Multi-Agent Blog Writer
4 AI agents collaborate on blog post creation — planner, researcher, writer, reviewer with feedback loop.
4 agents · 12 steps · feedback loop
Most companies know they want AI, but not where it will really help. I’ll find that spot with you and build the first working solution. No slides — a prototype on the table.
Automating repetitive tasks: reports, email triage, document processing.
Get in touch 02An assistant that knows your policies, contracts and manuals and answers in seconds.
Get in touch 03I'll find out what ChatGPT or Perplexity say about you and suggest how to improve it (GEO).
Get in touch4 AI agents collaborate on blog post creation — planner, researcher, writer, reviewer with feedback loop.
4 agents · 12 steps · feedback loop
Systematic testing of prompt techniques — few-shot, chain-of-thought, role prompting. Measuring output quality across models.
340+ prompts · there's no bad output, only a bad prompt
RAG assistant over personal documents, emails and calendar. Answers queries in context.
4 months · ~25 queries/day · saves 2h of work every day
GitHub Action that automatically reviews pull requests using Claude — checks code quality, security and consistency.
Experiments with Generative Engine Optimization — how to optimize content for visibility in AI models.
5 AI platforms · measuring citations and visibility
Platform for processing Bosch motor data — route sharing, ride analysis and performance stats for eMTB riders.
800 routes · 1,250 rides · 50 testers
Dashboard that calculates savings from smart control of EV charging power.
Automated LinkedIn post creation — from topic selection through generation to publication. Full pipeline.
90 posts · hundreds of hours saved
Automatic daily briefing — scans 50+ sources, filters relevant AI news and compiles a personalized summary.
6 months · 50+ sources · 180 briefings
Digital portal for managing municipal fees — waste, dogs, bio-waste. Citizens pay online, officials manage via admin panel.
Platform for event registration and management with AI assistant for organizers — from attendee registration to automated communications.
planning, tracking and evaluating events · 15 events in testing
Comprehensive solution for the digital agenda of small municipalities — forms, payments, citizen communication.
Automated sales network monitoring — data collection, performance analysis and reporting.
Real-time visualization of Prague integrated transport — public transit vehicle positions on a live map.
2,500–3,500 vehicles live · metro, trams, buses, trains, ferries
Financial market monitoring — earnings, analyses and signals from relevant sources for better investment decisions.
1 month · financial markets · earnings · analyses
From basics to advanced concepts — LLM, RAG, prompt engineering, agents, GEO and more. Clearly explained.
From zero to first results — for beginners and marketers. What AI can do, which tool for what, and how to write good prompts.
Techniques that work — zero-shot, few-shot, Chain-of-Thought, role prompting and system prompts. With examples and templates from practice.
See how AI agents work step by step. Pick a scenario and run it.
Analyzes a website for AI search engines.
Generates a short LinkedIn post.
Recommends a trail based on conditions.
4 agents collaborate on a blog post.
4 agents vet sources and write a report.
Answers from company documents and shows the source.
Experimental games built with AI assistance — from idea to code. Each one is a creative experiment in AI code generation.
Cyberpunk arcade shooter on a highway — dodge cars, collect power-ups and destroy enemies. Neon graphics, combo system and upgrade tree.
Canvas 2D · touch controls · endless mode
Above all with the hardest part: figuring out where AI will really save you time or make you money. I look at how things work at your company, work out what to use AI for and how, design the solution and quickly build a prototype you can actually try. Whether it's a website, an app, an AI agent or a whole multi-agent system. You know within days whether it works, not in six months.
You write me two or three sentences about what you are dealing with, and I get back to you within 24 hours. Together we find the place where AI really helps you, and I build the first working solution. No slides, but a prototype on the table.
GEO (Generative Engine Optimization) means making sure AI assistants such as ChatGPT, Perplexity or Google AI Overviews know and cite you. I find out what they say about you today and suggest how to improve it.
The assistant searches your policies, contracts or manuals and answers with a reference to the exact place in the document. If the answer is not in the documents, it says so instead of making something up. You can try it in the Document Q&A demo in the Agent Lab.