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.
Category: AI Deep Dives
9 posts in this category.
- 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 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.
- 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.
- 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.
- 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
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.
- 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.