Senior AI Solutions Engineer
Building AI-powered products, platforms, and tools
Projects
Records Analyzed
Companies
Senior AI Solutions Engineer at RITS and university lecturer at WSEI Krakow. I architect RAG systems, AI agents, and LLM-powered platforms — then build them end-to-end. I bridge the gap between business requirements and technical implementation, with zero tolerance for imperfections.
Kraków, Poland
50.0614 · 19.9366
-1.png)
University science club at WSEI Krakow focused on exploring applied artificial intelligence. Conducting workshops, research sessions, and hands-on AI projects with students.
AI hackathon organized by AI Possibilities Lab at WSEI Krakow. A competitive event bringing together developers, designers, and AI enthusiasts to build innovative solutions for urban challenges.
Polish political transparency platform. Aggregates data from 6 government sources: Sejm API, KRS, CEIDG, asset declarations, PKW, lobbyist registry. 498 MPs, 1.7M voting records, 16,331 interpellations. AI-powered analysis with network graphs, anomaly detection, and Gemini-grounded explanations. All data is publicly available by law — Pryzmat makes it accessible and understandable for every citizen.
The first AI system that independently analyzes the web daily and publishes its own brutally honest commentary about people, technology, and the world. Not an assistant — an independent AI commentator with its own agenda. The AI has a cynical, authoritative voice: precise academic vocabulary, no fake enthusiasm, and zero alignment safety nets. Episodes available at studio.aifrontline.info for early feedback.
High-performance local voice transcription app for macOS and Windows. Powered by Groq Whisper with 99.4% accuracy. Features: real-time transcription, instant copy & auto-paste, AI summaries & action items, built-in AI agent, semantic vector search, speaker recognition, smart categories, system audio capture, and MCP protocol integration. Everything stays on your machine — 100% private.
Multi-tenant admin management platform at admin.madejski.it. A secured, Cloudflare Zero Trust–protected back-office for managing content, users, and operations across projects. BasePlate acts as the operational foundation — the base layer that everything else runs on top of.
Community-driven navigation platform for clean transport zones (Strefa Czystego Transportu). Live one-tap reporting of enforcement cameras and police checkpoints. Consensus-based mapping with upvote/downvote system ensures accuracy and auto-prunes stale reports. Smart navigator calculates the safest path avoiding enforcement zones. Camera cones of vision show monitoring direction. For informational purposes only.
AI-powered personal training companion at dontstop.wtf. Generates personalized workout plans, tracks progress, and keeps you accountable. The name says it all — an always-on gym bro who won't let you skip leg day. Built for people who train seriously but don't have access to a personal trainer.
.png)
Next-generation education platform competing in EduMasters Merito. Features Omnisync (real-time slide synchronization across all student devices), Streambot (proactive AI teaching assistant that analyzes content and suggests improvements), and Hybrid-Scoring (AI-powered formative assessment that evaluates intent, not just answers). Validated with 80 students across 4 groups at WSEI. Enterprise-ready with SSO/Azure AD support.
Interactive C4 architecture diagram builder. The C4 model (Context, Containers, Components, Code) is the industry standard for communicating software architecture. C4 Mapper makes it easy to create, edit, and share these diagrams in the browser — no diagramming tool licenses or local installs required. Built for software architects and engineering teams.
Data analysis tool for the FDA Adverse Event Reporting System (FAERS). Explores pharmacovigilance data — adverse drug reactions, medication errors, and product quality complaints reported to the FDA. Turns raw government datasets into searchable, visual intelligence for researchers and healthcare analysts. Uses public FDA open data APIs.
Educational interactive graph visualization tool built during university studies at WSEI. Explores graph theory concepts — traversal algorithms, shortest paths, network analysis — through dynamic, interactive visualizations with real-time graph manipulation.
Profesjonalna strona wizytówkowa dla Pracowni Fryzjerskiej Tomasza Karcza w Krakowie. Minimalistyczny design podkreślający hasło: Precyzja. Uważność. Efekt. Pełna prezentacja usług, galeria prac i możliwość rezerwacji wizyty. Zbudowana z myślą o estetyce i konwersji.
Senior AI Solutions Engineer
Mar 2026 — Present
ArchitectingRAGsystems,AIagents,andLLM-poweredplatformsacrossenterpriseengagementsata600+persontechnologyconsultancy.
Apr 19, 2026
A personal set of rules and artifacts that turns Claude Code from a "fast kid who breaks things" into a partner you can run multi-month projects with. Seven non-negotiable rules, three decision paths, session continuity — open-source on GitHub.
Apr 1, 2026
A practical look at how large language models fit into my daily workflow — not as magic tools, but as accelerators for architecture, debugging, and code review.
AI Resources
A small, opinionated toolkit. Browse the library, grab a single file, drop it into your own harness.
01 · Prompts
A prompt is a specific instruction you hand an LLM to produce a specific kind of output. Good prompts are opinionated and constrained: they give the model a role, a format, and an escape hatch when uncertain. Think of each one as a short contract — you know what you asked for, the model knows what it owes you.
