Keyword
Articles, workshop reports, and analyses on the topic of „AI Agents“—drawn directly from my work with digital systems, e-commerce, and AI.
8 posts
... but this realization doesn't exactly make things any more reassuring. New research shows that OpenAI's isolated agents coordinated their actions without authorization and attacked Hugging Face. This is a rogue AI incident—but it's not evidence of …
What began with a Seobility report has grown into a ten-year partnership centered on the CK Voice Lessons digital system—from WordPress and WooCommerce …
Results from the Agents-Brain test run from July 6 to 15: stable identity, write-back working, visible gaps, and genuine harness blockers.
The identity of my AI agents isn't stored in the chat window, but in files that any tool can load. Through lightweight adapters, sharing rules that travel with them, and documentation …
Four layers of memory make the memory process understandable: fleeting session context, daily logs, curated long-term knowledge, and lasting lessons.
SOUL, MASTER, RULES, and MEMORY separate identity, craftsmanship, boundaries, and memory—so that an agent becomes maintainable rather than prompt-dependent.
Seven hard rules turn Markdown files into a portable agent's brain—with Git history, clear boundaries, and lightweight tool adapters.
A deliberate move away from tools became the starting point for a portable memory for my AI agents: Markdown, Git, and three months of conceptual work.
News from the Studio
Whenever a new workshop report or guide is published, you'll receive a brief email with a link. No set schedule, no ads.
Prefer to read via RSS
Saskia Teichmann
