Software engineer for agentic AI and open source. Building systems in Düsseldorf since 2023 where AI works for a business: custom software, connected data, agents with clear limits. Speaks at meetups about Claude Code, and about checking agents instead of trusting them.
Works with
AI agents · TypeScript · Claude Code · Model Context Protocol · AI for SEO
Claude Code Meetup, Mannheim · Hosted by Accenture
Stop prompting. Start engineering loops.
Invited by Accenture as an expert on applied AI and agentic systems, in front of an enterprise audience. The topic that evening: loop engineering, meaning AI agents that work in loops and check themselves. The thesis: the agent does not grade its own work. It writes the pull request, a second agent with a fresh context and read-only access scores it against five criteria. Same model, same prompts. The grader has nothing to defend.
Stop prompting. Start engineering loops. That was my talk in Mannheim.
It was the Claude Code Meetup, hosted at Accenture, with three talks on the evening.
One piece of my talk. The agent doesn't grade its own work. It writes a PR, then a second agent with a fresh context and read-only access scores it against five criteria. Same model, same prompt quality. The difference is that the grader never saw the work happen, so it has nothing to defend.
Thanks to Hans-Peter Erl for the invitation and to Accenture for having us.
Loading sends your IP address and browser data to LinkedIn. LinkedIn may set cookies, associate your visit with your profile and process data in the USA. You can close the post at any time. Privacy details (German)
Code with Claude, London · Invited by Anthropic
Workshops with Anthropic engineers
The invitation came from Anthropic's Head of Community, prompted by open-source AI agent projects on GitHub. On site: workshops, each run by Anthropic engineers, all of them attended. Managed agents, memory with background curation, decomposing an orchestrator into focused subagents. Taking home: do evals properly, decompose more.
That's a wrap on Code w/ Claude London.
Big thanks to Anthropic for the invite. Kicked off by Boris Cherny. Hearing him talk about his own builder roots hit different as a software engineer in the room.
A few highlights from the workshops: Isabella He on shipping your first Managed Agent. Kevin C. on Memory and Dreaming, a memory store as a filesystem where each entry has its own path and edit history. William Steuk on agent decomposition: when an orchestrator's tool catalog gets too big, push tools down into focused subagents.
Taking home: do evals properly, try dreaming in a side project, decompose more.
Loading sends your IP address and browser data to LinkedIn. LinkedIn may set cookies, associate your visit with your profile and process data in the USA. You can close the post at any time. Privacy details (German)
Positions
STRIQFounderMeerbusch near Düsseldorf
My Agentic SEOFounder and CEO, with Luke McCormacksince June 2025
HaveDevsSoftware Engineer, freelancesince August 2024
marketer UX GmbHIntegration & Software Engineersince August 2023