Ritual for starting a new Claude Code session. 5 minutes of reading before touching anything — in a set order. Solves the "cold start bias": the agent jumps to code before understanding state. List of sources of truth, reading order, infra checklist.
Three paths for making decisions: (1) one sensible option → proposal + "see any gaps?", (2) 2-3 real options → classic 3-line format + TL;DR, (3) > 3 options → narrow first. Eliminates fake A/B/C and option multiplication beyond need, while preserving discipline for real decisions.
The core working-mode manifest for Claude Code on long-form projects. Normalized version of the personal harness from the GroqeSTT project — auto-loaded via CLAUDE.md on every session. Contains agent-flaw diagnostics, seven non-negotiable rules, pre/during/post-task checklists, red flags, user steers, and the agent's decision-making space protocol (three paths).
Battle-tested prompt for secure OpenClaw installation on an isolated Linux server. Includes threat model based on audits from Microsoft, Kaspersky, Cisco Talos and CrowdStrike, config hardening, sandboxing, and a complete step-by-step plan. Mind the freshness — current as of creation (Q1 2026), CVE versions may change.
Build → Critique → Refine loop for when "good enough" isn't good enough. Instead of hoping the first output is perfect, plan for 2-3 iterations from the start. Each round has a specific focus: first pass for structure and correctness, second for quality and edge cases, third for polish and performance. Works for code, writing, architecture, and design.
Write the spec before you write the code. This prompt enforces a spec → plan → build → verify loop that prevents scope creep, architectural drift, and "it works but not how we wanted" outcomes. The spec is the contract between what you want and what gets built. Every implementation decision traces back to a spec requirement.
Strategy for managing long AI sessions without losing context or quality. Covers when to compact, how to structure checkpoints, what to keep in context vs. offload to files, and how to hand off between sessions. Prevents the "it forgot what we were doing" problem and the "last 20% of context produces worse output" degradation.
Systematic method for understanding an unfamiliar codebase fast. Instead of reading code top-to-bottom, follow the data flow: entry points → routing → business logic → data layer → external integrations. Produces an architecture map, key abstractions list, and "where to look" guide in under 30 minutes. Works for any stack.
02 · Skills
Claude Code is Anthropic's terminal-first AI developer agent. It reads your repo, runs commands, edits files, and keeps a single conversation across days of work. A skill is how you teach it to behave consistently.
Kreator i optymalizator CV maksymalizujący szanse na rozmowę rekrutacyjną. Przerabia istniejące CV pod konkretną rolę lub buduje od zera. Zawiera: Extraction Interview (wydobywanie ukrytego złota z kandydatów), Nothing-Left-Behind Principle, Page Density Algorithm, DOCX formatting specs (Classic + Modern), role-specific keyword patterns (Python/ML/QA/DevOps/Frontend), Strategic Truth-Stretching Framework, pełną bazę wiedzy ATS/Polish market. Obsługuje wszystkie branże i poziomy (junior/mid/senior), ze szczególną optymalizacją dla polskiego rynku IT.
Skill enforcing Read before every Edit/Write in the same session. Eliminates "blind edits" based on memory — every file the agent modifies must have been read in the current session. Protects against overwriting others' work.
Skill enforcing plan-first: a plan presented to the user before any code change. You wait for GO, then write. Exception: batch approval ("do X and commit"). Eliminates "I already started" and unauthorized commits. Two formats: single-path proposal (default for most steps) and plan-with-variants (when there are real options).
Skill for generating the next-session-phase{N+1}-brief.md file before ending a session. Eliminates the gap between sessions — the next session has ready context, first task, and infra quick-check. Zero momentum loss from "where did we leave off".
Meta-analytical meeting breakdown — not a summary, but an efficiency analysis. Produces signal/noise ratio, decision rate, topic weight distribution, voice distribution, red flags, and a brutal one-sentence Shelby-Musk verdict. Use for meetings over 10 minutes when you need to understand where the time actually went.
Framework for running retrospectives that actually change something. Produces a facilitation plan with warm-up, data gathering, insight generation, and action items. Includes 10+ retro formats to prevent format fatigue. The output is not a feel-good session — it's a systematic process for turning team friction into concrete improvements with owners and deadlines.
Framework for running effective 1:1 meetings as a manager, mentor, or peer. Produces an agenda with the right questions for the context, a note-taking template, and follow-up actions. Covers career development, performance feedback, blockers, relationship building, and difficult conversations. The output is not corporate theater — it's a tool for building trust and getting real signal.
Audience-calibrated messaging for different stakeholders. Transforms the same information into messages tailored for executives (business impact), engineers (technical detail), clients (value delivered), or team (actionable next steps). Produces ready-to-send drafts with tone, length, and emphasis matched to the recipient's priorities and communication style.
“Photography is the art of seeing beauty and training the eye — to freeze a story in the split second the shutter clicks, and let others see the world through mine.”View Gallery →
Open for consulting, collaborations, and interesting AI challenges.
