Skip to main content
The lively case study

Typing
was yesterday

Our articles follow a clear process: Two AI systems generate content based on predefined filters and topics. The information sources are editorial contributions, combined and prepared using our system prompt. Text matching against the sources ensures that we do not simply copy. We review every output before publication, edit and supplement it. The sources are linked - because nothing comes from nothing.

RSS → CLAUDE → NANO BANANA → TYPO3 UPDATES TWICE DAILY
Pipeline status
Last update
vor 6 Std.
Published today
6 Artikel
Pending approval
1 Entwurf
RSS Sources
5 Feeds
Current issue

Nine items. Always.

What is written here is new. What becomes old disappears. We stay at nine — and would rather follow the topic than the stack.

Team building Must read AI
18.11.2026 · 4 min · AI

AI in the developer team: Why juniors are still needed

AI assistants are changing daily development work. A CTO warns against forgoing junior talent as a result – and makes a point that is also relevant for clients.

1 Source linked → Read more
AI models Must read AI
17.11.2026 · 5 min · AI

AI coding at a plateau: Moonshot shifts focus, Qwen4-Max lowers costs

Moonshot AI sees hardly any model progress in programming and is aligning Kimi towards the natural sciences. Alibaba cuts the cost per task by 62 percent with Qwen4-Max. The lever is shifting from benchmarks to processes.

2 Sources linked → Read more
AI strategy Must read AI
16.11.2026 · 5 min · AI

AI as infrastructure: why isolated tools hold companies back

Many companies have so far used artificial intelligence only selectively as a tool. Those who understand it as infrastructure, by contrast, must restructure roles, processes and systems – and that is precisely where the benefit is decided.

1 Source linked → Read more
AI safety Must read AI
09.11.2026 · 5 min · AI

When AI coding agents carry secrets into public repositories

A recent report describes how credentials can end up in public repositories via AI coding agents. The trigger is a convenience feature. A reason to review guardrails and secret handling in the development process.

1 Source linked → Read more
AI development Must read AI
09.11.2026 · 5 min · AI

Vibe coding in practice: platform in a weekend

Andrej Karpathy built a curated video platform from 43 million Hacker News comments in a weekend using Claude Code. What this example says about prompt-driven development – and what it does not say.

1 Source linked → Read more
AI tooling Must read AI
05.11.2026 · 5 min · AI

Artcraft: AI image editing as an alternative to Photoshop

A developer is working with Artcraft on an AI-powered alternative to Adobe Photoshop. The project is still in development – a good opportunity to check your own image production for dependencies.

1 Source linked → Read more
AI development Must read AI
04.11.2026 · 4 min · AI

One week to the prototype – and what still remains to be done afterwards

Two OpenAI engineers designed a complete device with an AI model in under a week – enclosure, circuit board, firmware. However, several rounds of corrections were needed before manufacturing.

1 Source linked → Read more
AI tooling Must read AI
04.11.2026 · 5 min · AI

Vibe Coding: From requirements profile to a working prototype

Prompt-driven development shortens the path from idea to clickable prototype. Tool selection, precise requirements and a robust review of what the AI outputs remain decisive.

1 Source linked → Read more
AI development Must read AI
03.11.2026 · 5 min · AI

Vibe coding without review: when AI code goes online unchecked

AI tools turn ideas into working applications in hours – even for people without programming knowledge. However, anyone who cannot evaluate the resulting code is merely shifting the risk into operation.

1 Source linked → Read more
Workshop report

How our articles are created

Our blog is a semi-autonomous system. Four stations, clear responsibilities and a human who is not optimised away.

01 · Extraction & Cluster

Claude

RSS

Selected RSS feeds from the fields of IT, software development, TYPO3 and AI are filtered by system prompt. We maintain sources manually — no auto-discovery.

Result
Curated topic articles
02 · Writing

Claude

Article shortlist

Claude reads the new posts, groups them thematically and writes a German summary — with references to all original sources - the human heart of this step is our system prompt.

Result
Finished product
03 · Image material

Nano Banana

Illustration

Nano Banana Pro generates a symbolic image per article — in a narrow visual language that we specify. No identifiable people, no logos. It could be a little more varied - but the system learns.

Result
1 symbolic image
04 · Approval & Publish

TYPO3

Manual click

In the TYPO3 workflow, every draft goes to a real person — Christoph. The article only becomes visible after approval. No auto-publish. Classification as Must Read is also done manually. We decide what is really important.

Result
Article with Schema.org details
5
curated RSS feeds
2
Pipeline runs per day
100 %
manually approved
0
Auto-Publish
What you see here,

We can also build for you.

Pipelines with clear approval, AI as a tool, TYPO3 as the backbone. We would be happy to show you which of these suits your company — in 30 minutes.

Barrierefreiheit

Passen Sie die Darstellung an Ihre Bedürfnisse an. Ihre Auswahl bleibt auf diesem Gerät gespeichert.

Schrift und Text

100 %

Schriftgröße der Seite

Farben und Kontrast

Lesen und Bedienen