AI that ships to
production, not to slides
We build agents, RAG and automations that earn money and run in production — not ones that look pretty on slides. We join your team or take the whole project — from architecture to delivery.
What we
actually ship
Agentic AI
Autonomous agents in a loop doing real work — analysis, decisions, automation — in production, not in a demo.
RAG / knowledge
Retrieval over your documents and data; grounded answers, auditable, backed by evidence quotes.
Automation
LLM-powered document and process automation — with explainability: you know why the model made each call.
Robotics / embodied AI
Training and programming robots with agentic loops — embodied AI that does hard work, not a show.
What we
build on
Two ways
we come in
Team augmentation
We join your team for a concrete project — when hiring can't keep up; we plug into your stack and process and work as your people.
End-to-end project delivery
We take the project from architecture to production and deliver the whole thing — you get the outcome, not a hiring problem.
An experienced task force,
not lone hands
Behind every delivery stands a tight task force of experienced freelance specialists who have shipped together for years — ML, backend, frontend, robotics, RAG, DevOps. Szymon runs it hands-on and matches the right seniors to each problem.
- Battle-tested seniors — people vetted over years of real projects, not random contractors off a marketplace.
- Matched to the problem — every task gets the right competencies, not the first free hands from a body shop.
- Scaled to the stage — the team grows and shrinks with the project phase, so you do not overpay for slack.
- We own the whole thing — we are accountable for end-to-end delivery, with no finger-pointing between vendors.
Former CTO of uPacjenta; co-founder of Riot Agency, later acquired by Diagnostyka and renamed Diagnostyka Digital Hub; former Head of Strategy & Product at Golem Network.
Two models,
one decision
Time & Materials (billed per day)
You pay for work actually done — no more, no less; flexible scope. Best when the scope is still moving.
Fixed price
Agreed scope, agreed price; budget certainty. Best when the scope is well defined.
Minimum engagement is a quarter of full time, roughly 5 days a month. I do not take single-hour jobs: on delivery work half of that time goes into loading the context, so you would be paying for the run-up.
See what
we've shipped
Brand-message compliance control
The brand needs to know whether the messages appearing online are consistent with its PR strategy — scoring hundreds of publications by hand is slow and inconsistent.
An agent pulls publication links from media monitoring, extracts article content and metadata, then scores it against the brand's PR and brand theses (a brand playbook auto-built from the brand's documents as a RAG).
Auditable verdicts: aligned / neutral / divergent — each backed by an evidence quote (proof of concept).
Digital investigation studio
Investigators need to surface evidence and connections from phone data — including hours of audio recordings to review.
A React/TS desktop app plus an audio transcription pipeline: cloud models via Replicate, speaker diarization, VAD chunking, and LLM correction of grammar and speaker labels.
A working application: surfaces evidence and connections from phone data along with analysis-ready transcripts.
Tender spreadsheet normalization
Every supplier sends a tender Excel file with a different header format — normalizing them by hand is slow.
The system detects tables in Excel, infers canonical tender headers with GPT, maps them structurally, and generates normalized, styled spreadsheets plus Markdown explainability logs (source→target mapping, confidence %, and the model's reasoning when confidence is low).
Runs in production: normalized spreadsheets plus explainability logs for every decision.
Physical-AI command-and-control prototype
Explore how camera analytics, an AI decision engine and robot dispatch can work together under human oversight.
Co-architected a perception → decision → dispatch chain using ROS 2 and MQTT, with human oversight.
Demo-grade prototype validated in a cloud-hosted warehouse simulation.
Football spatial intelligence
Tracking-grade spatial analysis (pitch control, pressing, off-ball-run value, line-breaking) is out of reach for CEE and lower-tier clubs and agencies — they only have cheap on-ball event data.
Reconstructs the off-ball spatial layer from cheap event data: a physics-based spatial model (positions → pitch control etc., no training data needed) plus a light learned imputation step, calibrated and validated against paired event + tracking data.
The make-or-break technical gate passed: a player-level Spearman > 0.7 target, achieving 0.83 (LOMO) on sealed paired matches under a pre-registered, adversarially-audited protocol.
From brief
to production
Brief
We understand the problem and the business context — what should happen and how we'll know it worked. You get a clear scope and goal.
Architecture
We design the solution: choice of models, data and integrations. You get the architecture and a plan before we start building.
Build / PoC
We build a working PoC or feature and iterate on real data. You get something that works and that you can actually touch.
Production & handoff
We ship to production and hand the project over with docs plus maintenance. You get a living system, not a demo.
A good fit if...
- You have a real problem and data to work with
- You want AI in production, not a demo on slides
- You value auditability, explainability and team seniority
- You need one person accountable for the whole thing
- Your scope is clear or evolving — either billing model works
Not for you if...
- You're after the cheapest body-leasing billed by the hour
- You want buzzwords on slides with no real implementation
- You have no data or access to build anything on
- You expect magic without your own team's involvement
- You're looking for a large, anonymous software house
AI implementation — common questions
How long does an AI implementation take? +
It depends on scope — a first working pilot is measured in weeks, not months. The concrete timeline and budget are set after scoping, before you sign anything.
How is the work billed? +
Two models: Time & Materials (you pay per day of actual work, from 600 USD, flexible scope) or a fixed price for a scope agreed up front. Minimum engagement is a quarter of full time. You pick one — no hidden costs.
Is our company data safe during an AI rollout? +
Yes. Where data is sensitive I build Private AI architectures with local models — your data never leaves your infrastructure. Everything compliant with GDPR and the EU AI Act.
What stack do you build with? +
Claude and GPT, LangGraph/LangChain, pgvector, Redis, FastAPI among others — the stack is chosen for the problem, not the other way around. The code and docs stay with you.
What happens after the rollout? +
You get the system with documentation and team handover, optionally continued development in a team-augmentation model. Strategy and oversight come from AI consulting, team skills from the enterprise AI workshop.
Tell me what to build,
I'll come back with a plan
You're writing to me, not to a sales desk. I come back with questions, or straight away with a proposed scope, engagement model and budget.
Got a hard problem?
Let's talk.
A short call, a straight answer: whether it's doable, how, and in which model. One contact, one accountability.