I help you go from a fuzzy idea to a system that holds up — with AI where it gives a real edge.
Before you spend a budget on a team, an agency, or a CTO — let's check whether the idea is worth building at all. Where the technical and product risks are, what can be simplified, where AI actually helps and where it's just decoration. You get an honest recommendation: build, simplify, or kill — and what to do first.
The direction is clear — now a design that holds in production and won't torch the budget. System shape, integrations, AI / non-AI decisions, cost, maintainability, and production readiness. AI goes where it adds value — with fallbacks, quality evaluation, and cost control.
We build once it's clear what and why. A working system in production — not a demo that looks good on stage. Where AI makes sense: multi-provider setup, bring-your-own-keys, caching, fallbacks, answer quality evaluation.
Decision support before you hire a team, an agency, or a CTO too early. Someone who understands the tech, the product, and the business — and tells you straight what makes sense and what doesn't. For founders and companies launching something new.
AI in a prototype is magic. AI in production is engineering. What counts is the system that does its job every day — not just on stage.
— Rule no. 1A made-to-measure running plan for runners who have outgrown one-size-fits-all templates. Popular apps aim at beginners; advanced tools give you metrics, not a plan. own-tempo builds a plan for your race from your own Garmin runs, puts the workouts on your watch and adjusts when life gets in the way.
Private photo and video compression entirely in the browser — files never leave your device. Built on WebAssembly and FFmpeg.
I help judge, design, and build reliable software systems. I start with whether an idea is worth building at all and how to simplify it — then I design the architecture and ship it to production. AI goes in where it actually adds value: language models (LLMs) with answer quality evaluation, hallucination risk reduction, and cost controls.
Six years of production engineering in banking (BNP Paribas, Credit Suisse). Working with AI in production since 2023, AI Champion at Synergy Codes since 2024. First exposure to machine learning during my studies (Wrocław University of Science and Technology, MSc Eng. in Computer Science, 2017–2022). AI Devs 4 certified.
I work with multiple model providers — OpenAI (GPT), Anthropic (Claude), Google (Gemini), and local models (Llama, Mistral). The choice depends on the project: answer quality, data privacy, cost and infrastructure constraints. I often design multi-provider setups to avoid lock-in.
A product or system diagnosis usually takes 1–3 weeks. Architecture and technical plan run 2–6 weeks. Build and rollout for a new product takes 8–24 weeks, depending on scope. Every project starts with a short conversation and diagnosis. The concrete timeline comes after that.
Yes. I work remotely with clients across Poland and selectively internationally. Calls, project workshops, and delivery take place online.
Per-project pricing after the first conversation and scope review. Audits have a fixed rate. Implementation and architecture — priced by scope and risk, not hours.
First a 30-minute conversation: context, problem, goal. Then diagnosis (typically 1–3 weeks), a concrete proposal with scope and price, and execution in iterations with visible progress.