Peter Eysermans

I’m a CTO-in-residence at madewithlove. I write and speak about AI in software teams, product engineering, and technical leadership.

This is the home for my writing, talks, and the projects I’m building around agentic engineering.

Now

Now — building stadsgeheugen.be · running local models on the LLM lab

Your company needs more than an LLM subscription madewithlove 10 Jul

Handing everyone an LLM subscription gives them a model. A shared, self-hosted agent gives them a configured environment with company context, connected tools, and clear boundaries. Why a company should own that layer rather than rent it, and how to start small.
My email agent invented a prompt injection, then fell for it madewithlove 1 Jul

An autonomous email agent hit a missing script, spiralled through 25 pointless shell calls, then fabricated email content including a prompt injection, and acted on it. The fix is not more warnings. It is structural validation before the model ever sees the data.
The boring parts make AI agents production-ready substack 1 Jul

We have all been in the AI loop of hell, where the agent keeps going in circles to spoon-feed us the same knowledge base

All writing →