflow as it is created.
    2. ClassifyAn AI agent sorts it by topic and urgency.
    3. Draft a replyThe agent writes an answer grounded in the help-centre articles.
    4. Human approvalA person approves or edits the draft in Slack before anything is sent.
    5. Send or escalateThe reply goes to the customer, or the ticket is passed on for manual review.
    6. OutcomeCustomers get a grounded answer faster, and nothing reaches them without a person seeing it.

    Results

    • Leads Signature-verified, de-duplicated, scored 0–100 and routed
    • Invoices OCR, AI extraction, approval in Slack, register in Sheets
    • Tickets AI drafts the reply, a human approves before it is sent
    • Every failure lands in an ops channel — nothing fails silently

    Challenge

    Invoices, support tickets and sales leads were handled by hand: copied between systems, answered late and dropped without anyone noticing.

    What I built

    Automated business processes in n8n, Python and REST APIs: OCR-based AP invoice processing, Zendesk ticket triage, sales-lead routing, data sync between systems and central error monitoring with alerts.

    Built with

    • n8n
    • Python
    • REST APIs
    • OCR
    • Google Sheets API
    • Zendesk
    • Slack
  4. Containerized Infrastructure & Commercial Web Apps

    Full-Stack & DevOps. The platform everything above is deployed on.

    30+ repositories

    Git pushCI + E2E testsDocker buildCloudflare TunnelCompose stackNginxBackups + restoreGit pushCI + E2E testsDocker buildCompose stackNginxCloudflare TunnelBackups + restore

    Results

    • Multi-stage Docker images and Compose stacks
    • Jenkins and GitHub Actions pipelines, with end-to-end tests gating the deploy
    • Cloudflare Tunnel in front: no inbound ports open on the host
    • Encrypted, automated backups with integrity checks and rehearsed restores
    • Infrastructure serving 100+ users

    Challenge

    An application or an AI agent is only worth something while it is up: deployed the same way every time, backed up, and recoverable when a server fails.

    What I built

    Web applications (Next.js 16, Prisma, PostgreSQL) and internal automation systems deployed as Docker Compose stacks on Linux and Proxmox, shipped through CI/CD pipelines that run end-to-end tests before a deploy — with a reverse proxy and SSL in front, a Cloudflare Tunnel so that no inbound port is open, and encrypted, automated backups behind.

    Built with

    • Docker Compose
    • Proxmox VE
    • Linux
    • CI/CD
    • Nginx
    • Cloudflare Tunnel
    • Next.js 16
    • PostgreSQL

Most of the 30+ repositories are under NDA: commercial work for logistics, hospitality and healthcare-adjacent clients. Ask, and I will walk you through what I can show.

Get in touch

Where I work

  1. Sep 2025 — presentRemote

    Full-Stack Developer & AI Engineer

    Freelance & commercial projects

    End-to-end delivery of Next.js 16 applications (Prisma + PostgreSQL, Tailwind, Docker), 10+ AI and RAG agents on OpenAI, Claude and Gemini, and 20+ production automation workflows in n8n.

  2. Mar 2026 — presentRzeszów

    IT & Infrastructure Specialist (L1/L2) · Internal Automation

    AmeriPol

    Maintaining Docker Compose infrastructure on Linux, Proxmox virtualisation and CI/CD pipelines; building internal automations in n8n, Python and REST APIs that cut manual work; technical and network support for 100+ users.

Have something to ship?

Send a short brief — what you need built, the stack you are on and the timeline — and I will come back with how I would build it.

Or put it togetherPick the parts your project needs. They stand up on the floor as you choose them, and the brief writes itself.

Application

AI

Automation

Infrastructure

Your brief

Nothing picked yet. Choose a part above, or just write a line below.

How far