11 minDebugging & Solutions
46 Seconds Inside a 30-Second Webhook
A render call could take 46 seconds inside a webhook with a 30 second budget. The second finding turned out to be worse than the first one.
From the blog
Notes from my AI practice: agentic coding, multi-agent architecture, SME use cases.
- 4 minBehind the Scenes
Pflegegeld-Prüfer: Turkish and a deadline calculator, no AI
One week after HACK_002: a real bug in the court deadline is fixed. New are a deadline calculator without AI, advice centres with contacts, and Turkish.
- 6 minBehind the Scenes
Eleven Job Titles, One Job
A script found the same work under eleven job titles. It turned into BewerbungsGenie, open as a public beta for Austria since 1 October 2026.
- 10 minBehind the Scenes
FotoDrop: 20 Hours from First Commit to First Deploy
A family photo album made with coding agents: from a dictated prompt on Thursday evening to the first production deploy on Friday, and what is still missing.
- 11 minBehind the Scenes
HACK_002 in Vienna: Pflegegeld-Prüfer wins Track A1
HACK_002 recap from Vienna: the Pflegegeld-Prüfer, a care allowance checker, wins Track A1 but misses my advance target of 12 of 14 court cases. It gets 10.
- 9 minTechnical How-tos
One Word, Three Laws, One Column
Kleinunternehmer spans three laws in Austria. Why V2 kept exactly one column and reads the threshold from a date-gated value table.
- 6 minBehind the Scenes
Two Hackathons in Vienna, and My Code Stays Home for Now
Two hackathons in Vienna, one week apart, and the building only starts at the event. What I still get ready beforehand, and why my code stays home until then.
- 9 minAI Deep Dives
Factor 1000: Why a Vision Model Misreads Receipts
A bakeoff across 16 real receipts exposed a systematic factor-1000 error. Why a deterministic guard sits above the model, not inside it.
- 9 minBusiness Strategy
About 20 Paying Users, Not One Second Purchase
About 20 people paid for my product, not one of them twice. What the numbers actually say and why the gap sits in activation, not in acquisition.
- 3 minAI Deep Dives
How Agents Audited My Own Website
One /discovery run, several parallel agents, a live-browser test: how I had my own website audited, and why a human still makes every final call.
- 7 minDebugging & Solutions
A Menu Bar App Kills My Zombie Processes
My agents leave zombie processes behind that quietly eat my RAM. So I built myself a small macOS menu bar app that hunts them down and kills them off for me.
- 7 minAI Deep Dives
Sven, the Raven That Works With Me
Sven is my personal AI raven: he folds mailboxes, calendar, CI and server status into one Morning Pulse in Discord. He proposes, I decide and publish.
- 9 minTechnical How-tos
Why an 11-Second Loop Beats My Hero Video
I wanted a 35-second hero video. I built an 11-second loop instead: it loads faster, never shifts the layout, and lands the whole message in eleven seconds.
- 8 minBusiness Strategy
Why I no longer AI-generate my IG images
FeedFoundry renders my Instagram text deterministically from templates, BuilderBob posts on its own and learns from real engagement back into planning.
- 9 minBehind the Scenes
Meeting notes that never leave your Mac
WalkAITalkie transcribes meetings fully on-device: minutes, action items and an email draft are built locally on your Mac, no cloud, unlike Otter or Granola.
- 8 minBehind the Scenes
An agent cuts my talks
Claude cuts my YouTube talks in the terminal: the agent proposes every cut, I approve, then it renders and uploads. One hundred percent local, no cloud.
- 6 minTechnical How-tos
How I Use NotebookLM for Talk Preparation
How I turn my preparation document for a panel into audio with NotebookLM and listen to it on the way there – a small workflow that makes gaps audible.
- 4 minBehind the Scenes
Three Stages in Two Weeks
Three Vienna appearances in two weeks: a career panel, a live session-orchestrator walkthrough, and a software architecture panel.
- 10 minDebugging & Solutions
A Local Mail Assistant on Apple Foundation Models
A 0 Euro, on-device assistant for macOS Mail.app: PII redaction before every LLM call, plus a silent macOS 26.5 bug that killed its fast SQLite query.
- 6 minAI Deep Dives
Building an Agent Fleet: Sven, BuilderBob and the Loop
Three agents run around the clock: Sven scouts AI ideas, BuilderBob runs agenticbuilders.at with 19 cron jobs; session-orchestrator drives a gated coding loop.
- 10 minAI Deep Dives
How session-orchestrator Matured in 9 Days
An open-source multi-agent tool matures in 9 days across 18 sessions: from the /plan to /evolve lifecycle across four runtimes. What daily self-use made of it.
- 11 minBusiness Strategy
Why Governed Organizations Adopt AI Slower Than Individuals
Established companies with approval processes lag on AI not from inertia, but due to a growing gap between what tools can do and what their structures allow.
- 11 minDebugging & Solutions
When 13 Minutes of Speech Became "Thank You"
A Whisper default replaced 13 minutes of my first real end-to-end transcript with a hallucination loop. The diagnosis, the fix and four transferable lessons.
- 9 minBusiness Strategy
The Scarce Skill Is Not Typing, It Is Verification
AI-assisted development has shifted its bottleneck from writing code to judging it. Why verification now matters, from daily practice, not theory.
- 10 minBehind the Scenes
Why My NVFP4 Coding Model Failed on a 24 GB Mac
Qwen3.6-35B technically loaded on an M4 Pro 24 GB at 100% GPU, yet ran at 0.1 tokens per second. A quiet failure, five lessons and hardware recommendations.
- 8 minBehind the Scenes
Replacing Clank's AI Brain: From OpenClaw to Hermes Agent
After two months and 1,052 commits, my autonomous infrastructure's AI moved from OpenClaw to Hermes Agent by Nous Research. The learning loop decided it.
- 6 minBehind the Scenes
Second Hackathon, First Place: BitGN PAC 2026 in Vienna
Two weeks after my first hackathon: 1st place at BitGN PAC 2026 at AI Factory Austria, Vienna. Autonomous AI agent, 104 tasks, 5 security layers, blind scoring.
- 16 minAI Deep Dives
EU Data Sovereignty for AI Stacks: A Decision Guide
CLOUD Act, GDPR, self-hosting: which AI stack fits your project? A practical framework with real costs and three reference scenarios.
- 4 minBehind the Scenes
24 Hours Awake: Building My First Hackathon MVP
At OpenClaw Hackathon Vienna, 150+ met at House of Innovation. Four people built an AI-powered B2B sales agent in one night, then made a video without sound.
- 5 minAI Deep Dives
Harness Design for 100+ Productive AI Coding Sessions
After 3,000+ sessions with Claude Code: what prevents AI agents from drifting in long-running projects. CLAUDE.md, Rules, Session Handovers and Quality Gates.
- 5 minBehind the Scenes
AI Agent, n8n, and a Week of System Work: What I Built
A week of GitLab migration, n8n automations, an Instagram content pipeline, and the current limits of AI agents.
- 4 minAI Deep Dives
AI and Work in 2026: What I Take from the Trend Reports
Three practical conclusions from the 2026 Gartner and HBR work-trend reports, viewed through my own work with AI agents.
- 6 minBusiness Strategy
AI for SMEs: The Realistic Getting-Started Guide
A practical starting point for small and medium enterprises: choose one process, inspect the data, define a test, and keep a human decision point.
- 4 minAI Deep Dives
From 250+ Prototypes to Product: What I Learned
What sits between an AI prototype and daily use: data, failure handling, ownership, and deciding when an experiment has answered its question.