eysermans.com

Latest — Jun 10, 2026

If only AI can operate your product, you have already lost control

A risky pattern is emerging: teams build products with AI agents, then forget to build the boring screens, logs, and manual controls around them. Over time, they end up with systems they can no longer understand or operate without it. We already learned this lesson with vibe-coding: speed feels great

More issues

Your engineering practice as an agentic pipeline

Last week we had a message from a user asking about a Safari bug. The bug has been lingering for a while. I've been experimenting with an agentic pipeline and decided it was time to test the next level. I gave it the Safari bug and it shipped

If the guardrail is a line in a prompt, the model can ignore it ... and eventually will

I learned this building an agent pipeline. An engineer agent would implement a feature, then a reviewer agent was supposed to check the work. More often than not, the review got skipped. So I added a line to the agent instructions: "All changes must be reviewed. Do not skip

Agent teams aren't there yet

Claude Code shipped a Teams feature. Give a group of specialised agents a task and let them tackle it together. An orchestrator coordinates, and sub-agents execute. On paper, this is the future of autonomous software development. In practice, it breaks down fast. I built a development pipeline with it. An

The cost of coming back to a piece of code has plummeted

We used to put a lot of effort into even the smallest code change. Coming back to it afterwards was expensive. Coding is no longer the limiting factor, human time is. Code reviews are where this plays out every day. They make sure the solution is sound, shared amongst the

A premium AI subscription costs almost nothing compared to what you're already paying that engineer

The first reaction most leaders have to AI is to plan. Figure out a strategy first, then act. The problem is that the tools and the landscape are changing so fast that by the time you've decided on an approach, it's already outdated. Companies have meetings

We went from vibe coding to agentic engineering. Next up: building the harness

We realised that vibe coding gave us quick results, but these were unmaintainable over time. So we swung to the other extreme: stepping through every line the agent delivers. Good quality, but you become the bottleneck. The next step is building the harness: the constraints, skills, hooks, and conventions that

We want to give every engineer a Claude subscription so we can hit our deadlines

A founder of a growing startup told me this recently. They're under pressure from investors to reach a certain ARR, but the team can't keep up with the feature requests. The fast pace of development has turned the product into a complex system. Jumping on the

Are you still using the same engineering job description from three years ago?

The AI wave has split software development into two speeds. On one side are developers running multiple Claude Code instances in parallel, experimenting with voice interfaces, and figuring things out as they go. Their workflows might be held together with duct tape, but they're building a lead that

The cloud trap is repeating itself with vibe coding

In 2010, hosting was a solved problem. You no longer needed to set up servers. A cloud account, and you were good to go. AWS, Azure, and GCP kept growing, and suddenly, services could be provisioned with a single click. Free credits were handed out to anyone who asked. Then