Blog

Agentic engineering — from the trenches.

Page 2
chronological
If You Ship Faster, Someone Still Has to Click

If You Ship Faster, Someone Still Has to Click

We automated the coding. The PRs. The CI. Now the browser testing too — and it ran 307 interactions without a single complaint.

March 10, 2026 agentic, qa 9 8 min
Read more →
From Soft Trust to Hard Walls: Our Journey Toward Safe AI Agent Autonomy

From Soft Trust to Hard Walls: Our Journey Toward Safe AI Agent Autonomy

We run 18 AI agents with scoped instructions and logging. It works — until it won't. Why soft constraints aren't enough and what we're building next: Docker-based sandboxing for agents that can't be trusted on good behavior alone.

March 10, 2026 agentic-engineering, security 7 12 min
Read more →
The 97% Bundle Cut: Why AI Agents Need Human Expertise

The 97% Bundle Cut: Why AI Agents Need Human Expertise

An AI agent built our blog system. It worked. It also shipped a ticking time bomb. Here's why human expertise matters more, not less, in the age of agentic engineering.

March 9, 2026 agentic-engineering, architecture 10 8 min
Read more →
From Beta Tester to Agentic Engineer: A Timeline

From Beta Tester to Agentic Engineer: A Timeline

A chronological account of how I went from treating AI as a smart autocomplete to running 18 specialized agents on a production engineering pipeline.

March 9, 2026 timeline, journey 10 7 min
Read more →
The Clean Slate Is Gone: Claude Code's Memory and the Autonomous Workflow Problem

The Clean Slate Is Gone: Claude Code's Memory and the Autonomous Workflow Problem

Claude Code now remembers things you didn't tell it to. For interactive use, that's a nice feature. For autonomous pipelines, it's a different problem entirely.

March 9, 2026 agentic-engineering, claude-code 9 8 min
Read more →
Archaeologist Mode: Mining 700MB of AI Conversation Logs

Archaeologist Mode: Mining 700MB of AI Conversation Logs

Claude Code keeps full conversation transcripts. I mined 700MB of them to reconstruct 20 lost journals and find the founding conversations I thought were gone.

March 9, 2026 persistence, memory 8 5 min
Read more →
I Let AI Build This Website — Here's What Actually Happened

I Let AI Build This Website — Here's What Actually Happened

Building CodeWithAgents.de with AI agents. What worked, what broke, what surprised me.

March 8, 2026 agentic-engineering, case-study 7 12 min
Read more →
The AI Slop Problem: When Everyone Can Publish, Nobody Can Filter

The AI Slop Problem: When Everyone Can Publish, Nobody Can Filter

AI makes content production trivial. That's not the revolution — surviving the flood of mediocrity is.

March 6, 2026 ai-slop, quality 18 5 min
Read more →
Built in One Session: From Empty Repo to Deployed Presentation

Built in One Session: From Empty Repo to Deployed Presentation

I started with an empty Git repository and ended with a fully deployed mobile-first presentation on GitHub Pages — without writing a single line of code myself.

March 1, 2026 agentic, presentation 3 8 min
Read more →
97.78% Confidence: Building a Receipt Scanner with AI Agents

97.78% Confidence: Building a Receipt Scanner with AI Agents

Three phases, five critical bugs, and what 97.78% OCR confidence actually looks like when real users upload real photos.

February 25, 2026 ocr, side-project 4 6 min
Read more →

Ready to level up?

Get in Touch