Applied GenAI · Agents · Graph RAG
Make sense
of AI.
Notes on applied generative AI, agentic systems and graph RAG — written by Marton Szel for builders, leaders and the AI-curious.
Monthly briefing · second Friday · no spam
Mind the Orchestrator: Agentic Apps That Let Your Business Shine Instead of Eating Your Resources
Most GenAI pilots fail before they matter. Beat the odds: pick the right tasks to automate, demand the right framework and platform, and ship apps that get better with every conversation.
Know When to Ask for Help: Decision Models Meet the Durian
On 15 September, a start-up released an AI model that can't write a single sentence. Five weeks later, it has USD 870 million in fresh funding, an OpenAI copy and more than 30 rivals - so we put it to the big durian test.
Forward-looking Laziness: What Changes When AI Writes 95% of the Code
AI-enhanced project delivery is great: it gives you a ~1.5× speedup almost for free. But making your team AI-native — and reaching a 3-5× organization-wide speedup — requires real mastery of orchestration on top of a well-designed AI strategy.
2026: AI Won't Take Your Job (It'll Take Your Busywork)
AI writes code, makes presentations, and analyzes data — scary for white-collar workers like me. So let's set the existential crisis aside: an optimistic mid-to-short-term AI roadmap where we don't just keep our jobs, but find ourselves doing more fulfilling work.
Engineering Intelligence from Autocomplete
LLMs don't think; they predict the next token. A walkthrough of the engineering tricks — from prompting and RAG to tool use and Tree of Thoughts — that force a simple autocomplete to behave intelligently.
Breaking Bot: Hacking & Defending LLM-based Applications
Let's say your "super-intelligent" agentic chatbot — the one with access to sensitive customer data — is hijacked. You've effectively welcomed a genius-level saboteur behind your own defense lines.