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.
Topic: Lessons
17 posts on this topic.
- 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.
- 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.
- 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.
- 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.
- 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.